TCYB2026

Abstract:
Many real-world datasets contain high-dimensional heterogeneous features, exhibiting complex and evolving distributions. The coexistence of high dimensionality and heterogeneity poses challenges for reliable feature selection and real-time analysis, while most existing feature selection solutions either assume that the features are of the same type or struggle to handle extremely high-dimensional features. Moreover, these methods are usually designed for static datasets, neglecting the dynamic capture of heterogeneous interfeature relationships in real-time environments. To address these challenges, we propose a new feature selection method called graph-unified adaptive decision boundary enhancement (GRADE) for online heterogeneous feature selection (OHFS). To provide a reliable foundation for evaluating feature subsets under dynamic and heterogeneous data streams, an incremental graph-unified metric (IGUM) is introduced. It mitigates information loss between heterogeneous features by leveraging graph structures to unify feature-value-level and interfeature-level relationships. With such a consistent relation measure, an adaptive density-guided neighborhood relation (ADNR) is proposed to assess the capability of selected feature subsets to classify samples. Since it dynamically captures prominent neighborhood regions, local decision boundaries can thus be precisely delineated. It turns out that GRADE can obtain a more concise feature subset while achieving competitive classification accuracy. Besides, GRADE is parameter-free and very efficient compared with state-of-the-art methods. Comprehensive experimental evaluations, including significance tests, ablation studies, efficiency evaluation, and case studies, have been conducted to verify the efficacy of GRADE.

Abstract:
evolutionary multitask optimization (EMTO) aims to optimize multiple tasks simultaneously. In recent years, various EMTO algorithms based on knowledge transfer (KT) have been developed to utilize the information from other tasks and promote the optimization of the current task. However, most of them often use the fixed KT probability (ktp) and a single evolutionary search operator (ESO) during the evolution process, which lacks an adaption mechanism and cannot meet the different searching requirements among multiple tasks. Fuzzy system can effectively express the qualitative knowledge with unclear boundaries, which has good adaptability to nonindependent EMTO. Therefore, this article proposes a fuzzy adaptive multitask optimization (FAMTO), which employs a fuzzy adaptive transfer (FAT) strategy for intertask KT to achieve the adaptive adjustment of the ktp by designing a comprehensive evaluation in KT performance from two aspects, including the survival rate and the quality of transferred offspring. In FAT strategy, the fuzzy logical is employed to handle the interdependent relationships among multiple indicators, further achieving the more robust and adaptive ktp adjustment. In addition, an individual-based random selection (IRS) strategy is developed for each individual to choose the suitable ESO for intratask self-evolution in fuzzy adaptive multitasking optimization (FAMTO). Experimental results show that FAMTO achieves significantly better performance than other state-of-the-art EMTO algorithms on two well-known multitask benchmarks, CEC17 and CEC22. Furthermore, FAMTO is applied to a real-world multitask planar kinematic arm control application, demonstrating its applicability. Finally, the extended experiments on many-task optimization problems (MaTOPs) illustrate the scalability of FAMTO.

Abstract:
This article explores the controllability robustness of simplicial complexes under both node-based and edge-based attacks. By considering network topology, dynamical properties, and higher order interactions, we propose a universal nodal dynamical model applicable to simplicial complexes of arbitrary dimensions. Quantitative analysis reveals that both the quantity and spatial distribution of 2-simplices play a pivotal role in regulating the robustness of network controllability. These results highlight the critical impact of second-order interaction structures on network robustness and suggest that the underlying mechanisms, such as higher order topological connectivity and dynamical synergy, can be extended to elucidate how higher dimensional q -simplices ( q\gt 2 ) influence controllability robustness.

Abstract:
In the last decade, a variety of multiobjective evolutionary algorithms (MOEAs) with specific enhancements have been developed for solving multiobjective optimization problems (MOPs). In this article, unlike MOEAs, we provide a new artificial intelligence approach to solve MOPs, which adopts an imitation learning-based end-to-end method, namely AlphaMOEA. AlphaMOEA is entirely a model composed of neural networks that mainly follow the architecture of multitask learning (MTL). It has two training stages: the supervised learning (SL) stage and the reinforcement learning (RL) stage. In the SL stage, AlphaMOEA fits the solutions in the decision space provided by a number of selected MOEAs. Since neural networks in AlphaMOEA are composed of parameters with high dimensions, the fitting process can be viewed as a transformation of the solutions from a low-dimensional space into a high-dimensional space. This allows AlphaMOEA to obtain different valuable knowledge from a perspective of high dimensionality. Then, AlphaMOEA is trained in the RL stage to obtain good performance for MOPs with various problem characteristics in a self-driven manner. The RL stage relies on several designed components, including a similarity-based state design to measure the distance between solutions, an evolution operator-based action set to provide exploration behavior, and an indicator-guided reward to produce an incremental evaluation. Experimental results demonstrate that AlphaMOEA can learn valuable information about the decision space in high-dimensional representations, thereby achieving a desirable balance between exploration and exploitation. AlphaMOEA can further improve the performance for solving MOPs with various problem characteristics in a reasonable time.

Abstract:
This article focuses on the constrained maximal controllability of complex networks, which aims to maximize the generic dimension of controllable subspace of networks with a given candidate set of constrained input locations. To address this issue, we first transform it to a maximum general-cactus cover problem. By introducing network flow, this problem is further converted to a minimum-cost maximum-flow problem. An algorithm named minimum-cost maximum-flow-based general-cactus cover (MMGC) is proposed to achieve the optimal solution. Furthermore, a series of simulations on Erdős–Rényi networks (ERNs) and scale-free networks (SFNs) and applications in network controllability robustness demonstrates the effectiveness of MMGC. The simulation results have revealed that augmenting the number or range of inputs can enhance the controllability of networks, and the presence of multicyclic structures significantly strengthens the controllability robustness of complex networks.

Abstract:
Vision-and-language navigation (VLN) has garnered extensive attention in the field of embodied artificial intelligence. VLN involves time series information, where historical observations contain rich contextual knowledge and play a crucial role in navigation. However, current methods do not explicitly excavate the connection between rich contextual information in history and the current environment, and ignore adaptive learning of clues related to the current environment. Therefore, we explore a Prompt Learning-based strategy which adaptively mines information in history that is highly relevant to the current environment to enhance the agent’s perception of the current environment and propose a history-guided prompt generation (HGPG) framework. Specifically, HGPG includes two parts, one is an entropy-based history acquisition module that assesses the uncertainty of the action probability distribution from the preceding step to determine whether historical information should be used at the current time step. The other part is the prompt generation module that transforms historical context into prompt vectors by sampling from an end-to-end learned token library. These prompt tokens serve as discrete, knowledge-rich representations that encode semantic cues from historical observations in a compact form, making them easier for the decision network to understand and utilize. In addition, we share the token library across various navigation tasks, mining common features between different tasks to improve generalization to unknown environments. Extensive experimental results on four mainstream VLN benchmarks (R2R, REVERIE, SOON, R2R-CE) demonstrate the effectiveness of our proposed method. Code is available at https://github.com/Wzmshdong/HGPG.

Abstract:
Traditional evolutionary game theory (EGT) typically assumes fixed, well-mixed populations, neglecting the fact that agents in many real-world systems can strategically form or eliminate connections based on individual incentives. This article introduces a novel framework that integrates EGT with strategic network formation to model the co-evolution of strategies and intercommunity links. We consider populations in which agents interact primarily within their own communities but may establish external connections when such interactions yield higher payoffs. To formalize this, we propose a strategic connections model (SCM) based on the concept of pairwise stability that determines which subsets of agents from different communities form links, and how these links influence evolutionary dynamics. The SCM operates as a two-stage optimization process that accounts for mutual incentives and payoff improvements. Applying our framework to classical evolutionary games, we show that intercommunity connections reshape population-level outcomes. In the prisoner’s dilemma, cooperation—typically unstable in well-mixed settings—can emerge and persist under a simple benefit-to-cost condition. In the rock-paper-scissors ( RPS ) game, intercommunity links can alter or suppress the characteristic cycles observed, for instance, under replicator dynamics, affecting the long-term coexistence of strategies. In congestion games, our framework improves infrastructure usage and resource allocation, outperforming intuitive but nonstrategic connection choices. These results highlight the critical role of strategic intercommunity links in shaping collective behavior, offering new insights into the interplay between intercommunity and intracommunity dynamics in biological, social, and engineered systems, where such links can represent interactions among species, individuals, and/or machines within cybernetic environments.

Abstract:
This article investigates the differentially private leader-following consensus control (DPLFCC) problem for multiagent systems (MASs) operating on two-time scales. A new co-design framework with a private preserving scheme and a consensus controller is constructed by building a unique time-scale-dependent Lyapunov function. To achieve the ultimate mean-square leader-following consensus while maintaining differential privacy, the proposed strategy establishes a new distributed consensus controller with noise control for each follower. The initial state of the follower can be made more private by adjusting the noise control gain. It should be pointed out that controller-solving criteria and privacy level performances are designed depending on the time-scale parameter, thereby eliminating the numerical stiffness caused by the two-time-scale property. Furthermore, the results are extended to the leader’s privacy-preserving situation. Finally, the effectiveness of the developed algorithm is illustrated by numerical simulation examples.

Abstract:
Recently, the cross-modal retrieval task has gained significant attention with the advent of large-scale vision-language pretraining models, e.g., CLIP. These methods typically map the vision and language modalities into a shared embedding space and then build similarity relations based on the joint feature representations. Despite tremendous progress in this field, most existing methods still suffer from unreliable retrieval results caused by data and model uncertainties, which can arise from inherent data ambiguity or noisy pairs. In this article, we propose a novel cross-modal retrieval framework with aleatoric-epistemic joint uncertainty modeling (AEUM). AEUM is committed to providing reliable uncertainty estimation for both data (aleatoric uncertainty, AU) and model (epistemic uncertainty, EU), which are then used to correct the initial cross-modal similarity to yield more accurate retrieval results. Specifically, for AU, we introduce learnable semantic tokens for each modality to estimate the data-induced uncertainty in another modality, offering guidance on data complexity or ambiguity. For the EU, we leverage the efficient evidential learning paradigm to estimate model-induced uncertainty and incorporate it into the model’s predictions, thereby enhancing robustness against noisy data. Extensive experiments demonstrate the effectiveness and generalization of our method on multiple cross-modal retrieval benchmarks, including five video–text retrieval datasets (MSRVTT, LSMDC, MSVD, VATEX, and DiDeMo) and two image–text retrieval datasets (MSCOCO and Flickr30K). Our code is publicly available at https://github.com/cty8998/AEUM

Abstract:
Human-gaze–target prediction aims to predict the target point or object that humans are looking at in images. However, existing methods predominantly rely on vision-only features, which often struggle to capture the semantic context of small or occluded objects and lack explicit priors for precise head direction regression, leading to slow convergence and suboptimal performance. Therefore, we introduce VL-HTR, a novel vision–language learning method for human–target representation, which integrates multimodal knowledge from vision–language models (VLMs) to construct robust human–target relationships. Unlike traditional approaches, extracting multimodal features via pretrained VLMs enhances the model’s grasp of human–target knowledge through the learnable target class and direction context. Then, a language-guided query alignment (LQA) module is introduced to improve the semantic-aware object representation capability through vision–language query alignment. Finally, to accelerate the gaze point regression learning process, we design a language-guided direction prediction (LDP) module to introduce multimodal human gaze direction priors, thereby facilitating the human–target relationship construction. Extensive validations across two distinct tasks, i.e., gaze object prediction (GOP) and gaze target estimation, involving five challenging benchmarks, demonstrating that VL-HTR achieves superior performance and much faster training convergence.

Abstract:
Understanding the inter-relations and interactions between tasks is crucial for multitask dense prediction. Existing methods predominantly utilize convolutional layers and attention mechanisms to explore task-level interactions. In this work, we introduce a novel decoder-based framework, parameter-aware Mamba model (PAMM), specifically designed for dense prediction in multitask learning (MTL) setting. Distinct from approaches that employ Transformers to model holistic task relationships, PAMM leverages the rich, scalable parameters of state-space models (SSMs) to enhance task interconnectivity. It features dual state-space parameter experts (PEs) that integrate and set task-specific parameter priors (PPs), capturing the intrinsic properties of each task. This approach not only facilitates precise multitask interactions but also allows for the global integration of task priors through the structured state-space sequence (S4) model. Furthermore, we employ the multidirectional Hilbert scanning (MDHS) method to construct multiangle feature sequences, thereby enhancing the sequence model’s perceptual capabilities for 2-D data. Extensive experiments on the NYUD-v2 and PASCAL-Context benchmarks demonstrate the effectiveness of our proposed method. Our code is available at https://github.com/CQC-gogopro/PAMM

Abstract:
Ensuring safe driving while maintaining travel efficiency for autonomous vehicles (AVs) in dynamic and occluded environments is a critical challenge. This article proposes an occlusion-aware contingency safety-critical planning approach for real-time autonomous driving. Leveraging reachability analysis for risk assessment, forward reachable sets (FRSs) of phantom vehicles (PVs) are used to derive risk-aware dynamic velocity boundaries. These velocity boundaries are incorporated into a biconvex nonlinear programming (NLP) formulation that formally enforces safety using spatiotemporal barrier constraints, while simultaneously optimizing exploration and fallback trajectories within a receding horizon planning framework. To enable real-time computation and coordination between trajectories, we employ the consensus alternating direction method of multipliers (ADMMs) to decompose the biconvex NLP problem into low-dimensional convex subproblems. The effectiveness of the proposed approach is validated through simulations and real-world experiments in occluded intersections. Experimental results demonstrate enhanced safety and improved travel efficiency, enabling real-time safe trajectory generation in dynamic occluded intersections under varying obstacle conditions. The project page is available at: https://zack4417.github.io/oacp-website/.

Abstract:
The rapid development of deep learning-based image inpainting poses serious challenges to image authenticity. As inpainting methods continue to evolve, the inpainted images exhibit extremely high visual fidelity, presenting recognition difficulties to the forgery detection model due to differences in operational mode and forgery traces among methods. In particular, the detection performance tends to drop significantly in the testing phase when the test samples differ from the training data. To address this issue, we propose a test-time adaptive detection framework for image inpainting forgeries. First, we propose an image gradient-based metric that quantifies model uncertainty and orchestrates the entire adaptation process. Integrating this metric with sample-specific batch normalization (BN) statistics enhances the ability of pretrained models in the inference stage. Second, we introduce a cross-attention module as a side-tuning module, enabling the model to adapt dynamically to reliable test samples without altering the backbone network. To validate the effectiveness of the proposed method, we construct a dataset comprising synthetic images of multiple inpainting methods and design experiments under two scenarios of distributional bias. The results demonstrate that our proposed framework outperforms the existing baseline method, enhancing the adaptability and detection performance of the forgery detection model in dynamic environments.

Abstract:
In real-world scenarios, optimization problems generally exhibit multiobjective characteristics, necessitating a balance among conflicting evaluation criteria. An effective approach to multiobjective optimization (MOO) is to approximate the Pareto front. However, completely solving for the Pareto front incurs extremely high computational costs, making it almost infeasible in practical applications. In practical scenarios, decision makers (DMs) typically require only a single most preferred solution from the Pareto-optimal set. Existing optimization methods often struggle to incorporate real-time DMs’ preferences during the optimization process. To address this limitation, this article proposes a preference-aware Bayesian optimization (PABO) framework for interactive decision-making that seamlessly integrates DMs’ feedback throughout the entire optimization process. By embedding preference information into the candidate solution generation stage, PABO dynamically adjusts the balance between exploration of uncertain regions and exploitation of preference-aligned solutions, thereby achieving efficient preference satisfaction. Experiments on benchmark functions and real-world engineering cases demonstrate that PABO achieves comparable or superior solution quality with significantly fewer expensive evaluations than state-of-the-art methods. This achievement indicates that PABO demonstrates significant advantages in improving optimization efficiency and reducing costs, providing a more feasible technical approach for the practical application of MOO problems.

Abstract:
This article presents a new design of self-triggered impulsive control (STIC) for prescribed-time stability (PTS) of nonlinear systems. A prescribed-time convergent function is proposed to determine the impulsive control strength together with the information of the impulsive interval. Different from previous impulsive control strategies, the impulsive control with designable strength is implemented under a non-Zeno self-triggering mechanism (STM) with enforced bounded execution times and the triggering times established by a comparison system. The involvement of the upper bound of the impulsive interval in both control strength and STM not only renders the closed-loop prescribed-time stable but also ensures decreasing impulsive strengths as the time approaches the prescribed time. The validity of the proposed STIC scheme is verified by the application to prescribed-time synchronization of reaction-diffusion neural networks (RDNNs) and numerical examples.

Abstract:
Multiagent reinforcement learning (MARL) has shown strong performance in cooperative tasks. However, most existing approaches are designed for single-task scenarios and struggle to adapt to complex and dynamic environments. Multitask MARL methods aim to improve adaptability by sharing policies across tasks, but they often suffer from negative transfer due to conflicting task-specific knowledge. To address this, we propose dual-policy fusion for multitask MARL (DPF-MTMARL), which explicitly integrates a shared policy for leveraging common knowledge and task-specific policies for capturing task-specific information. Specifically, in DPF-MTMARL, we propose a learning method to efficiently train the task-specific policies and provide corresponding theoretical analysis. Additionally, we derive the theoretical conditions for decentralizing the joint policy and enforce these conditions through a regularization term during training. Extensive experiments demonstrate that DPF-MTMARL significantly outperforms state-of-the-art baselines in both homogeneous and heterogeneous task sets, effectively mitigating negative transfer and enabling robust multitask learning.

Abstract:
Time-series forecasting is considered a critical task with extensive applications across diverse domains. However, effectively capturing both cross-dimension and cross-time dependencies in nonstationary time series remains a significant challenge, particularly due to the confounding effects of environmental factors. These factors often introduce spurious correlations that obscure the learning of meaningful temporal features. In this article, the novel framework Caformer (Causal Transformer) is proposed for time-series forecasting grounded in causal reasoning, the science of identifying causality. The framework consists of four key modules: the dynamic learner, environment learner, temporal learner, and decompose learner. The dynamic learner uncovers dynamic interactions among features to model cross-dimension dependencies, while the temporal learner infers cross-time dependencies under causal constraints. The environment learner, together with the decompose learner, extracts environmental factors and applies a backdoor adjustment to mitigate the confounding effects on the time series. Extensive experiments demonstrate that Caformer achieves the state-of-the-art performance in both long-term and short-term forecasting. It achieves up to a 26.2% mean square error (mse) reduction on the traffic dataset and 21.8% on the electricity dataset compared to PatchTST, with consistent gains across eight long-term benchmarks. On the M4 dataset, Caformer ranks first across all 15 short-term forecasting categories. In addition to strong predictive accuracy, Caformer provides interpretable insights into the learned dependencies.

Abstract:
Multimodal multiobjective optimization aims to provide diversified acceptable decisions (ADs), including global optimal solution with consistent objective evaluations and local optimal solutions (LOSs) with acceptable objective evaluations. However, the discrimination of LOSs highly depends on the distribution of candidate solutions, which may result in the catastrophic elimination of LOSs to damage the diversity in the decision space. To address this problem, a local regularity model (LRM) method is proposed to improve the distribution of candidate solutions. There are three novelties of LRM. First, a hierarchical principal component analysis is developed to extract principal components for different nondominated sets. Then, the distribution features of different nondominated sets are described in segments by a small number of candidate solutions to construct LRM. Second, a self-organization strategy, based on the feature correlation and neighborhood violation analysis, is proposed to improve local fitting ability. Then, LRM are efficiently constructed to estimate the manifold of ADs. Third, a probability reproduction strategy is developed to reconstruct the population by LRM. Then, the population is reconstructed to enhance the distribution of candidate solutions in the decision space. Finally, the proposed optimization method is integrated into the popular multimodal multiobjective optimization algorithm to demonstrate its effectiveness in terms of the benchmark multimodal multiobjective optimization problem test suite.

Affiliations: Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China; Department of Control Science and Engineering, College of Electronic and Information Engineering, State Key Laboratory of Autonomous Intelligent Unmanned Systems, Frontiers Science Center for Intelligent Autonomous Systems, Ministry of Education, Shanghai Research Institute for Intelligent Autonomous Systems, Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China; Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China

Abstract:
This article focuses on nonconvex distributed composite optimization over time-varying multiagent networks, where each agent possesses a local objective function, composed of a nonconvex and smooth function plus a nonsmooth function. The network aims to minimize the sum of all local functions subject to local set constraints and global nonconvex coupled inequality constraints. The inherent nonconvex and nonlinear characteristics of the objective and constraint functions pose formidable challenges in developing efficient distributed algorithms with convergence guarantees. To tackle this intricate problem, a novel distributed linearized augmented primal–dual algorithm is designed by incorporating distributed tracking and dynamic consensus techniques. It is theoretically shown that, with appropriately chosen parameters, the proposed algorithm can find an \epsilon -Karush–Kuhn–Tucker (KKT) point. Specifically, the sequences of average optimality, constraint violation, and complementary slackness measure converge to zero at sublinear rates. Finally, a numerical application is presented to validate the effectiveness of the proposed algorithm.

Abstract:
Sensor drift, which is the deviation of measurements over time, can compromise controller performance and cause system instability. To address this challenge, this article proposes a proactive fault-tolerant control strategy for distributed parameter systems. The proposed strategy is based on a time-varying spatiotemporal model that captures system dynamics. The initial phase of this research involves designing an adaptive observer-based detector to identify the temporal and spatial locations of fault occurrences accurately. Subsequently, a joint state-and-fault estimator is developed to accurately reconstruct the fault profile, even in the presence of strong state–fault coupling. The controller provides real-time corrections based on the estimation results. A rigorous stability analysis of the closed-loop system is provided, and the effectiveness of the controller is validated through experiments involving two distinct fault scenarios.

Abstract:
Multigranularity knowledge modeling is an influential study for information processing and knowledge discovery in artificial intelligence (AI). A central research focus is the multigranularity representation and learning of knowledge structures. Among them, fuzzy rough sets (FRSs) have emerged as a representative method for characterizing uncertain knowledge. However, the existing FRS studies still exhibit two limitations: low robustness in knowledge acquisition and incomplete characterization of uncertainty. Hence, this article proposes a zentropy-enhanced multigranularity knowledge modeling framework for robust feature selection (ZeMG-FS). Specifically, we design a fast and adaptive multigranularity information granulation mechanism based on generalized granular-ball generation to effectively capture data distributions embedded in complex data. Then, the fuzzy rough approximation method is incorporated into the representation of multigranularity knowledge. Furthermore, we analyze the fundamental relationships and structures of the multigranularity knowledge model to introduce a novel multilevel zentropy. Unlike existing entropy measures, the primary consideration of the proposed zentropy is to match and enhance the performance of the proposed model. Finally, we design two feature evaluation criteria grounded in the model and apply them to feature selection. Extensive experiments demonstrate that our proposed methods achieve superior robustness and effectiveness compared with state-of-the-art approaches.

Abstract:
This article addresses a collective heterogeneous multiagent pursuit–evasion (MPE) game problem where pursuers cooperatively capture escaping evaders. The analytical challenge of the present design lies in solving the associated coupled Hamilton–Jacobi–Isaacs (HJI) equations induced by the additional interacting roles in the MPE game while ensuring the achievement of the Nash equilibrium. To tackle this issue, a gaming framework is accordingly proposed to solve the coupled HJI equations. Sufficient conditions are derived to guarantee both the capturability and Nash equilibrium of the proposed collective MPE gaming scheme. Finally, numerical simulations are conducted to verify the effectiveness of the present MPE gaming strategy.

Affiliations: Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR, China; School of Automation and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China; Beijing Key Laboratory of Air-Ground Collaborative Intelligent Control for Autonomous Transportation, North China University of Technology, Beijing, China; State Key Laboratory of Intelligent Control and Decision of Complex Systems and the School of Automation, Beijing Institute of Technology, Beijing, China; School of Control Science and Engineering, Shandong University, Jinan, China

Abstract:
With the increasingly integrated nature of networked control systems (NCSs), security has become a challenging issue for their widespread deployment. Although resilient control methods against various attacks have been reported, the analysis and design of defense mechanisms for NCSs still require fresh efforts. To this end, this article is concerned with the security control of a class of NCSs vulnerable to smart false data injection (FDI) attacks. Specifically, the scenario of output tracking of NCSs is considered, where the communication between sensors and controllers, as well as between controllers and actuators, is compromised by sophisticated malicious adversaries. To enhance security, peer-to-peer (P2P) networks with blockchain technologies are utilized instead of traditional communication patterns to transmit measurement and control signals. Unlike previous work, this work carefully designs an optimal blockchain consensus policy by perceiving the performance of NCSs and develops a resilient dynamic output tracking controller based on this policy. The formulation of the consensus policy is derived from a game-theoretic framework that models the interaction between the blockchain and the malicious adversary, enabling deep integration of blockchain technology with NCSs. With the proposed approach, the adverse effects of malicious FDI attacks can be greatly mitigated by balancing energy consumption and tracking performance. Finally, the applicability of the proposed security control strategy is verified in a real-world power system.

Abstract:
In music streaming applications, next music tracks are typically played automatically and require less consumption time than many other contents (e.g., books and movies). These characteristics potentially lead to long and noisy user listening history, making generic sequential recommendation models more error-prone when modeling user interests. To bridge the gap, we propose to retrieve representative music tracks from the original listening history for recommendation. Differing from existing user behavior retrieval techniques, we pursue a fine-grained, content-based, and temporal user behavior retrieval framework, namely FactUBR, to better exploit music track content and the fine-grained connections between temporally dependent tracks in the listening history. Technically, FactUBR consists of a reinforced content-based retrieval module (RCB) and a differentiable temporal-channel (DTC) retrieval module. RCB follows a reinforcement-learning procedure to optimize sequential retrieval decisions based on content differences between the state and the observation, maximizing rewards of retrieval diversity and recommendation performance. DTC evaluates the fine-grained correlations between temporal listening segments and the candidate music track, and employs the perturbed maximum technique for hard retrieval optimization. Extensive experiments on two public music recommendation benchmarks demonstrate that FactUBR can enhance various representative sequential recommendation models and outperform state-of-the-art (SOTA) behavior retrieval techniques.

Affiliations: School of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an, Shaanxi, China; School of Computer Science, the School of Artificial Intelligence, OPtics and ElectroNics (iOPEN) and the Key Laboratory of Intelligent Interaction and Applications, Ministry of Industry and Information Technology, Northwestern Polytechnical University, Xi’an, Shaanxi, China; Zhijian Laboratory, Rocket Force University of Engineering, Xi’an, China

Abstract:
Feature selection is one of the hot issues in machine learning. It reduces storage pressure by effectively screening features and has become a very practical data preprocessing method. At present, most feature selection algorithms apply \ell _2,1 -norm on the transformation matrix to calculate the scores for all features and then select appropriate features according to these scores. But their sparsity is limited, and meaningless regularization parameters increase the cost, making it prone to falling into local optimum. To solve the above difficulties, this article proposes a novel max–min robust unsupervised feature selection via sparse subspace (MMRUFS), which considers both the reconstruction term and variance term of data, so that the model can not only fully retain the original information of data, but also make the data more dispersed. Second, \ell _2,0 -norm constraint is used on the transformation matrix to directly select the optimal feature subset, avoiding the fine-tuning of regularization parameters. To enhance the robustness, MMRUFS carefully designs mark weight vector to make the model treat normal samples and outliers differently and achieves the effect of anomaly detection. Finally, MMRUFS is solved by designing the surrogate matrix, and its convergence is strictly guaranteed, experimental results reveal that MMRUFS outperforms other feature selection algorithms on multiple real-world datasets.

Abstract:
Test-time few-shot object detection (FSOD) represents an innovative approach for identifying novel categories using a limited number of support examples, obviating the need for model fine-tuning. Despite advancements, existing FSOD methods, including our prior work, continue to grapple with challenges posed by domain/category shift and limited data availability. Building upon our previous research on test-time FSOD, this article proposes a novel dynamic prototype fusion network (PFN) to overcome these limitations. To mitigate the impact of the distribution shift, a dynamic prototype refinement method is introduced that updates prototypes from supporting images in an adaptive manner. Further, limited samples are mitigated through exhaustive exploitation of information within support images. Specifically, we design a dual-level multiscale information integration approach that effectively fuses information across different network layers and image scales, enhancing the model’s discriminating capabilities. Additionally, a mask-based preprocessing technique harnesses segmentation labels on support samples, effectively suppressing the adverse impact of background noise on model accuracy. Notably, to align with the constraints of test-time scenarios, model parameters remain fixed during the configuration step, with only prototypes being updated each time users input novel supporting samples. As a result, our method achieves superior performance over existing state-of-the-art FSOD methods on multiple benchmarks, demonstrating remarkable potential in the realm of FSOD. The code is available at https://github.com/CatfishW/TIDEV2

Abstract:
This article focuses on the fixed-time (FXT) and preassigned-time (PAT) bipartite output regulation of heterogeneous linear multiagent systems (MASs), where both cooperative and adversarial interactions among neighboring agents are considered under a signed graph framework. Since the exosystem information may be unavailable to the agents, an FXT distributed observer and an FXT adaptive distributed observer are designed to accurately identify the exosystem’s coefficient matrix and state, respectively. Subsequently, in the absence of the stabilizability and detectability of coefficient matrices, distributed state- and output-feedback control protocols are designed to ensure FXT bipartite output regulation. Besides, for a preset convergence time, the bipartite output regulation is explored by developing control protocols incorporating distributed PAT observers and controllers. Finally, the theoretical results are applied to warehouse automation robot systems.

Abstract:
This article develops a dual-link coded event-triggered control (DL-CEC) for consensus in nonlinear multiagent system. To reduce the communication burden of signal transmission between the control box and actuator box or among agents and to enhance the security of information exchange, a dual-link coded scheme is proposed to compress each transmitted information into an L-length string. Furthermore, since the intrinsic complexity of nonlinear systems often causes traditional prescribed performance methods to fail in meeting constraints during the initial stages of operation, an adaptive prescribed performance (APP) scheme is introduced. By utilizing auxiliary functions, the APP is capable of dynamically adjusting performance boundaries, enabling seamless adaptation to varying initial system conditions. As a result, it ensures the tracking error is rigorously guaranteed to remain within a user-defined range over a prescribed time horizon, effectively accommodating diverse initial conditions of the system. By integrating DL-CEC with the APP method, the proposed control strategy ensures bounded consensus tracking with reduced communication cost and prescribed-time performance under arbitrary initial conditions. Simulation experiments corroborate the effectiveness and feasibility of the proposed approach.

Affiliations: Departamento de Ingeniería de Sistemas y Automática, Instituto de Automática e Informática Industrial, Valencia, Spain; Department of Excellence in Robotics and AI, Sant’Anna School of Advanced Studies, BioRobotics Institute, Pisa, Italy; Laboratory for Neuromechanics, and Biorobotics, Jožef Stefan Institute, Ljubljana, Slovenia; Laboratory for Collaborative Robotics, Jožef Stefan Institute, Ljubljana, Slovenia; Departamento de Ingeniería Mecánica y de Materiales, Centro de Investigación de Ingeniería Mecánica, Valencia, Spain; Laboratory for Neuromechanics and Biorobotics, Jožef Stefan Institute, Ljubljana, Slovenia

Abstract:
This article presents a novel control framework for assisting human arm movements with a robotic device. Unlike existing collaborative and wearable robots that predominantly operate in task space or joint space, our framework focuses on controlling variables related to the muscular space, which refers to the activation and force generation of individual muscles. Translating these variables to the robot’s actuation space is challenging, which hinders the development of human-centered tasks and limits the transparency of robotic assistance for the central nervous system. To address these issues, we consider the relationship between the muscular space and the robot’s task space, using the kinematics and dynamics of the human limb obtained from a calibrated musculoskeletal model based on Hill’s muscle model. Our framework includes two muscle-targeted methods: assistance and augmentation. The assistance method allows exercise or rehabilitation of specific muscles, while the augmentation method achieves isotropic manipulability, enabling the user to exert forces uniformly in all directions using the novel concept of a force envelope. The experiments were conducted using a haptic robot in admittance mode with a viscous environment simulating a load. The results demonstrate significant improvement in the prediction capabilities of the calibrated model compared with the baseline. Muscle-targeted assistance induces substantial changes in targeted muscular efforts. In addition, we achieve isotropic manipulability in a more precise way as compared with previous methods. In summary, our proposed control framework proves effective in assisting human arm movements with a robotic device for rehabilitation and power augmentation in human-centered applications.

Abstract:
This article investigates the event-triggered composite control problem for switched two-time-scale systems (TTSSs). First, the stabilization problem of switched TTSSs under switching composite control is addressed. Unlike existing results that require the singular perturbation parameter (SPP) to be sufficiently small or to satisfy specific linear matrix inequality conditions, an explicit upper bound of the SPP is derived. Then, both SPP-dependent and SPP-independent dynamic event-triggered mechanisms are developed to reduce the computational burden associated with control signal updates in switched TTSSs. These mechanisms are novel in that they incorporate the boundary layer system and explicitly balance the fast and slow time-scale dynamics. Furthermore, two sufficient stability conditions are established: one concerning the upper bound of the SPP and the other concerning the mode-dependent average dwell time, ensuring the stability of switched TTSSs under the respective mechanisms. In addition, Zeno’s behavior is excluded in both cases. Finally, three numerical examples, including a comparative study, are provided to demonstrate the effectiveness and advantages of the proposed results.

Abstract:
Direct, indirect, and network reciprocities are established mechanisms that sustain cooperation in natural and artificial systems. Yet which mechanism most effectively promotes cooperation on a given network remains unclear. Here, we develop a game-theoretic model to explore the evolution of direct and indirect reciprocity on weighted networks. Unlike classical donor–recipient frameworks, we study symmetric repeated interactions on undirected weighted networks with bilateral reputation updates, capturing heterogeneous tie strengths and accelerating reputation spread. We derive a general condition for reciprocal cooperation that unifies unweighted and weighted cases. Across large ensembles of random and empirical networks, indirect reciprocity consistently enhances cooperation, whereas stronger interactions sharply lower the benefit-to-cost threshold under direct reciprocity. To test the robustness of these insights, we examine competition among six reciprocity strategies and find that indirect reciprocity dominates. Our findings demonstrate that choosing the right reciprocity can promote global cooperation on social networks.

Abstract:
This study develops a reinforcement learning (RL)-based control framework with guaranteed predefined performance for nonlinear switched interconnected systems. This approach effectively addresses challenges arising from unmeasurable states and group average dwell time switching mechanisms, allowing both convergence time and accuracy to be preset via parameter configuration. First, the system equations are reconstructed to target nonlinear and interconnected terms, which are then approximated using neural networks (NNs). Additionally, an NNs-based switching state observer is designed to estimate the unmeasurable states. Second, within the backstepping synthesis framework, a distributed optimal controller is designed by integrating a performance transformation function into the cost function, with the resulting control law approximated via an identifier–actor–critic architecture. Furthermore, the group average dwell time-based stability analysis is generalized to address the optimal control challenges inherent in nonlinear switched interconnected systems. Compared with existing studies, this approach demonstrates enhanced extensibility and practicality for real-world applications. Finally, two simulation examples verify the effectiveness and superiority of the proposed method over state-of-the-art alternatives.

Abstract:
In this article, we investigate the triggering behaviors of periodic event-triggered multiagent systems (MASs) under multiplicative false data injection (FDI) attacks. An abstraction-based traffic model is established to characterize all possible triggering behaviors under arbitrary initial states, including the minimum interevent time (MIET) and the transition relations among IETs. We further answer the following two questions: 1) how FDI attacks affect the MIET and 2) how to select the sampling period for the anomalous MIET detection. As a potential application scenario, a behavior-based anomaly detection algorithm is developed based on the proposed traffic model to identify anomalous triggering behaviors caused by attacks. Simulations demonstrate the effectiveness and practical application of the proposed results.

Abstract:
The topology of a communication system is crucial in determining data transmission. Although significant research has been conducted on the integration of control and communication, existing studies on communication for control systems predominantly emphasize control aspects and warrant further exploration. Furthermore, there is a lack of research on the impacts of topology changes on control systems. This article aims to establish a connection between control and communication via communication topology, examining how communication topologies affect controllers. This article also analyzes the relationship between communication and control in depth. For static topologies, specific controller forms are derived from a general controller to illustrate the impacts of static topologies on controllers. In dynamic topologies, communication is nondeterministic, so whether a controller can receive data from other nodes is nondeterministic. Therefore, controller forms in which some coefficients are random variables following a probability distribution are derived. We utilize them to establish a close connection between control and communication. Furthermore, extensive simulations are conducted to investigate the impact of different topologies on the control system.

Abstract:
In this article, we investigate the distributed optimization problem of heterogeneous general linear multiagent systems by the adaptive dynamic programming (ADP) approach over directed communication networks. A distinctive feature of this work is the development of a data-driven approach that eliminates the need for prior knowledge of system dynamics for all agents. To address the challenges posed by unknown system dynamics, we utilize the ADP-based data-driven approach to develop the distributed optimization control law. First, the feedback gain of the control law is determined based on the state and input data of the controlled systems. Next, the system dynamics are reconstructed using the solved feedback gain and the running data of the controlled systems. Then, the remaining parameters in the control law are designed by solving a series of steady-state equations. Under standard assumptions and through the application of the certainty equivalence principle, we prove that the proposed approach solves the distributed optimization problem, ensuring output consensus of all agents at the optimal solution of the global cost function. Finally, the viability of our proposed approach is demonstrated through its application to optimal output power sharing control of hydraulic turbine systems and their large-scale form.

Abstract:
This article focuses on the problem of N -step model predictive control (MPC) under a mixed time/event-triggered encoding–decoding strategy for polytopic uncertain systems with hard constraints. A staged requirements-dependent mixed time/event-triggered mechanism (MTEM) is proposed. When the system state is outside the terminal constraint set (TCS), the time-triggered pattern is implemented to meet the staged requirement of improving control performance. When the system state is in the TCS, an event-triggered pattern is used to fulfill the staged requirement of conserving resources. The event-triggered pattern contains an adaptively adjusting variable related to the “distance” of the system state from the TCS core, which helps meet the relative staged requirements in the TCS. The staged requirements-dependent MTEM-based encoding–decoding strategy improves the communication security while saving computational resources for encoding and decoding, as well as network resources. Based on two offline optimization problems (OPs), the TCS and the approximate robust one-step sets are designed, respectively. The control laws outside the TCS are obtained by an online OP. A mixed time/event-triggered encoding–decoding-based N -step MPC algorithm is proposed based on three OPs. The algorithm’s feasibility and the input-to-state stability of the closed-loop system are analyzed. Two examples are presented to illustrate the effectiveness and superiority of the proposed MTEM and MPC algorithm in saving resources while ensuring control performance.

Abstract:
This article investigates the finite-horizon H_\infty tracking control problem for discrete-time (DT) linear systems with partial observation and unknown dynamics from a game-theoretic perspective. Unlike existing reinforcement learning (RL) approaches that primarily address infinite-horizon, time-invariant systems with full state information, our setting requires solving time-varying Riccati equations and developing model-free methods that rely solely on input–output data. To tackle these challenges, we reconstruct the system state from historical input–output trajectories, driving to a data-driven system representation, and we define an input–output-based time-varying Q -function. We then propose two minimax Q -learning algorithms that do not require an initially admissible policy and avoid the use of a discount factor, thereby removing a long-standing obstacle to stability guarantees. Moreover, the framework readily extends to both infinite-horizon and time-varying systems without structural modifications. Convergence is proved theoretically, and the effectiveness of the algorithms is validated through simulations.

Abstract:
This article addresses the problem of distributed state estimation (DSE) for discrete-time interconnected systems, where the observed system is composed of subsystems interconnected through state-to-state and state-to-output couplings. Inspired by the leader–follower consensus method, we propose a distributed observer that enables each subsystem to estimate the entire state of the interconnected system. Under certain structural assumptions, we derive necessary and sufficient conditions for the stability of the estimation error dynamics. We further present a decentralized design of the proposed observer, where the operation and construction of the observer can be completed by each subsystem using its locally available information, including the system’s basic configuration, local measurements, and data exchanged with neighboring subsystems. In addition, we demonstrate that our distributed estimation framework can be applied to solve the distributed estimation problem for linear time-invariant (LTI) systems with fixed composition by employing an observability decomposition method. Finally, we illustrate the effectiveness of our scheme by applying it to vehicle platooning.

Abstract:
Deep neural networks have recently achieved promising performance in the vein recognition task and have shown an increasing application trend. However, they are prone to adversarial attacks by adding imperceptible perturbations to the input, resulting in incorrect recognition. To address this issue, we propose a novel defense model named MsMemoryGAN, which aims to filter the perturbations from adversarial samples before recognition. First, we design a multiscale memory autoencoder (MsMemoryAE) to achieve high-quality reconstruction, where the memory module (MM) within it is capable of learning the detailed patterns of normal samples at different scales. Second, to overcome the limitations of handcrafted similarity metrics, we propose an MM with learnable similarity (LSMM), which retrieves the most relevant memory items to purify the input feature. Finally, the perceptual loss and adversarial loss are integrated with the pixel loss to further enhance the quality of the reconstructed image. During the training phase, the MsMemoryGAN learns to reconstruct the input by merely using fewer prototypical elements of the normal patterns recorded in the memory. At the testing stage, given an adversarial sample, the MsMemoryGAN retrieves its most relevant normal patterns in MMs for reconstruction. Perturbations in the adversarial sample are usually not reconstructed well, resulting in adversarial purification. We conduct extensive experiments on two public vein datasets under different adversarial attack methods to evaluate the performance of the proposed approach. The experimental results show that our approach removes a wide variety of adversarial perturbations, allowing vein classifiers to achieve the highest recognition accuracy.

Abstract:
In this article, cycle-time configuration is realized using max-plus algebra for a parallel processing system via a synchronous feedback controller. As a key efficiency metric of parallel processing systems, throughput is determined by cycle time, which is threatened by clock asynchrony and the curse of dimensionality. Using instruction dependency and weak linear independence, the parallel processing system is equivalent to a max-plus nonautonomous system to mitigate the curse of dimensionality caused by numerous processing tasks. Based on the max-plus nonautonomous system, the cycle-time configuration is achieved via a synchronous feedback controller while adhering to time restrictions of the parallel processing system. Numerical simulations validate the effectiveness of the proposed cycle-time configuration in parallel processing systems.

Abstract:
This article proposes an accelerated learning control framework for point-to-point (P2P) tracking systems subject to stochastic noise, with a focus on reducing input energy. A novel stochastic accelerated method with a fixed penalty factor is established, resulting in substantial performance advancements for the overall iteration process. In this method, we introduce a two-loop structure. A historical term is designed and appropriately incorporated into the input update to improve the convergence process of the inner loop, and a Lagrange multiplier is updated in the outer loop to ensure the input sequence to converge to a limit that is closest to the initial input, achieving the effect of energy reduction. Additionally, practical implementation of the proposed framework is addressed by terminating the inner loop within a finite number of iterations according to a given accuracy. In this scenario, two types of Lagrange multiplier updating are conducted to handle the noise’s impact. Numerical simulations are provided to validate the theoretical results.

Abstract:
This article presents two fault-tolerant control (FTC) frameworks for high-order fully actuated systems (HOFASs) with actuator faults, sensor faults, and measurement noise. After analyzing the observable architecture corresponding to each measurement, actuator faults are compensated through fusion observers, and sensor faults are rejected through redundant observability. The first FTC framework with traditional fusion observers can merely yield an ultimately uniformly bounded (UUB) error system. To further suppress measurement noise, a dead-zone fusion observation strategy is applied to the FTC redesign. Especially in a linear HOFAS model, the noise suppression performance of the novel FTC framework is proved to be superior. In more general systems, two comparative cases experimentally illustrate trajectory tracking results and noise suppression performance.

Abstract:
Hot rolling production scheduling (HRPS) is an essential process in modern steel manufacturing. Its effectiveness is influenced by three primary challenges: selecting suitable slabs to maximize efficiency and maintain product quality, adhering to increasingly stringent carbon tax regulations, and managing uncertainties in processing times stemming from fluctuations in rolling speed. This article presents a novel robust HRPS problem under carbon tax regulation (RHRPSP-CTR) that considers slab selection, carbon tax regulation, and uncertain processing times simultaneously for the first time. Based on a budgeted uncertainty set, we develop a robust counterpart model that utilizes a classical dualization scheme and dynamic programming recursive equations to address the challenges associated with evaluating the worst case cost of carbon emissions (CEs) and determining the worst case completion time for each slab caused by processing time uncertainty, respectively. Recognizing the characteristics of slab selection and the high computational complexity in the large-scale RHRPSP-CTR, we propose an adaptive large neighborhood search algorithm incorporating two enhancement strategies: a slab selection rule and a max–min weight update mechanism. Extensive computational experiments demonstrate that the proposed method yields optimal solutions for small-scale problem instances and high-quality, robust solutions for large-scale instances within a relatively short computation time. Moreover, the results indicate that compared with deterministic HRPS schemes, robust HRPS schemes lead to only a slight increase in cost. Notably, a higher carbon tax does not necessarily lead to lower CEs, and a larger uncertainty budget coefficient or uncertainty range does not always result in higher CEs.

Abstract:
For uncertain strict-feedback nonlinear systems with self-restructuring structures and nonaffine dynamics, this article addresses the challenge of achieving exact full state zero-error stabilization within a prescribed finite time. An adaptive prescribed-time control scheme is proposed, which guarantees that all system states converge to zero within the user-specified settling time, irrespective of initial conditions. The controller is designed based on a time-varying scaling state transformation and incorporates the Nussbaum function to handle unknown self-restructuring control gains. The self-restructuring structures are treated as a time-state-dependent lump, which is effectively estimated by freezing both time and system states and then applying an adaptive estimation strategy. Numerical simulations on a piezoelectric-actuated stage and a second-order nonlinear system are conducted to demonstrate the effectiveness of the proposed scheme.

Abstract:
This work aims at developing a novel direct design and analysis method of learning control protocol toward consensus performance of multiagent systems (MASs) without using any model. A nonlinear autoregressive moving average (NARMA) function is designed at first to formulate the inherent consensus dynamics with respect to the consensus error and the control protocols. Then, a consensus performance-related iterative linear data model (CPiLDM) is constructed for equivalently reformulating the NARMA consensus system’s iterative dynamics in a data-driven framework. The CPiLDM does not rely on a model no matter through first-principle modeling or system identification methods. Next, a direct distributed iterative learning control (DirDILC) method is developed through an optimization technique subject to the CPiLDM. The convergence is proved directly for the virtual NARMA consensus system, without relying on the dynamics of the agent itself, and thus simplifies the analysis consequently. Since the presented DirDILC is purely data-driven without relying on an explicit model, it constitutes a significant step forward from the existing consensus control theory.

Abstract:
This article develops an event-triggered safe critic learning control (ESCLC) algorithm for nonlinear systems subject to asymmetric state constraints by integrating a safe critic learning control (SCLC) framework with an event-triggering mechanism. The SCLC algorithm innovatively incorporates control barrier functions into the safe value function design, addressing the challenge of deriving optimal control policies that guarantee system safety. Convergence of the SCLC algorithm is rigorously established within the value iteration framework, along with a criterion for assessing the admissibility of control policies. To enhance the application value of the algorithm in resource-constrained scenarios, an event-triggering mechanism is incorporated into the SCLC framework, yielding the ESCLC algorithm. The resulting closed-loop system under the ESCLC algorithm is proved to be asymptotically stable, and an upper bound on the actual value function is derived to ensure bounded performance degradation. In addition, a policy improvement method based on particle swarm optimization is designed that eliminates dependence on the system control matrix. Finally, the effectiveness of the ESCLC algorithm is verified through simulation experiments on a torsion pendulum system and a ball-and-beam system.

Abstract:
Byzantine-robust distributed or federated learning (FL) refers to providing reliable performance under Byzantine attacks, which violate the prescribed protocols and transmit arbitrary information to the server to hamper the convergence of machine learning (ML) algorithms, via designing resilient aggregation rules to combat attacks. Although numerous robust rules have been suggested, their performance degrades for heterogeneous data. A few techniques have been exploited to handle this problem, but they either require preaggregation operations, hence increasing the computational load, or lack breakdown point analysis of their rules. This article proposes a new aggregation rule, which clips the gradients received from all workers according to the distance between the gradient and the aggregation center. That is, when the distance is larger than the radius \gamma , the gradient will be clipped, and the longer the distance, the closer the clipped gradient is to the center. We theoretically analyze that the breakdown point of the developed rule is 0.5, the maximum value for robust aggregators. Moreover, our rule achieves order-optimal Byzantine-robust training error under data heterogeneity, while the median-based schemes, such as coordinate-wise median (CM) and geometric median (GM), are suboptimal. Experimental results demonstrate that the devised aggregation mechanism can handle different attacks well and outperforms the existing rules.

Affiliations: College of Computer and Information Science and the Chongqing Key Laboratory of Brain-Inspired Cognitive Computing and Educational Rehabilitation for Children with Special Need, Chongqing Normal University, Chongqing, China; Key Laboratory of Big Data Intelligent Computing, Chongqing University of Posts and Telecommunications, Chongqing, China; School of Mathematics and Statistics, Hubei Minzu University, Enshi, China; School of Mathematical Science, Shanxi Normal University, Taiyuan, China; Chongqing Key Laboratory of Brain-Inspired Cognitive Computing and Educational Rehabilitation for Children with Special Needs, Chongqing Normal University, Chongqing, China

Abstract:
Density peak clustering is an effective and interpretable method for uncovering potential knowledge in unlabeled datasets with arbitrary shapes. It has been extensively studied by researchers, and a series of extended models have been proposed. The performances of these algorithms largely depend on the positions and number of cluster centers. However, accurately selecting these centers remains a challenging problem. Therefore, to address this issue, an adaptive density distribution clustering (ADDC) method based on graph theory and k -nearest neighbors is developed in this study. ADDC is a decentralized and robust clustering approach, which consists of three main components. First, an undirected neighborhood graph is constructed based on the neighbor degree defined in this article to implement a decentralized allocation strategy. Second, componentwise local density is introduced, and a new criterion for selecting density peaks is established to serve as one of the guidelines for determining the number of clusters. Third, with the neighborhood graph and density peaks, criterion-based decomposition and fusion strategies are formulated to identify clusters with multiple peaks or to detect low-density clusters without peaks. Finally, experiments and comparisons on widely used real datasets and synthetic datasets demonstrated that ADDC significantly outperforms five classical clustering methods and seven state-of-the-art density-based cluster approaches.

Abstract:
In a recent article, we mathematically extended conventional discrete-time finite Markov chains, characterized by an N × N transition probability matrix, to discrete-time finite fuzzy Markov chains capable of modeling fuzzy states and fuzzy events, which frequently arise in fields such as biomedicine. This advancement is built upon the theory of stochastic fuzzy discrete event systems (SFDESs) and the supervised learning algorithm for FDESs, previously published by the authors. The fuzzy Markov chain is represented by a single-event SFDES comprising N^2 FDES, each with its own occurrence probability and an associated N × N event transition matrix, which is automatically learned using the aforementioned learning algorithm. Additionally, each FDES is associated with a set of fuzzy sets that fuzzify the random variable values and are required to satisfy specific constraints. Manually designing these fuzzy sets can be challenging, especially for modelers with little or no prior knowledge of fuzzy set theory. To overcome this challenge, we develop stochastic gradient descent-based algorithms that simultaneously learn constrained Gaussian fuzzy sets and the event transition matrices. To reduce the complexity of parameter learning, the Gaussian fuzzy sets are designed such that their means are computed directly from the terminal points of the subintervals that divide the ranges of the random variables, rather than being learned. Furthermore, dependencies between the Gaussian fuzzy sets for each random variable are introduced, reducing the number of standard deviations to be learned to N for all Gaussian fuzzy sets in an FDES, while the remaining standard deviations are computed based on these dependencies. In addition, we establish that these new algorithms are fully applicable to continuous-time finite fuzzy Markov chains, extending their utility to a broader range of applications. An illustrative example is provided to demonstrate the effectiveness of the learning algorithms. These new algorithms make fuzzy Markov chains more accessible to modelers, regardless of their familiarity with fuzzy sets, while enhancing the overall practicality of the approach.

Abstract:
This article concentrates on the problem of practically time-synchronized tracking control for multi-input multi-output (MIMO) systems with unmatched nonlinearities and input saturations. Different from the existing approaches, a practically time-synchronized command filtered backstepping (CFB) control scheme is proposed. By integrating modified command filters and control signals designed with norm-normalized sign functions, the newly developed framework not only retains the advantages of the CFB control approach but also guarantees the property of time-synchronized convergence. Specifically, the “explosion of complexity” phenomenon and the influence of filtering errors are simultaneously addressed, and all components of the tracking error can achieve practically synchronous convergence to a small neighborhood of the origin in a finite time, despite the presence of unmatched nonlinearities in high-order systems. Furthermore, novel auxiliary systems are recursively embedded into each step of the time-synchronized CFB design to counteract the effect of input saturation. Rigorous theoretical analyses and comparative simulations demonstrate the rationality, effectiveness, and superiority of the proposed control scheme.

Abstract:
Modern engineering and scientific systems are usually equipped with abundant sensors to collect large-dimensional time series for monitoring and operations. In this article, we develop a novel principal predictor analysis (PPA) framework with reduced-dimensional dynamics to obtain parsimonious predictor models of large-dimensional time series data. Principal predictors are obtained by maximizing the variance of predictions from their past values. Unlike classical principal component analysis (PCA), which reduces the dimensionality without emphasizing the prediction, PPA focuses on extracting latent variables with the maximum predictive capability. The PPA application to dynamic process monitoring is performed with predictive monitoring indices to account for variations in the predictors and the unpredicted residuals, which can be subsequently modeled with PCA. PPA-based monitoring and diagnosis are demonstrated in an illustrative closed-loop system and the industrial Dow Challenge Problem and an extension to include known first-principles relations to show their effectiveness.

Abstract:
Semi-supervised multiview clustering has garnered considerable attention for its ability to integrate multiview data with limited labeled information. However, existing methods predominantly focus on labeled samples, neglecting abundant unlabeled data, which leads to suboptimal utilization of available prior knowledge. Moreover, existing pairwise constraint propagation-based methods typically follow a two-stage procedure, resulting in unstable clustering outcomes. To address these limitations, we introduce a unified framework that integrates multiview subspace clustering with pairwise constraint propagation, proposing a tensor-based semi-supervised multiview subspace clustering (TSMSC) method with pairwise constraint propagation. Specifically, each view’s subspace representation is decomposed into a consensus part and private parts, enabling the consensus representation to better approximate the low-rank structure. Then, a pairwise constraint propagation method is developed for multiview data, which propagates the initial pairwise constraint through a low-rank matrix completion approach. Finally, observing that the ideal multiview consensus representation and the propagated pairwise constraint matrix share the same low-rank structure, we naturally construct them into a third-order tensor to capture high-order correlations via tensor low-rank representation, allowing for joint optimization within a unified framework. Extensive experiments on eight real-world datasets demonstrate the superiority of our method over state-of-the-art approaches.

Abstract:
In this article, we investigate a decentralized constrained optimization problem over time-varying directed networks. The nodes in the network aim to collaboratively minimize the aggregate of all locally known convex cost functions, subject to local nonidentical and multiple constraint sets, inequality constraints, and equality constraints. Problems of this nature arise in a number of applications in real networks, such as facility location in wireless sensor networks and image deblurring in machine learning. To address these types of problems, we propose an efficient subgradient-rescaling-based decentralized fixed-random projection (SR-DFRP) algorithm, named the SR-DFRP algorithm. In particular, the SR-DFRP algorithm employs Polyak’s random projection to handle nonidentical and multiple constraints, which reduces computational load by avoiding the formulation of complex subproblems. Furthermore, by utilizing dynamically constructed row-stochastic matrices, the algorithm employs a subgradient rescaling strategy to mitigate the imbalance induced by the time-varying directed networks. Rigorous theoretical analyses are provided to establish that the SR-DFRP algorithm converges almost surely to the optimal solution. Extensive simulations on facility location and image deblurring problems are presented to validate the efficacy of the algorithm and the validity of the theoretical results.

Abstract:
Effective transmission line (TL) inspection in complex corridor environments is essential for ensuring reliable power delivery. This work presents a 3D-based perception method for this task. The proposed method is designed by considering two key characteristics of TL inspection. First, the point cloud data are sparse and class distributions are highly imbalanced, which weakens the signals from thin conductors and tower components. To address this issue, we model long-range spatial relations along the corridor to mitigate data sparsity and imbalance. Second, strong structural correlations exist between conductors and towers, which can be leveraged to improve perception performance. To exploit this property, we construct a unified 3-D representation that jointly models towers, conductors, and vegetation, while fusing Cartesian and polar geometries through geometry-aware alignment. Experiments on real-world corridor datasets demonstrate that the proposed method, termed multigeometric and long-distance TL perception Network (MGLD-TLNet), consistently improves stability and accuracy under conditions of sparsity, occlusion, and complex environmental interactions.

Abstract:
In this article, the practical fixed-time (FxT) control of switched neutral Filippov systems (SNFSs) on networks is considered. The perturbation functions that can be discontinuous, and the neutral logics expressed by the difference operators, are addressed by new approaches. Several novel Lyapunov inequalities with indefinite functions are proposed, where detailed estimations of the settling-time (ST) are obtained by discussing the different values of the exponents of the Lyapunov functions, which can include the existing results. Considering that the states generally cannot converge to the origin accurately under finite-time control in real applications, practical FxT stability lemmas with indefinite functions are established for the first time, in which the bounded condition imposed on the indefinite function is more practical than the previously unbounded ones. By designing the adaptive control strategies, the FxT and practical FxT synchronization control are investigated based on the Lyapunov–Krasovskii functionals (LKFs), which show the delay characteristic via the adaptive update law containing delay values. Notably, the theoretical deficiency arising from the Lyapunov function when studying the FxT stability of real systems with delays by using the FxT stability lemmas with indefinite function is solved in a successful way. Finally, the validity of the main results is verified by numerical simulations on an electrical device containing an LC transmission line.

Abstract:
This article proposes two types of unscented particle filters (UPFs) that leverage unscented transformation (UT) from a geometric perspective to compute the proposal distribution. An UPF on Lie groups is first developed. Specifically, both the propagation of the sigma points and the computation of the mean and covariance are performed on the Lie groups, while the weight update and resampling are conducted on the Lie algebra. Second, we introduce the log-linear property of group elements to streamline particle propagation by reducing redundant operations, thereby optimizing the proposed UPF framework. In the update process, intermittent measurements that are caused by factors such as packet dropouts and stochastic sensor scheduling are considered. While lowering computational demands, these measurements pose challenges to filter stability. To this end, the introduced property is used to prove that the estimation error remains bounded under certain assumptions. We further establish a critical threshold for the arrival rate of intermittent measurements and derive an upper bound for the expected state error covariance. Moreover, a detailed computational complexity analysis is conducted to evaluate the efficiency of the proposed method. Finally, with the original method serving as a benchmark, simulation and real-world GNSS/INS integrated navigation experiments confirm that the redesigned approach delivers comparable performance and significantly improved computational efficiency.

Abstract:
Few-shot anomaly detection (FSAD) has emerged as a critical paradigm for identifying irregularities using scarce normal references. While recent methods have integrated textual semantics to complement visual data, they predominantly rely on features pretrained on natural scenes, thereby neglecting the granular, domain-specific semantics essential for industrial inspection. Furthermore, prevalent fusion strategies often resort to superficial concatenation, failing to address the inherent semantic misalignment between visual and textual modalities, which compromises robustness against cross-modal interference. To bridge these gaps, this study proposes VTFusion, a vision–text multimodal fusion framework tailored for FSAD. The framework rests on two core designs. First, adaptive feature extractors for both image and text modalities are introduced to learn task-specific representations, bridging the domain gap between pretrained models and industrial data; this is further augmented by generating diverse synthetic anomalies to enhance feature discriminability. Second, a dedicated multimodal prediction fusion module is developed, comprising a fusion block that facilitates rich cross-modal information exchange and a segmentation network that generates refined pixel-level anomaly maps under multimodal guidance. VTFusion significantly advances FSAD performance, achieving image-level area under the receiver operating characteristics (AUROCs) of 96.8% and 86.2% in the 2-shot scenario on the MVTec AD and VisA datasets, respectively. Furthermore, VTFusion achieves an AUPRO of 93.5% on a real-world dataset of industrial automotive plastic parts introduced in this article, further demonstrating its practical applicability in demanding industrial scenarios.

Abstract:
Machine learning-based optimization frameworks have attracted increasing attention for accelerating the solution of large-scale quadratically constrained quadratic programs (QCQPs) by exploiting shared problem structure across instances. However, existing machine learning (ML) frameworks often rely on the assumption of parametric models and large-scale solvers. This article introduces HEQP, a hypergraph neural network-based evolutionary optimization framework for large-scale QCQPs. This framework features two main components: 1) hypergraph-based neural prediction, which predicts optimal solutions for QCQPs without assumptions of models; and 2) evolutionary large neighborhood search (Evo-LNS), which employs a McCormick relaxation-based repair strategy to search and apply crossover on neighborhood solutions using a small-scale solver. We further show that our framework is equivalent to the interior-point method (IPM), a polynomial-time algorithm, for quadratic programming. Experiments on two types of benchmark problems and 13 large-scale real-world instances from the QPLIB illustrate that our framework outperforms state-of-the-art solvers (including Gurobi, SCIP, and SHOT) in both solution quality and time efficiency, highlighting the efficiency of ML-based optimization frameworks for QCQPs.

Abstract:
This article proposes a new adaptive event-triggered controller with prescribed tracking performance for a class of uncertain nonlinear systems. The controller is global, instead of semiglobal, by eliminating the initial-condition-dependence on the performance function. In contrast to the existing results, the controller design is tight to reduce conservatism, in which two enablers are involved. First, the controller fully leverages available information on system nonlinearities, rather than discarding the information as is done in the context of funnel control (FC). This enables the controller to more efficiently counteract the nonlinearities, potentially avoiding unnecessarily large control effort, thereby reducing conservatism. Second, dedicated dynamic compensations are introduced with the help of tuning functions to compensate for the intrinsic uncertainties appearing in the execution error, system nonlinearities, and control coefficients. In this way, estimating conservative bounds of multiple uncertain parameters is circumvented, and especially, inequality estimates, including completing squares, are largely avoided, thereby also reducing conservatism. To further improve communication efficiency, the proposed control scheme is extended to the scenario where the information transmission from sensor to controller is also event-triggered, by delicately designing a double-sided event-triggering mechanism. A classical pendulum system is utilized to verify the effectiveness and superiority of the proposed method.

Affiliations: Department of Control Science and Engineering, College of Electronics and Information Engineering, State Key Laboratory of Autonomous Intelligent Unmanned System, Frontiers Science Center for Intelligent Autonomous Systems, Ministry of Education, Shanghai Research Institute for Intelligent Autonomous Systems, and Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China; Department of Automation, Shanghai Jiao Tong University, Shanghai, China

Abstract:
This article focuses on nonconvex federated composite optimization (FCO) problem, where the loss function is nonconvex and contains a nonsmooth regularizer. To resolve this problem, we propose FedRREF, a novel federated learning algorithm that integrates error feedback (EF) with the efficient random reshuffling (RR) technique, resulting in lower computation and communication costs. To the best of our knowledge, FedRREF is the first algorithm to consider RR and biased compression simultaneously in federated learning, especially in nonsmooth and nonconvex settings, and it is shown to have a \mathcal O(1/\sqrt T) convergence rate, where T is the number of communication rounds. Finally, the numerical experiments illustrate the validity of the proposed algorithm.

Abstract:
This article proposes an adjustable-error neural network (NN) approximator and incorporates it into the adaptive neural tracking controller design of uncertain nonlinear systems. Noted that the error between the unknown nonlinear function and the NN approximator cannot be adjusted under the traditional NN control framework, as it is solely determined by the selection of neurons, basis functions, and the estimation of the ideal weight vector. This inherent constraint compromises the precision of the NN approximation and the convergence accuracy of the tracking error. To improve the approximation accuracy of unknown nonlinear functions in adaptive neural control systems, an adjustable-error NN approximator is designed, in which the error between the approximator and the unknown nonlinear function can be adjusted by designed parameters. Based on the proposed NN approximator, an adaptive neural tracking controller is designed for a class of uncertain nonlinear systems, which achieves higher accuracy of the tracking error compared with traditional methods. The stability of the resulting closed-loop system is proved in the Lyapunov sense, and the convergence of the tracking error is also analyzed. The effectiveness of the proposed scheme is verified by simulation and experiment.

Abstract:
In this article, we propose a differential evolution (DE) algorithm specifically tailored for the design of linear-quadratic-Gaussian (LQG) controllers in quantum systems. Building upon the foundational DE framework, the algorithm incorporates specialized modules, including relaxed feasibility rules, a scheduled penalty function, adaptive search range adjustment, and the “bet-and-run” initialization strategy. These enhancements improve the algorithm’s exploration and exploitation capabilities while addressing the unique physical realizability requirements of quantum systems. The proposed method is applied to a quantum optical system, where three distinct controllers with varying configurations relative to the plant are designed. The resulting controllers demonstrate superior performance, achieving lower LQG performance indices compared to existing approaches. In addition, the algorithm ensures that the designs comply with physical realizability constraints, guaranteeing compatibility with practical quantum platforms. The proposed approach holds significant potential for application to other linear quantum systems in performance optimization tasks subject to physically feasible constraints.

Abstract:
This article addresses the resilient cooperative optimal output regulation (COOR) control problem for nonlinear strict-feedback multiagent systems (MASs) under denial-of-service (DoS) attacks. By constructing the resilient adaptive distributed observers, the leader’s dynamics and states can be estimated by each follower. In the control design, a control input constructed by feedforward and feedback control input is proposed based on the system data. Neural networks (NNs) are employed to learn solutions of the feedforward and optimal feedback control problems. Meanwhile, to handle the influence caused by unknown nonlinear dynamics, combining off-policy integral reinforcement learning (IRL) algorithm with actor-critic NNs (A-C NNs), an optimal feedback security control law is designed. To illustrate the feasibility and effectiveness of the proposed optimal control strategy, numerical and practical simulation examples are provided. Unlike prior studies limited to linear systems, this work explicitly accounts for complex nonlinear dynamics, significantly broadening the applicability of resilient COOR control problem in real-world applications.

Abstract:
Deep clustering has achieved remarkable success in handling various types of real-world data, but often suffers from overconfidence, forcing ambiguous samples into specific clusters even when the evidence is insufficient. To address this limitation, we propose trustworthy deep credal clustering, a novel framework for uncertainty that integrates deep neural networks with the Dempster–Shafer Theory of evidence (DST). This method leverages credal cluster structures to enhance the model’s robustness against uncertain data. Our model can refrain from assigning uncertain samples to a specific cluster, thereby reducing errors and enhancing the model’s trustworthiness. Theoretically, we derive closed-form solutions for updating cluster memberships and prototypes, employing a coordinate descent strategy to rigorously optimize the objective function. Experiments on various datasets confirm that our proposed trustworthy clustering method leads to enhanced overall clustering effectiveness. Code is available at https://github.com/H1nkik/Trustworthy-Clustering

Affiliations: School of Electrical and Information Engineering, the Provincial Key Laboratory of Power Electronics and Motion Control, Anhui Key Laboratory of Low Carbon Metallurgy and Solid Waste Resource Utilization, the Key Laboratory of Multidisciplinary Management and Control of Complex Systems of Anhui Higher Education Institutes, Anhui Province Engineering Laboratory of Intelligent Demolition Equipment, and Anhui Province Key Laboratory of Special Heavy Load Robot, Anhui University of Technology, Maanshan, China; School of Electrical and Information Engineering, Anhui University of Technology, Maanshan, China; School of Electrical and Information Engineering and the Provincial Key Laboratory of Power Electronics and Motion Control, Anhui University of Technology, Maanshan, China; School of Information and Intelligent Science, Donghua University, Shanghai, China; Department of Automation, School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China; School of Engineering, Trustworthy and General AI Laboratory, Westlake University, Hangzhou, China

Abstract:
Robust multiobjective evolutionary algorithms (RMOEAs) aim to obtain robust optimal solutions. However, traditional RMOEAs typically require evaluating a large number of sampling points, which is often impractical in real-world applications due to the high computational cost. In this article, we propose a robust multiobjective evolutionary algorithm based on surrogate-assisted (RMOEA-SA), which incorporates a radial basis function (RBF) surrogate model and a novel robust distance metric (RDM). The proposed algorithm employs the RBF surrogate model to approximate the fitness values of sampling points, thereby significantly reducing the number of function evaluations during the robust optimization process. Furthermore, an RDM assisted by the RBF surrogate model is introduced to measure the robustness of solutions. Besides, the RDM value of each solution is treated as an additional objective, expanding the original objective space, and selection is conducted in this augmented space to achieve a desirable trade-off between robustness and optimality. The experimental results on standard benchmark functions and two real-world application problems demonstrate the superior feasibility and effectiveness of the proposed method compared with several existing algorithms.

Abstract:
This article presents a prescribed-performance-controller-based equivalent-input-disturbance approach (PEID) that enhances the disturbance-rejection performance of a Stewart platform. The PEID approach ensures that the disturbance-estimation error converges to a bounded region in a prescribed time. The bound of disturbance-estimation error can be chosen arbitrarily small, and the convergence time of disturbance-estimation error can be prescribed in advance. Stability conditions are derived by dividing the PEID-based control system into three subsystems, and a barrier Lyapunov function is used to design a prescribed-performance-controller-based compensator. An algorithm for designing system parameters devises state feedback and observer gains. The experiments conducted on a Stewart platform validate the effectiveness and superiority of the PEID approach.

Affiliations: School of Electrical Engineering, Hebei University of Science and Technology, Shijiazhuang, China; Shanghai Key Laboratory of Power Station Automation Technology, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China; Engineering Research Center of Intelligent Control System and Intelligent Equipment, Ministry of Education, and Hebei Key Laboratory of Intelligent Rehabilitation and Neuromodulation, Yanshan University, Qinhuangdao, China

Abstract:
This article investigates the stealthy distributed pole-dynamics attacks (dPDAs) detection for multiagent systems (MASs) by distributed additive watermarking (DAW). First, the limitation of traditional MASs for dPDAs is revealed, where dPDAs cannot be detected. Second, unlike the well-established single-agent additive watermarking, to eliminate the side effect of watermarking signal on system state and enable dPDAs detection, the proposed DAW adds watermarking to the control signal of any agent for transmission and removes watermarking of the control signal after receiving it. Meanwhile, the covariance of the watermarking signal in DAW for all agents is different from each other to enable compromised links isolation. Furthermore, the relationship between the dPDAs detection performance and DAW is quantified in the sense of expectation, where the dPDAs detection performance is directly proportional to the sum of the watermarking covariance of the compromised links. Third, leveraging the relationship between dPDAs detection performance and DAW, a DAW-based link isolation scheme is proposed to accurately isolate the compromised links by comparing with the detection function and its approximation, where the approximation of the detection function is iteratively calculated on all possible attack links combination for the compromised agent. As a result, the adverse impacts of dPDAs on MASs are mitigated. Finally, simulation results are conducted to validate the theoretical results.

Abstract:
Electroencephalography (EEG) emotion recognition plays a key role in improving human–machine interactions. Advanced algorithms have been proposed for this task. However, two challenges remain, i.e., unclear decision boundary in the embedded space and noise in physiological signals from various devices. To this end, we develop a novel framework, namely, UACL-Net, for EEG emotion recognition. It is based on uncertainty-aware contrastive learning (UACL) and frequency-aware self-attention (FASA). Specifically, UACL uses a multivariate Gaussian distribution to construct the latent space for different emotions. It is able to highlight interclass differences, thereby improving the robustness of model decisions. In addition, FASA generates learnable weights by applying self-attention (SA) to the real and imaginary components in the frequency domain. This helps adaptively reduce noise and capture global dependencies in temporal sequences. Our model is trained and tested on four benchmark datasets, achieving up to 94.88%, 98.71%, 96.91%, and 99.29% accuracy on SEED, DEAP, DREAMER, and FACED, respectively. Experimental results demonstrate that it is effective and has advantages over peer state-of-the-art (SOTA) methods.

Abstract:
Soft sensors are essential for advanced monitoring and control to prevent undesirable operations and improve product quality. However, nonlinear, autocorrelated, and cross-correlated behaviors in industrial data demand concurrent modeling of the dynamics and nonlinearities. Deep learning-based soft sensors, such as recurrent neural network (RNN) and long short-term memory (LSTM) networks, often incorporate complex structures and numerous parameters, which can lead to an overly complex model. In practical applications where training data samples are limited, a lightweight neural network with strong generalization capability is preferred. With a simple structure of feed-forward layers of 1-D convolutional neural networks (CNNs) (1-D-CNN) for time-series data modeling, this article proposes a novel lightweight dynamic CNN (LDCNN) for soft sensors. Positional embedding (PE) and simplified temporal attention mechanisms are integrated for improved dynamic modeling, while dilated convolutions and layer normalization (LN) are incorporated to significantly reduce the depth and width of the network and avoid over-parametrization. Experimental results on a real industrial case indicate that a lightweight model outperforms the traditional methods with limited training samples.

Abstract:
As control systems increasingly rely on limited-bandwidth networks, quantization and data rate constraints present significant challenges for iterative learning control (ILC). This study aims to design a general framework of linear encoding–decoding pairs for quantized ILC under channel transmission constraints. We first develop a unified mathematical framework that integrates existing encoding–decoding schemes within the quantized ILC loop, enabling both the linear encoder and decoder designs to be parameterized by a common set. By employing a p-type controller, we derive a convergence criterion for quantized ILC using the general linear encoding–decoding pair. Furthermore, we introduce a control signal fidelity metric (CSFM) to quantify the discrepancy between the control signal generated with and without a general linear encoding–decoding pair. Based on the CSFM, we provide systematic guidelines for selecting the parameters of the linear encoding–decoding pair. Finally, we establish practical selection rules for the parameters of linear encoding–decoding pairs when finite-level quantizers are used. These rules ensure that no saturation occurs while minimizing both the steady-state output tracking error and the CSFM, thus facilitating the practical quantizer selection in quantized ILC. The theoretical findings are validated through simulations involving industrial robot joint models.

Abstract:
This article investigates reach–avoid games involving defenders equipped with capture radii, where both defenders and attackers have different speeds. The main challenge lies in using geometric methods to analyze different speed ratios, construct barriers, or defensive advantage angles, and divide the state space into defensive and offensive advantage regions. This article proposes optimal analytical strategies for players based on the corresponding payoff functions, depending on the attacker’s position within different winning regions under various speed ratios. In addition, we demonstrate the existence of a unique optimal target point within the offensive advantage region. Unlike numerical methods, which are limited by computational complexity and real-time application capabilities, the proposed method allows for the precise calculation of barriers and real-time updates in nonpoint capture scenarios. Finally, simulation results validate the effectiveness of the constructed barriers in multiplayer reach–avoid games.

Abstract:
When disturbances or nonlinearities couple the observer and the controller, implementing active fault-tolerant control (AFTC) via the separation principle (SP) becomes challenging. This article proposes a novel AFTC framework with the goal of decoupling design for a class of uncertain nonlinear systems, thereby recovering the use of SP in AFTC design. An observer is developed for fault diagnosis and state estimation based on the system outputs, and the boundedness of the estimation errors is guaranteed. Next, an active fault-tolerant controller integrated with an adaptive mechanism is constructed for fault accommodation using the obtained fault information. To mitigate bidirectional influences between the observer and controller designs, all estimation errors and disturbances are treated as new disturbances in the AFTC system (AFTCS), and adaptive updating terms are designed to compensate for these disturbances. The stability of the AFTCS is analyzed, ensuring that all signals in the closed-loop system remain bounded and that the output tracking error converges to a neighborhood around zero. The effectiveness of the proposed approach is illustrated through a numerical simulation example.

Abstract:
This article presents a novel nonlinear adaptive proportional–integral (PI)-like tracking control approach designed for a class of uncertain nonlinear systems. The proposed method offers several key advantages: 1) it maintains a simple PI structure while incorporating nonlinear elements; 2) unlike traditional PI control, which typically employs fixed PI gains and is susceptible to integration saturation, this approach utilizes self-tuning PI gains to effectively eliminate saturation issues, thereby addressing the long-standing windup problem; and 3) it skillfully manages both the transient behavior and steady-state accuracy of the tracking error through a new prescribed performance function that is independent of initial conditions. This ensures that, for any unknown bounded initial tracking errors, the proposed PI-like control can uniformly confine the tracking error to a specified boundary (accuracy) within a predetermined time rather than over an infinite duration. The effectiveness and advantages of this method are validated through simulation results.

Affiliations: School of Intelligent Science and Control Engineering, Shandong Vocational and Technical University of International Studies, Rizhao, China; School of Engineering, Qufu Normal University, Rizhao, China; School of Control Science and Engineering, Tiangong University, Tianjin, China; Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan; School of Mathematics, Southeast University, Nanjing, China; School of Astronautics, Harbin Institute of Technology, Harbin, China

Abstract:
This work addresses the nonfragile fault-tolerant control for power cyber-physical systems (CPSs) under denial-of-service (DoS) attacks, in which the cyber attacks are considered to be strongly concealed. In the fact of power CPSs frequently subject to various attacks during the operation, the innovation is to construct a double-layer stochastic process composed of a semi-Markov chain and a sequence of observed mode to analyze the DoS attacks from the viewpoint of hidden semi-Markov chain. To address potential actuator failures and controller gain perturbations, an observed-mode-dependent nonfragile control scheme is developed. By constructing a mode-dependent Lyapunov function that incorporates both attack modes and observed modes, sufficient conditions are derived to ensure mean-square stability of the closed-loop system through the semi-Markov kernel (SMK) approach, which systematically handles the stochastic characteristics of dwell time (DT) distributions under incomplete attack mode information. Finally, a simulation example demonstrates the validity of the proposed approach.

Abstract:
This article investigates the fast consensus problem in open multiagent systems (OMASs), where agents can randomly join or leave the network. Such dynamic behaviors significantly impact system consensus and its convergence rates. To address these challenges, we analyze both the frequency of agent switching and the duration during which the network remains nonconnected. A consensus condition for OMAS with time-varying network topology is derived, and explicit upper bounds on switching frequency and dwell time are established to guarantee consensus. To further achieve fast consensus, a convergence rate optimization scheme is proposed, along with a distributed implementation based on the alternating direction method of multiplier. Extensive simulations demonstrate the effectiveness and superiority of the proposed control strategy compared to existing OMAS consensus approaches.

Abstract:
The high precision tracking is a fundamental objective for iterative learning control (ILC) systems, which may be challenging in the presence of the iteration-varying disturbances. This article aims to address the robust tracking control problem for ILC systems having the iteration-varying disturbances, where the accurate model information is unavailable. Based on the input and disturbed output data collected from the test iterations, the nominal model of the ILC system is first constructed, under which a disturbance observer (DOB) is established to estimate not only the iteration-varying disturbance but also the model uncertainty. Further, a DOB-based ILC updating law is developed to achieve the robust tracking objective through inserting the estimation of the iteration-varying disturbance and the model uncertainty such that the tracking error is dependent continuously on the bound of the second-order variation rate of the disturbance. Particularly, the perfect tracking objective can be realized under the iteration-varying disturbance subject to the convergent variation rate. As a result, the tracking performance of the ILC system is improved under the iteration-varying disturbance, where the design of the DOB and the DOB-based ILC updating law depends only on the input and output data from the test iterations in the absence of the accurate model information.

Affiliations: Key Laboratory of Service Computing and Applications, Guangdong Province Key Laboratory of Popular High Performance Computers, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China; Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China; Department of Radiology, Guangzhou First People’s Hospital School of Medicine, South China University of Technology, Guangzhou, China; Department of Experimental Research, South China Hospital, Medical School, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Shenzhen University Medical School Shenzhen University, Shenzhen, China

Abstract:
Diffusion probabilistic models (DPMs) have recently demonstrated promising performance in medical image segmentation. However, traditional DPM has difficulty handling the irregular structure of images and the inherent similarity between lesions and surrounding tissues. To overcome these challenges, we propose an innovative architecture, the multiscale Mamba DPM (MsM-DPM), designed to enhance medical image segmentation. Specifically, MsM-DPM introduces a multiscale attention fusion module (MSAFM) in a multiscale denoising UNet (Ms-DU) to capture lesion deformations from multilevel features, thereby enhancing the model’s robustness to shape and scale variations. Furthermore, in the segmentation network, a multilayer axial feature module (MLAFM) is used to adaptively aggregate the global context features from the Mamba encoder to enhance the expression of features in the spatial dimension by capturing axial multiscale features. The multilevel global context (MLGC) module is then used to reconstruct skip connections using graph convolutional network inference, and the enhanced features are assigned to each layer in the decoder to capture the contextual relationship of features. Finally, the feature fusion module (FFM) integrates deep features with upsampled features in the decoder, enhancing the network’s ability to capture lesion boundary details. Our MsM-DPM effectively encodes the semantic difference between lesions and background to improve the representation of their internal features. Extensive experiments on six datasets, LUNA16, ATM22, COVID-19, Self-collected datasets, Pancreas, and BT-MSD, show that the proposed MsM-DPM outperforms existing segmentation methods. Our code is publicly available at https://github.com/suhuaqiang/deep-learning

Abstract:
This article is concerned with the zonotopic set-membership fusion estimation (SMFE) problem for a class of complex networks (CNs). The measurements of the CNs are transmitted to a remote fusion center through a shared communication network. Due to the limited network bandwidth, the transmissions of the measurement information occur intermittently, and the nodes’ transmission intervals may exceed their sampling periods. To enhance the utilization of the measurement information, each node of the CN is equipped with a buffer for real-time data storage, so that the fusion center can utilize more measurement information at time instants when the node’s transmission interval is larger than its sampling period. The aim of this article is to design SMFE algorithms based on both the parallel fusion scheme and the data-compression fusion scheme, respectively, using the data received at the fusion center. First, by iterating the state equation of the CN, a batch processing method is proposed to process the input data of the fusion center concurrently. Subsequently, by employing the zonotopic set-membership estimation (SME) technique, the desired SMFE algorithms are designed. Moreover, sufficient criteria are established to ensure that the sizes of the output zonotopes of the SMFE algorithms remain uniformly bounded. Finally, two numerical examples are presented to illustrate the effectiveness of the proposed algorithms.

Affiliations: Department of Mathematics, School of Sciences, Hangzhou Dianzi University, Hangzhou, China; School of Automation, Southeast University, Nanjing, China; Institute of Information and Control, Hangzhou Dianzi University, Hangzhou, China; School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen, China; Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen, China

Abstract:
In this article, the evolution of social power is studied within a unified framework comprising two classes of individuals: oblivious individuals and stubborn individuals, whose opinion dynamics are described by the DeGroot averaging model and the Friedkin–Johnsen model, respectively. A proper subset of the simplex is identified to ensure the well-posedness of social power, and it is demonstrated that the corresponding opinion dynamics is convergent for each issue by restricting the initial social power to this proper subset. Through the reflected appraisal mechanism, a nonlinear mapping governing the social power evolution together with its invariant set is derived, and some sufficient conditions with linear time complexity for the convergence of social power are established by proving that this nonlinear mapping is contractive on the invariant set. Furthermore, for the final social power, it is found that both autocratic and democratic social power cannot be achieved during the evolution, and the average social power of oblivious individuals is larger than that of stubborn individuals, indicating that the network topology has a greater impact on social power than individual stubbornness. In addition, it is observed that the final social power ranking of oblivious individuals is consistent with their centrality ranking, and a rigorous lower bound on the final social power is derived for each stubborn individual. Finally, a numerical example is provided to demonstrate the correctness of the theoretical analysis.

Abstract:
This article delves into an optimal fixed-time tracking control scheme for human-in-the-loop (HiTL) multiagent systems (MASs) against actuator faults. For adapting various complex environments, an HiTL optimal control protocol is developed based on the simplified optimal control. Furthermore, the synchronization error containing the leader input is embedded into the cost function, which enables the achievement of the optimal control objective and ensures the execution of the tracking control under the HiTL control. By adding exponential terms, a novel reinforcement learning (RL) algorithm satisfying the fixed-time form is proposed to attain the optimal fixed-time controller, which prompts the convergence rate of system signals while ensuring minimum energy consumption effectively. Meanwhile, actuator faults are considered and compensated in the controller design process to attain exceptional system performance. Consequently, the presented optimal control scheme ensures that all signals of the closed-loop system maintain bounded in a fixed time. The simulation results verify the feasibility of the presented control method.

Abstract:
In this article, the variational generalized Nash equilibrium (vGNE) seeking problem for general monotonic game with multiple coupling constraints involving dynamical players is explored. Specifically, a distributed vGNE-seeking neural network (vGSNN) with a feedback controller is designed based on high-pass filter, which efficiently transforms players’ high-order dynamics into equivalent second-order ones. To further relax the requirement on parameter predesign, we propose a controller that uses adaptive weights to replace the traditional fixed gains, which realizes the full distribution of the vGSNN. Furthermore, to enhance the robustness of the vGSNN against disturbances, a novel sliding-mode controller is incorporated to ensure finite-time disturbance rejection while maintaining the full distribution of the vGSNN. Finally, an uncrewed aerial vehicle (UAV) swarm game is put forward to verify the effectiveness of the vGSNNs.

Affiliations: Department of Electrical Engineering, Pakistan Institute of Engineering and Applied Sciences, Islamabad, Pakistan; Electrical Engineering Department and the Interdisciplinary Research Center for Sustainable Energy Systems, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia; Interdisciplinary Research Center for Sustainable Energy Systems, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia; School of Electrical Engineering, Korea University, Seoul, South Korea; Université Paris-Saclay Evry, IBISC, Evry, France

Abstract:
This article investigates the leader–following cluster consensus for generic linear heterogeneous multiagent systems (MASs). Unlike the existing research, a novel event-triggered (ET) control mechanism is designed and developed on the transmission side of the agents, over directed communication topologies, to reduce communication load. For this purpose, a variable threshold function as the fully distributed ET condition (ETC) is suggested, which provides a smooth transition and considers both maximum and minimum threshold levels for triggering. A relative-state feedback-based cluster consensus control protocol is designed by considering the cooperative and competitive interaction behavior of agents. Then, the convergence analysis is performed by utilizing the Lyapunov method. This work is then further extended for the ET observer-based output feedback cluster consensus problem. The proposed ETC naturally eliminates the Zeno behavior for each agent. In contrast to existing methods, a variable threshold-based ET scheme, a cooperation-competition network, and an elimination of Zeno behavior for both state-based and output-based methods have been considered for the leader–following cluster consensus. Finally, illustrative examples are used to validate the theoretical results.

Abstract:
Panchromatic images (PANs) and multispectral (MS) images (MSs) are widely used for dual-source remote sensing image classification, gradually becoming a research hotspot. However, making the most of dual-source image information with insufficiently labeled samples is a significant challenge. This article proposes a progressive semi-distillation model (PSDM) to classify dual-source remote sensing images with insufficient samples. We design a framework of rookie teacher network (RTN)-teaching assistant system (TAS)-student grouping network (SGN) in the case of a traditional teacher network (TN) (i.e., rookie TN (RTN)) that does not provide excellent guidance to student network (SN) due to insufficient samples. The PSDM expands the samples and compresses the space through the RTN-SGN structure to cope with the dilemma of insufficient samples. To make RTN better guide the SGN, we design TAS, which can gradually guide SGN to learn the samples from easy to difficult. It can also further assist SGN training to improve the classification performance of SGN with insufficient samples. We design SGN and add cooperation and correction mechanism to better learn dual- source information. These strategies can eliminate SGN’s over-dependence on the RTN, help SGN outperform the RTN, and achieve the effect of semi-distillation. Experimental results and theoretical analysis have sufficiently pointed out the proposed method’s accuracy, efficiency, and robustness under insufficient sample situations. Our model is available at https://github.com/MarjordCpz/PSDM.

Affiliations: College of Electronic and Information Engineering, Tongji University, Shanghai, China; Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China; College of Electronic and Information Engineering, State Key Laboratory of Autonomous Intelligent Unmanned Systems, Frontiers Science Center for Intelligent Autonomous Systems, Ministry of Education, Tongji University, Shanghai, China; Department of Electrical and Computer Engineering, Tandon School of Engineering, Control and Networks Laboratory, New York University, Brooklyn, NY, USA

Abstract:
This article considers the output regulation problem for an unknown discrete-time system subject to the random combination of denial-of-service, replay, and deception attacks on both sensor-controller and controller-actuator channels. We propose a learning-based receding-horizon control with historical output signals. It offers two advantages over state and output feedback regulators in the sense that it requires neither exact knowledge of system dynamics nor a direct measurement of external disturbance on one hand, and on the other hand, it can counteract the adverse impact of hybrid attacks on the executive capability of the actuator, regardless of the seriously tampered data on the sensor-controller channel. To overcome technical difficulties from hybrid attacks on both channels, we generalize the Markov-parameter-based time-series control method to generate a data packet containing the current and future control inputs, which are further compromised on the controller-actuator channel. Thus, a recovery procedure is additionally designed to solve the model-free output regulation problem by distinguishing the undamaged predicted inputs based on the proposed hybrid attack detection procedure.

Abstract:
competitive swarm optimizer (CSO) is considered as a prominent paradigm for solving large-scale multiobjective optimization problems (LMOPs). However, the pairwise random competition (PRC) mechanism used in most existing CSOs may limit their performance in solving LMOPs due to the following reasons. First, when the winner particle obtained by PRC is of poor quality, it may limit the learning effect of its corresponding loser particle. Second, due to the stochastic nature of PRC, the evolutionary direction of the loser particles may be drastically perturbed over the iterations, thus slowing down their convergence speed. To alleviate the above issues, this article proposes a constrained learning (CL)-based CSO for tackling LMOPs, called CL-CSO. First, CL-CSO adopts a set of reference vectors to divide the original objective space into several subregions. Second, CL-CSO designs a CL-based strategy, including the intra-subregion learning and cross-subregion learning strategy, which let the loser particles only learn from the winner particles in their intra-subregions or neighboring subregions, respectively. Moreover, CL-CSO designs a Gaussian model assisted evolutionary strategy to help the evolution of winner particles, aiming to further improve the diversity and quality of winner particles. This way, the learning effect of particles and the overall convergence speed can be significantly enhanced. Compared to several competitive algorithms for tackling LMOPs, experimental results show that CL-CSO performs well in solving two well-known benchmark LMOPs (containing 2–3 objectives and 500–5000 decision variables), as well as real-world instance selection problems.

Affiliations: School of Artificial Intelligence and Big Data, Hefei University, Hefei, China; School of Artificial Intelligence, Hefei Institute of Technology, Hefei, China; School of Electrical and Mechanical Engineering, the University of Adelaide, Adelaide, Australia; School of Artificial Intelligence, Beijing Normal University, Beijing, China; Anhui Province Key Laboratory of Big Data Analysis and Application, School of Data Science and School of Computer Science and Techonology, University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence, Hefei, Anhui, China; Department of Computer Science, University of Illinois at Chicago, Chicago, IL, USA; Zhuhai UM Science and Technology Research Institute, Faculty of Science and Technology, University of Macau, Macau, Hong Kong

Abstract:
The knowledge tracing (KT) aims to track changes in students’ knowledge status and predict their future answers based on their historical answer records. Current research on KT modeling focuses on predicting student’ future performance based on existing, unupdated records of student learning interactions. However, these approaches ignore the distractors (such as slipping and guessing) in the answering process and overlook that static cognitive representations are temporary and limited. Most of them assume that there are no distractors in the answering process and that the record representations fully represent the students’ level of understanding and proficiency in knowledge. In this case, it may lead to many lack of synergy and incoordination issue in the original records. Therefore we propose a cognitive representation optimization for KT (CRO-KT) model, which utilizes a dynamic programming algorithm to optimize structure of cognitive representations. This ensures that the structure matches the students’ cognitive patterns in terms of the difficulty of the exercises. Furthermore, we use the co-optimization algorithm to optimize the cognitive representations of the subtarget exercises in terms of the overall situation of exercises responses by considering all the exercises with co-relationships as a single goal. Meanwhile, the CRO-KT model fuses the learned relational embeddings from the bipartite graph with the optimized record representations in a weighted manner, enhancing the expression of students’ cognition. Finally, experiments are conducted on three publicly available datasets respectively to validate the effectiveness of the proposed cognitive representation optimization model. The source code of CRDP-KT is available at https://github.com/bigdata-graph/CRO-KT.

Abstract:
Semi-supervised learning on data streams with concept drift has attracted considerable attention in recent decades. Many existing algorithms have achieved promising results on low-dimensional data streams by leveraging unlabeled data and adapting to nonstationary distributions. However, real-world data streams often exhibit complex entanglement and high dimensionality, which are usually overlooked by current approaches, resulting in fragile classification performance. This highlights the need for effective representation learning on evolving data streams to enhance the reliability of model prediction. To this end, we propose a novel algorithm for online semi-supervised learning on high-dimensional data streams by learning from contrastive evolving micro-clusters (MCs), named CEMC. Unlike existing methods, CEMC explicitly mitigates feature entanglement through contrastive MC representation learning, with model initialization guided by contrastive objectives and representation updates triggered by potential drift. To ensure reliable semi-supervised learning, we further model the reliability of contrastive MCs to support online classification and enable rapid adaptation to concept drift. By maintaining contrastive MCs online, CEMC preserves and adapts to evolving concepts within a limited memory budget, while sustaining a discriminative representation space. Empirical results on fourteen real-world benchmark datasets demonstrate the effectiveness of CEMC compared to six state-of-the-art algorithms.

Abstract:
The study investigates the problem of attack-compensated control for two-dimensional (2-D) fuzzy systems modeled by the Roesser framework, subject to the constraints of limited communication channels. A novel event-triggered stochastic protocol (ETSP) with nonhomogeneous sojourn probabilities is introduced to save communication resources. By randomly selecting a controller node at each time step to transmit signals, the protocol schedules communication between controllers and actuators, thereby reducing communication load. To address the injection of false data into control signals caused by network attacks, a compensation mechanism based on a sojourn-probability-based predictor is designed. Sufficient conditions are subsequently established, based on Lyapunov theory, to ensure the mean-square asymptotic stability of the closed-loop system while preserving the desired performance level. Finally, the particle swarm optimization (PSO) algorithm is employed to enhance the controller design, and a simulation example is provided to verify the effectiveness and applicability of the proposed method.

Abstract:
This study focuses on the model reference adaptive tracking control problem for uncertain switched systems using a dynamic event-triggered approach. Compared with the existing studies, the switching adaptive laws and switching adaptive tracking controller are dynamically event-triggered simultaneously for data transmission, leading to several challenges in achieving the tracking task and Zeno-free behavior. A multiple Lyapunov function method is established to design a switching event-triggered adaptive law and switching dynamic event-triggered adaptive tracking controller. The proposed dynamic event-triggered mechanism guarantees that the interexecution time between two consecutive triggered points has a positive lower bound. The state-dependent switching signal and switching dynamic event-triggered adaptive tracking controller are designed such that all the signals of the error dynamic system are bounded, and the system state asymptotically tracks the desired reference model state. Finally, an example of an electro-hydraulic system illustrates the availability of the established strategy.

Abstract:
In the aerospace field, equipment failures can lead to substantial economic losses and pose significant safety risks, making effective fault diagnosis crucial. Traditional fault diagnosis methods typically require large, precisely labeled datasets, which are challenging to obtain in aerospace applications due to the rarity and unpredictability of faults. To overcome these limitations, this article proposes a novel conditioned multiscale generative adversarial networks (GANs) approach designed to enhance fault diagnosis performance under small-sample conditions. Initially, raw vibration signals undergo preprocessing using the short-time Fourier transform, which expands frequency-domain features while preserving essential time-frequency characteristics. Subsequently, conditioned multiscale GANs are trained on these limited datasets, employing multiscale convolutional kernels to extract and fuse rich features, thus generating high-quality synthetic samples. Finally, these synthetic samples are combined with the original dataset to train a convolutional neural network offline, which can subsequently perform real-time online fault diagnosis. Extensive validation on two aerospace-related datasets demonstrates that the proposed method significantly enhances fault diagnosis accuracy and efficiency, even when the available training data is severely limited.

Abstract:
Colorectal cancer remains a pressing challenge in global health, necessitating advanced biological models and analytical methodologies. Tumor organoids (tumoroids) have emerged as a compelling platform for cancer research, owing to their capacity to replicate the genetic and structural complexity of human tissues. However, extracting meaningful gene regulatory insights from bulk ribonucleic acid (RNA) sequencing data derived from tumoroids remains nontrivial due to cellular heterogeneity and temporal variation. We propose, for the first time, a comprehensive Bayesian framework to model gene expression dynamics throughout the developmental trajectory of colorectal tumoroids. We introduce a nonparametric Dirichlet process mixture model (DPMM) to cluster genes based on temporal expression patterns and a sparse regression scheme, incorporating Horseshoe+ priors, to construct gene regulatory networks (GRNs) among identified clusters. The proposed approach demonstrates robust performance in capturing high-dimensional relationships, enabling elucidation of key regulatory mechanisms in tumor progression. Our results offer valuable insights for personalized treatment and underscore the utility of Bayesian methods in complex biological systems.

Abstract:
Robust optimization (RO) methods have been developed to improve the reliable operation performance of wastewater treatment process (WWTP) under uncertainties. However, the time-linkage uncertainty between uncertainties in the successive process of WWTP leads to a more complex problem. To solve this issue, a distribution-prediction-based robust multiobjective optimization (DP-RMO) algorithm is proposed to obtain robust optimal set points, which can enhance the operation stability of WWTP. First, the robust multiobjective optimization (MOO) objectives are established based on adaptive kernel functions. Then, the effluent quality (EQ) and operation cost (OC) objectives with time-linkage uncertainty in WWTP can be dynamically described. Second, a data-driven predictor is designed based on Gaussian process (GP) to obtain the distribution of time-linkage uncertainty. The predictor takes the variations in the robust solution spaces at adjacent moments as input, which can capture the time-linkage uncertainty between uncertainties at different moments. Third, a self-adjustment evolutionary strategy is proposed to optimize the expectation of robust objective functions through the predicted information. The evolutionary parameters are adaptively adjusted according to the discrepancy in evolutionary states, which can obtain robust optimal set points of WWTP. Finally, the proposed DP-RMO algorithm and other comparison algorithms are tested in the benchmark simulation model No. 1 (BSM1) of WWTP. The experimental results show that DP-RMO can reduce the adverse effects of time-linkage uncertainties. Besides, the optimal set points obtained from DP-RMO exhibit better EQ and OC without sacrificing the robustness performance.

Abstract:
By means of a fully actuated system (FAS) approach, this article is concerned with an anti-disturbance tracking control problem toward a class of lumped disturbances containing the model uncertainties and external disturbances. A FAS predictive control with a generalized proportional-integral observer (GPIO) is presented to address this problem. Concretely, a FAS model of discrete-time nonlinear systems with the lumped disturbances is firstly given as a control-oriented one. Then, a GPIO is developed to achieve an accurate estimation for the lumped disturbances by adopting a less conservative disturbance assumption, which provides a better foundation to construct a disturbance preview. Furthermore, an incremental FAS (IFAS) prediction model with a disturbance preview is constructed by utilizing a new type of Diophantine Equation. Dependent on this IFAS prediction model, the multistep ahead predictions can be obtained to minimize an objective function to yield an optimal anti-disturbance controller, such that the desired tracking performance can be guaranteed. The depth analysis derives a sufficient condition for the bounded stability and tracking performance of the closed-loop FASs. The proposed GPIO-based FAS predictive control provides a solution to the spacecraft attitude control for verifying the feasibility.

Abstract:
This article investigates the leader-follower consensus tracking problem for non-smooth multiagent systems (MASs) with prescribed performance constraints. The non-smooth system is transformed into an equivalent smooth one based on Cellina approximate selection theorem. A novel mapping-based barrier function is introduced to get rid of the sign limitation, which enables us to design a tube-type performance function capable of achieving zero-overshoot consensus, as the initial constraining condition can be naturally satisfied without manual adjustment. The design of the controller is approximation-free by the use of the backstepping technique that can achieve the performance requirements with low computation complexity. Based on the Lyapunov stability analysis, it is proved that all signals of the closed-loop system are uniformly ultimately bounded. The effectiveness of the method is demonstrated with simulation examples.

Affiliations: School of Information Engineering, Key Laboratory of Marine Synaesthesia Fusion Detection Technology and Amphibious Unmanned Intelligent Equipment, and Key Laboratory of Photonic Technology for Integrated Sensing and Communication, Ministry of Education of China, Guangdong University of Technology, Guangzhou, China; School of Information Engineering, Guangdong University of Technology, Guangzhou, China; School of Computer Science, School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, China

Abstract:
Linear discriminant analysis (LDA) is a widely used dimensionality reduction (DR) technique that is effective in extracting discriminative features across various fields. Ratio sum LDA (RSLDA), a variant of LDA, was developed to address the shortcoming of the LDA method, which tends to obtain features with weak discriminative information. However, the traditional ratio sum formulation is dominated by the maximum ratio, which makes it difficult to select highly discriminative features and contradicts the original goal of the ratio sum. In this article, we analyzed the underlying causes of the dominance problem in RSLDA. A novel discriminant feature learning method via balance ratio sum discriminant analysis (BRSDA) is proposed. BRSDA effectively balances the ratios of the model formulation, thereby mitigating the domination problem. It focuses on optimizing low-quality projection directions, thereby yielding a well-balanced solution with consistently strong projection quality. First, a minimization ratio sum (Min-RS) criterion is adopted, which leverages the balance property of the harmonic mean to balance the gaps between the ratios. Second, Min-RS is integrated with the \ell _p -norm to further balance gaps between ratios. By amplifying the differences across projection directions, the \ell _p -norm drives BRSDA to emphasize the optimization of low-quality directions, thus raising the lower bound of direction quality. Finally, since obtaining a closed-form solution for the BRSDA problem is challenging, the gradient descent method is employed to solve its optimization. Sufficient experimental results verify the effectiveness of BRSDA, and BRSDA can effectively solve the domination problem and extract discriminative features.

Abstract:
The existence of stochastic sampling phenomena in wastewater treatment processes (WWTPs) breaks the assumption that the existing control strategies use periodic data, and the operational constraints of equipment and the requirements for effluent water quality impose constraints on the system’s input and output. These factors collectively increase the difficulty of achieving stable control of dissolved oxygen concentration (DOC). To solve these problems, a data-driven model predictive control (DDMPC) strategy is proposed to achieve stable control of constrained WWTPs with stochastic sampling intervals. First, a DDMPC framework is designed, which involves designing the objective function based on the mathematical expectation of the predicted output and considering system input and output constraints. In this framework, the problem of stochastic data acquisition caused by stochastic sampling can be solved, and the stable operation of the system can be ensured under constraints. Second, a data-driven multimodel prediction structure is constructed based on the stochastic characteristics of the sampling intervals. Specifically, fuzzy neural networks (FNNs) that match possible sampling intervals are established, thereby providing predictive outputs for the control process at the corresponding sampling instants. Third, a controller solving algorithm based on the generalized multiplier method is proposed, in which the constrained optimization problem within the model-predictive control (MPC) framework is reformulated by incorporating system constraints into the objective function as penalty functions to obtain the optimal control input that satisfies the constraints. Finally, the stability of the proposed DDMPC strategy is demonstrated, and its effectiveness is verified through the simulations on the benchmark simulation model No. 1 (BSM1). The results show that the proposed DDMPC strategy can achieve stable control of DOC in constrained WWTPs with stochastic sampling intervals.

Abstract:
This article studies a multiplayer capture-the-flag (CTF) differential game, where multiple pursuers try to intercept evaders whose objectives are to first reach a flag and then reach a return region. The critical point is that the flag and the return region are half-planes. Our goal is to address the problem of determining the game winner and computing the pursuit winning strategies. By decomposing the complex multiplayer game into many manageable subgames involving multiple pursuers and one evader, we present the strategies under which the pursuers guarantee to win against the evader, regardless of the evader’s strategy, with the necessary and sufficient conditions to determine the game winner. We then extend the results to the cases of the flag-staying time and the minimum safe flag position. To reduce the computational burdens, we prove that if multiple pursuers can ensure the pursuit winning against an evader, then at most two pursuers in this coalition are required. Finally, we solve the multiplayer game by evaluating pairwise subgame outcomes for pursuer–evader matchings. Numerical and experimental results are presented to illustrate the theoretical conclusions.

Affiliations: School of Artificial Intelligence and Robotics and the National Engineering Research Center for Robot Visual Perception and Control Technology, Hunan University, Changsha, China; College of Electrical and Information Engineering and the State Key Laboratory of Offshore Wind Power Equipment and Efficient Utilization of Wind Energy, Hunan University, Changsha, China; School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing, China; Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China; School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China; Department of Systems Engineering, City University of Hong Kong, Hong Kong, China

Abstract:
This article presents an adaptive neural network (AdNN)-based fault detection framework for the thermal processes of lithium-ion (Li-ion) batteries governed by 2-D semilinear partial differential equations (PDEs) with partially-known dynamics. To address the challenges of unknown nonlinear heat generation and limited sensor measurements, a two-stage approach combining reduced-order modeling with adaptive neural observation is proposed. First, a computationally tractable reduced-order model is derived through spectral approximation techniques. An adaptive neural observer is then designed to simultaneously estimate battery states and unknown nonlinear dynamics using only available surface temperature measurements. For robust fault detection, a hybrid scheme is developed that integrates model-based residual generation with data-driven threshold generation. Experimental validation on a pouch-type battery demonstrates the effectiveness of the proposed method in reliably detecting thermal abnormalities.

Abstract:
This article investigates the mean-square output consensus problem for heterogeneous linear multiagent systems (MASs) over random packet loss channels. Agent heterogeneity is reflected in possibly different state dimensions and dynamic parameters. In addition to heterogeneity, a major challenge arises from relaxing the commonly adopted independent and identically distributed (i.i.d.) assumption on packet losses. To capture temporal correlations that are prevalent in practice, packet losses are modeled by a discrete-time Markov process. Since existing consensus controllers designed for i.i.d. losses may fail under Markovian packet losses, novel dedicated control schemes are developed. Two packet loss scenarios are considered: identical and nonidentical packet losses. For identical packet losses, where all channels drop packets simultaneously, both analytical and numerical consensus conditions are derived to guarantee consensus of the distributed observers. The analytical condition reveals the interplay among packet loss rate, communication topology, and system dynamics, while the numerical conditions are more computationally tractable. An output-regulation-based controller is then designed to achieve mean-square output consensus. For the more general case of nonidentical packet losses, edge Laplacian theory is employed to decouple packet loss processes from the communication topology, leading to consensus conditions for the distributed observers, as well as corresponding controllers that guarantee mean-square output consensus. Finally, numerical simulations are utilized to validate the results.

Abstract:
This article investigates the consensus problem of multiple heterogeneous-dimensional switched nonlinear systems (HDSNSs). Each HDSNS consists of nonlinear subsystems that may have distinct state dimensions, along with a rule governing the switching among them. Currently, the consensus problem of multiple HDSNSs remains unresolved, primarily due to the highly complex dynamic characteristics exhibited by multiple HDSNSs. This article addresses the specific practical output consensus problem for a class of multiple HDSNSs, thereby aiming to fill the corresponding research gap. Each subsystem of the considered agent system is described by a nonlinear strict-feedback system, and the switching signal of the agent system is subject to the minimum dwell-time constraints. The cooperative control goal for the multiple HDSNSs is accomplished through the proposed protocol, which requires only sampled-data output interactions between agents. A numerical example verifies the proposed theorem.

Abstract:
Prescribed performance (PP) control is widely used in the construction of consensus protocols for multiagent systems (MASs) due to its property of ensuring that the variables of interest are constrained within the prescribed range during the control process. However, when unpredictable faults such as sudden sensor faults occur, or parameters such as the sampling interval are selected improperly, it can cause singularity problems and render the PP protocol ineffective. Introducing shear mapping into the PP mechanism can resolve the singularity problems, but it requires solving complex nonlinear equations, which may heavily occupy agents’ computational resources. To address this issue, we propose a novel dynamic shear mapping mechanism, based on which an event-triggered PP consensus protocol is developed for a class of heterogeneous leaderless MASs. Specifically, by constructing a dynamic shear angle related to the constraint performance functions and variables of interest, the need to solve nonlinear equations is reduced, while the hard–soft transition of performance constraint in the control process is achieved. It is proven that, under the proposed protocol, the consensus errors can strictly satisfy the PP requirements during a prescribed stage, and ultimately converge to zero asymptotically. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed method.

Abstract:
In this article, a novel hybrid event-triggered (ET) control framework is constructed based on the adaptive critic technique, aiming to address the optimal tracking issue of discrete-time nonlinear networked control systems. First, an augmented plant is created by combining the system state with the reference trajectory, transforming the optimal tracking control design into the optimal regulation problem of the reconstructed nonlinear error system. Subsequently, to conserve communication network resources and ensure the stability of the error system, a hybrid ET mechanism is developed to determine a constant interval for event silence. This approach not only alleviates the limited network bandwidth but also eliminates the need for continuous evaluation of triggering conditions, as seen in traditional event-based methods. Regarding algorithm implementation, the model, critic, and action networks are established to execute the online adaptive critic algorithm, which allows the tracking control policy to be adjusted in real-time to reach the optimal level. Finally, an experimental plant with nonlinear characteristics is presented to illustrate the overall performance of the proposed online tracking control method with the hybrid ET mechanism.

Abstract:
Existing computational methods for the k -winners-take-all ( k WTA) operations often suffer from limitations in eliminating lagging errors, high computational complexity, and weak robustness. To deal with these challenges, we propose an integral-enhanced adaptive gradient neural network (IAGNN) for k WTA. We demonstrate that the IAGNN integrates an adaptive coefficient to eliminate lagging errors while retaining an O(n^2) computational complexity. We proved the Lyapunov stability and robustness of the IAGNN. We provide a numerical simulation, and the results demonstrate the stability and robustness of the IAGNN. Furthermore, we implement the IAGNN in a multirobot tracking system for competitive allocation coordination, and the results demonstrate the operational feasibility and noise resistance of the IAGNN.

Abstract:
This article investigates the optimal tracking control problem for high-order uncertain nonlinear systems by developing a simplified reinforcement learning (RL) framework with minimal neural networks (NNs). In contrast to conventional RL-based schemes that rely on recursive backstepping and require 3n NNs (where n is the system order), the proposed method leverages high-order fully actuated (HOFA) system theory to reformulate the dynamics into a compact normal form. This enables a unified, nonrecursive controller design that requires only three NNs regardless of the system order, thereby significantly reducing computational complexity and facilitating practical implementation. Furthermore, this work overcomes a critical theoretical deficiency in existing simplified RL strategies, where the vanishing minimum eigenvalue of the NN basis function correlation matrix often leads to invalid Lyapunov stability analysis. A novel critic–actor weight update law is designed to bypass this problematic matrix, rigorously guaranteeing the semiglobal uniform ultimate boundedness of the closed-loop system without requiring persistent excitation (PE) conditions. Simulation results on a representative example demonstrate the effectiveness and computational efficiency of the proposed approach compared with existing methods.

Abstract:
This article investigates fixed-time synchronized convergence for disturbed second-order multiagent systems (MASs) in distributed optimization under the zero-gradient-sum (ZGS) scheme. A fixed-time ZGS distributed optimization method via sliding mode is first proposed for the second-order MASs, which avoids local minimization and rejects disturbances. To further achieve time-synchronized convergence, a hierarchical robust optimization method is then introduced. It employs a time-varying function-based local-minimization-free ZGS scheme within a virtual MAS to generate a reference signal that reaches the global cost function’s minimizer and a fixed-time synchronized sliding mode tracking controller to drive the original second-order MAS to track this signal. Beyond the capabilities of the first protocol, this method also ensures the time-synchronized convergence of each agent’s state components, low conservatism in terms of convergence time bounds, and privacy preservation. Numerical simulations demonstrate the effectiveness of the proposed methods.

Abstract:
The growing popularity of blockchain technology has underscored the need for robust network security. However, public blockchain networks remain vulnerable to attacks in which adversaries exploit numerous nonfunctional peer connections to disrupt block propagation across the entire network. In this article, we propose a practical nontargeted delay attack method and validate its feasibility, scalability, and significant impacts on blockchain networks of varying sizes, including EthereumPoW (ETHW) and premerge Ethereum Mainnet. In the ETHW network with 95 nodes, our adversarial peers introduce delays ranging from 0.33 to 2.8 s for half the nodes, with nearly one-third experiencing delays exceeding 5.9 s, derived from the 90th percentile of delay times. When in the premerge Ethereum network with 5739 nodes, over 80% of peers experience prolonged block propagation, resulting in a 77% increase in delay time, underlining the attacks’ scalability and efficacy in large-scale environments. We also optimize the Ethereum client Geth by relaxing certain connection restriction, significantly reducing attack costs. Delving deeper, we analyze the implications of delay attacks on proof-of-work (PoW) and proof-of-stake (PoS) consensus mechanisms, illustrating how attackers can gain extra revenues through such attacks. Specifically, we propose a novel combined strategy to facilitate reorganization attacks under PoS. These findings highlight the urgent need to strengthen network-layer defenses and reinforce peer-to-peer (P2P) network protocol security against real-world delay exploits.

Abstract:
This article proposes a novel discounted inverse reinforcement learning (DIRL) algorithm for linear quadratic (LQ) control of unknown continuous-time (CT) systems with partially observable states and an unknown discounted value function. Existing DIRL methods predominantly rely on full-state feedback, limiting their applicability to practical scenarios where only input–output data are available. To this end, a state reconstruction method is designed for the system controlled by an expert using the measured desired output. Based on this, a model-free output-feedback (OPFB) DIRL algorithm is presented to iteratively solve the unknown value function and the corresponding optimal OPFB control policy equivalent to the expert control policy. The convergence of the proposed algorithm and the nonuniqueness of solutions are rigorously analyzed. Finally, comprehensive simulations reveal the effectiveness of the proposed algorithm in recovering the expert control policy and its superior computational efficiency compared to state-of-the-art (SOTA) methods.

Abstract:
In this article, an input-constrained visual servoing formation controller is proposed for multiple quadrotor systems operating without intervehicle communication or relative position measurements. The aerial formation control is achieved by formulating image-based leader–follower dynamics using a virtual camera framework and sphere-based image moments. An adaptive velocity observer is developed for the follower quadrotor to estimate the relative velocity with respect to the leader quadrotor in communication-free environments. Input-constrained visual servoing and attitude controllers are proposed using an off-policy reinforcement learning (RL) algorithm to handle visibility and attitude constraints, without relying on accurate system model parameters. The stability of the closed-loop system is theoretically analyzed, and the effectiveness of the proposed controller is demonstrated through case studies.

Abstract:
Transferability estimation is a fundamental problem in transfer learning, which aims to predict whether transferring knowledge from a source domain will improve performance on a target task. Existing research focuses on classification and neglects domain/task differences, as well as only very limited research for regression. Most importantly, there is a lack of research to determine whether to transfer or not. To address these gaps, we propose Wasserstein distance-based joint estimation (WDJE), a unified transferability metric for both classification and regression under domain and task differences. WDJE facilitates decision-making on whether to transfer by comparing the target risk with and without transfer. To enable this comparison, we estimate the unobservable post-transfer risk using a nonsymmetric, interpretable, and easy-to-calculate upper bound that remains applicable even with limited target labels. The proposed bound relates the target transfer risk to source model performance, domain, and task differences based on the Wasserstein distance. We further extend the proposed bound to the unsupervised setting and establish a generalization bound from finite empirical samples. We evaluate WDJE and the proposed risk bound across 42 transfer scenarios, including CIFAR-100 (CF100) and Office-Home image classification and C-MAPSS remaining-useful-life regression prediction. WDJE achieves a perfect consistency index ( CI ) of 1 in 25 cases and an overall mean CI of 0.89, accurately suggesting when transfer should (or should not) be performed. The proposed bound achieves the average Pearson correlations of 0.99 on CF100, 0.72 on Office-Home, and 0.96 on C-MAPSS, illustrating state-of-the-art performance in approximating the true post-transfer risk.

Abstract:
Recurrent stochastic configuration networks (RSCNs) have shown great potential in modeling nonlinear dynamic systems with uncertainties. This article presents an RSCN with hybrid regularization to enhance both the learning capacity and generalization performance of the network. Given a set of temporal data, the well-known least absolute shrinkage and selection operator (LASSO) is employed to identify the significant order variables. Subsequently, an improved RSCN with L2 regularization is introduced to approximate the residuals between the output of the target plant and the LASSO model. The output weights are updated in real-time through a projection algorithm, facilitating a rapid response to dynamic changes within the system. A theoretical analysis of the universal approximation property is provided, contributing to the understanding of the network’s effectiveness in representing various complex nonlinear functions. Experimental results from a nonlinear system identification problem and two industrial predictive tasks demonstrate that the proposed method outperforms other models across all testing datasets.

Abstract:
We introduce a novel deep graphical representation that integrates game theory (GT) principles with the laws of statistical physics (SP), enabling feature extraction and pattern classification within a unified learning framework. In our approach, neurons in a network are analogous to players in a GT model. Each neuron, viewed as a classical particle governed by the laws of SP, corresponds to a set of actions that represent specific activation values. The feed-forward process in deep learning (DL) is interpreted as a sequential game with each game involving multiple players. During training, neurons are evaluated iteratively and filtered based on their contributions to a payoff function, which is quantified using the Shapley value driven by a Gaussian–Boltzmann energy model. To mitigate the computational burden of exact Shapley value computations, we employ Monte–Carlo (MC) sampling, reducing the algorithmic complexity from exponential to polynomial. This approximation significantly improves scalability, making our framework suitable for larger networks. Neurons that significantly contribute to the payoff form strong coalitions, and only these neurons are allowed to propagate information to the next layers. Using the Shapley value, we devised a new model regularization technique, thereby improving overall performance. We applied this framework to facial age estimation and gender classification tasks. Experimental results show that our approach outperforms several traditional and recent machine learning models in terms of accuracy, precision, recall, and F1 -score.

Abstract:
Silent packet loss (SPL) poses a significant challenge for state estimation, due to the lack of information regarding the packet loss status (PLS). This issue is particularly prominent in event-based systems, where the interplay between event-triggered feedback mechanisms and SPL complicates the estimation process. Existing approaches often employ detectors, but achieving 100% detection accuracy remains nearly impossible, and false detections further complicate the probability distribution of system states. In this article, we propose a silent message-passing mechanism (SMPM) to address the SPL of measurements, which may be coupled with an event-based scheduler, as the feedback channel is also affected by the SPL. Besides, a dynamic Chi-square ( d – \mathcal X^2 ) detector is proposed, whose detection accuracy is proven to converge to 100% with time. Subsequently, an estimator based on the d – \mathcal X^2 detector under the SMPM is designed for unstable systems with the SPL of measurements. More importantly, a stability condition is established, revealing the relationship between the SPL rate and estimation performance. Both simulations and experiments validate the effectiveness of the theoretical findings presented in this article.

Abstract:
Modern manufacturers often require handling multiple tasks simultaneously under dynamic environments by sharing constrained machines. Existing multitask scheduling algorithms typically focus on transferring knowledge among multiple tasks. However, these algorithms overlook the need for collaborative multitasking efforts required to share constrained machines. To overcome this limitation, we propose a multiagent transformer (MAT)-based algorithm to solve multitask dynamic scheduling with constrained machines. Specifically, we first formulate the multitask scheduling problem as a sequential multiagent decision-making process, enabling agents to make collaborative decisions by accessing the actions of others. Furthermore, a joint policy network is developed to support the agents in adaptively selecting the appropriate heuristic for each task. It improves the decision-making quality by enabling agents to leverage common and task-specific knowledge. In addition, a comprehensive reward function is designed to guide the learning of a joint policy network for collaborative decision-making across tasks. This ensures that agents holistically consider the objectives of all tasks during the learning process. With these designs, the proposed algorithm can effectively address multiple tasks through collaborative machine sharing. The proposed algorithm is evaluated against 14 state-of-the-art competitors on 270 instances with varying scales. The results confirm that the proposed algorithm outperforms all competitors on each instance. In addition, the ablation study demonstrates the effectiveness of distinct reward mechanisms, revealing that the joint policy network makes more informed decisions by leveraging both individual and common knowledge.

Abstract:
In this article, to exclusively conquer detection degradation of benthonic organisms due to domain shifting between training and testing scenarios, an innovative domain-adaptive detection scheme, termed DAD-ULC, is holistically invented by uniformising light field and color distribution. To that end, the encoder–decoder domain converter (EDDC) with residual connection is created, such that samples in degraded domains can be transformed into a unified domain. The underwater light field perception loss (ULFPL) is further conceptualized by virtue of a multiscale Gaussian filter, so as to directly expedite light-field conversion, getting rid of benthonic organism structure information, thereby facilitating light-domain adaptation. By exploiting the similarity between generated and referenced images in Lab space, a color distribution consistency loss (CDCL) is empowered for color-distribution transfer. Eventually, the DAD-ULC scheme is established in an end-to-end manner by integrating with EDDC, ULFPL, and CDCL modules, thereby enabling identical light-color domains between training and testing samples. Comprehensive experiments and comparisons conducted on detecting underwater objects (DUOs) and URPC2020 datasets sufficiently demonstrate effectiveness and superiority in diversified domain-shifting challenges.

Abstract:
Set meal design (SMD) for online-to-offline (O2O) restaurant services presents a complex optimization problem, requiring the simultaneous satisfaction of diverse customer preferences, operational constraints, and profit maximization objective. To address this challenge, this article proposes a comprehensive mathematical formulation for the O2O-SMD problem. This formulation integrates complex operational requirements, such as dish variety, pricing, nutritional balance, and profitability, into a unified optimization problem with well-defined objective and constraints. To efficiently solve the O2O-SMD problem, we propose a tensor-based ant colony optimization (TACO) algorithm. Distinct from traditional ant colony optimization (ACO) variants, the core of TACO lies in reformulating the fundamental ACO operations into a tensor computational structure, enabling parallel optimization over O2O-SMD tasks at the algorithmic level. Furthermore, a dedicated local search strategy is integrated to refine solutions and accelerate convergence of the algorithm. The performance of TACO is evaluated on real-world restaurant data and benchmark instances. The experimental results show that TACO significantly outperforms a wide range of comparison algorithms in terms of solution quality, scalability, and computational efficiency, confirming its effectiveness and practical value for real-world O2O-SMD problems.

Abstract:
Constructing memristive neural networks (MNNs) with multiscroll chaotic attractors helps advance both theoretical and applied research on neural networks. However, the existing models mainly utilize complex memristor models with polynomial functions, nested composite functions, and so on, to generate multiscroll chaotic attractors, which leads to increased model complexity and difficulties in on-demand adjustment. Hence, this article proposes a reconfigurable multiscroll MNN (RMMNN) that can yield different types of multiscroll chaotic attractors merely by altering the memristive parameters without modifying its model. Through numerical methods, the complex dynamics of the RMMNN in different cases are analyzed, such as parameter-controlled multiscroll chaotic attractors, adjustable multistability, and parameter-induced transitions of multistability. In addition, the reliability of the numerical analysis is verified via the hardware circuits. Moreover, to address the issues of image security and low quality in telemedicine, a bidirectional rotation medical image encryption scheme (BRMIES) is developed based on the good pseudorandom chaotic sequences generated by RMMNN. Performance analysis demonstrates that BRMIES can effectively protect medical image and robustly handle various potential adverse interferences within telemedicine process.

Abstract:
A common scenario in aluminum electrolysis process is that the collected dataset contains different behavioral policies and some risky policies, such industrial scenario brings new challenges for offline reinforcement learning to learn safety and feasible optimization policy. This article proposes an offline multiobjective reinforcement learning with multicategory policy constraint for operation optimization decision-making (OODM) of the aluminum electrolysis process. The learned optimization policy can surpass the behavior policy while also meet the strict safety requirements of industrial operations. To alleviate the distribution shift problem on multicategory behavioral policy, we present a multicategory policy constraint in the actor network that utilizes the mixture Gaussian variational autoencoder (GMVAE) to implement behavior cloning between the behavioral policy and the learned policy. Based on the actor–critic reinforcement learning architecture, we design two critic networks for multiobjective optimization. Except for the operational performance critic network, an additional safety critic network is introduced to guarantee that the learned policy satisfies the strict safety requirements of industrial operations. We also conduct extensive comparative experiments on the real-world aluminum electrolysis process. Experimental results demonstrate that the proposed method can achieve superior performance against the other offline reinforcement learning algorithms.

Abstract:
Encoding historical traffic scenarios is critical for autonomous driving trajectory prediction. However, existing methods face two fundamental challenges. First, neglecting future interactions leads to myopic predictions. Second, although query-centric paradigms capture multimodal interactions, their typically static query design may limit the adaptability of cross-temporal context fusion. To address these limitations, we propose Miformer, a trajectory prediction model that enhances historical–future spatial–temporal context interactions. First, we introduce a time query mechanism that transforms static agent interactions into dynamic temporal modeling by enabling cross-timestep information exchange between different agents and road geometry. Building upon this temporal foundation, we design a historical–future spatial–temporal interaction module (HF-STIM) that leverages iTransformer to model bidirectional dependencies between past and future contexts. To address the redundancy inherent in inverted embeddings, we further propose the minus-inverted Transformer (Mi-Transformer), which incorporates a dynamic residual learning mechanism to eliminate irrelevant dependencies while preserving critical bidirectional information flow. Finally, we employ a DETR-like decoder to generate diverse multimodal trajectory predictions. Experimental results demonstrate that Miformer achieves state-of-the-art performance on the INTERACTION dataset and exhibits competitive performance on the Argoverse dataset. These results highlight its effectiveness in real-world motion prediction. Our code is available at https://github.com/Morphlingxxx/Miformer-Trajectory-Prediction

Abstract:
Ergonomics or human factors engineering (HFE) mainly exploits human experiments to discover one’s cognitive and behavioral mechanisms. Such a paradigm, however, suffers from the scale of subject group and the extent to which they can stand for the whole studied population. Additionally, for real-time human–machine tasks, the experiment-modeling-validation-application path may not be applicable since the experiment cannot be flexibly conducted to update cognitive models, leading to a failure of the online system control and management. To solve the dilemma, this article proposes the generative artificial intelligence (GAI)-driven ergonomics to augment the HFE research. By introducing GAI techniques, virtual-real hybrid experiments are combined and supplement more heterogeneous samples, enhancing the input diversity for cognitive modeling and behavioral learning. The case studies of human–machine cooperative driving and aerospace robotic arm operation indicate that the innovative paradigm can effectively and efficiently augment the human experiment data. It can elevate the generality and robustness of human models.

Affiliations: College of Automation, Shenyang Aerospace University, Shenyang, China; School of Mathematical Science and Heilongjiang Provincial Key Laboratory of the Theory and Computation of Complex Systems, Heilongjiang University, Harbin, China; College of Information Science and Engineering, Northeastern University, Shenyang, China; State Key Laboratory of Industrial Control Technology, Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China

Abstract:
In this article, the double-layered iterative learning control (DLILC) approach is adopted to investigate the tracking control problem of repetitive nonlinear multiple-input–multiple-output (MIMO) systems under false data injection (FDI) attacks. Based on historical data, two control loops in the scheme are devised to improve tracking accuracy. More specifically, an outer loop adaptive set-point tuning mechanism is developed, which is independent of the inner-loop controller. Such a mechanism dynamically optimizes learning gains by leveraging historical data and significantly reduces reliance on preset system parameters. In the inner loop, a proportional-derivative controller is employed to form the feedback circuit. Furthermore, the double dynamic linearization technique is adopted to transform complex nonlinearities, coupling effects, and unknown uncertainties into a set of linearly estimable parameters. To address FDI attacks, an output observer-based real-time compensator is constructed, which is capable of promptly mitigating the impact of such attacks on system outputs. Simulation results demonstrate that the proposed scheme ensures high-precision tracking, substantially reduces computational burden, and exhibits superior resilience against attacks. The approach thus provides a new pathway toward secure and efficient iterative learning control of nonlinear systems.

Abstract:
Representation learning on continuous-time dynamic graphs (CTDGs) is critical for modeling evolving network behaviors. However, existing methods often fail to capture both temporal dynamics and structural nuances effectively. Since the community is well-known for manifesting the mesoscopic structure of graphs, we propose community-enhanced temporal walks (CTWalks), a novel framework that explicitly leverages community structures to enhance representation learning on CTDGs. CTWalks integrate three key innovations: 1) a community-guided temporal walk sampling strategy that captures intra and intercommunity interactions to mitigate locality bias, with theoretical guarantees; 2) a community-aware anonymization process that embeds contextual community labels for robust node representations; and 3) a neural ordinary differential equations-based encoding mechanism that models continuous temporal dynamics, including community information with high fidelity. Furthermore, we establish a theoretical connection between CTWalks and matrix factorization, revealing the principled foundation. Extensive experiments on six benchmark datasets, including the large-scale tgbl-comment dataset with approximately one million nodes, demonstrate that CTWalks significantly outperform ten state-of-the-art methods in temporal link prediction, achieving substantial improvements in Area Under the receiver operating characteristic Curve (AUC) and average precision (AP) scores across diverse settings. This work advances dynamic graph learning by bridging community-aware structural insights with continuous-time modeling, enabling more accurate and adaptable representations for real-world networks. Our implementation is publicly available at https://github.com/leonyuhe/CTWalks.

Abstract:
In this study, the observer-based asynchronous stabilization is addressed for networked system under multichannel attacks, in which the asynchronous phenomenon refers to the mismatch between the controller mode and the actual attack mode. To accurately depict complex attack behaviors, a piecewise homogeneous semi-Markov chain (SMC) model modulated by a superstratum Markov chain is introduced, which can simultaneously describe the randomness of attack mode transitions and the time-varying nature of transition probabilities. Considering that the actual attack modes are inaccessible, an observer-based mode switching delay technique is designed to solve this challenge. Under the framework of a piecewise homogeneous SMC, a sufficient criterion is established to ensure the \varsigma -error mean-square stability under random multichannel denial-of-service attacks by means of a Lyapunov function depending on observed attack modes, piecewise homogeneous variables, and elapsed time. Moreover, matrix decoupling and convexification techniques are employed to reduce the computational complexity. Finally, the effectiveness of the proposed method is demonstrated through two practical simulation cases.

Affiliations: School of Journalism and Communication, Renmin University of China, Beijing, China; School of Journalism and Communication, South China University of Technology, Guangzhou, China; Department of Electrical and Information Engineering, Polytechnic University of Bari, Bari, Italy; Department of Informatics, Modeling, Electronics, and Systems, University of Calabria, Arcavacata, Italy; School of Computer Science and Engineering, South China University of Technology, Guangzhou, China

Abstract:
In a socially tense environment with rising emotional pressure, understanding the spread patterns of group emotions—particularly negative emotions—is crucial for identifying social risks. Extensive research has explored emotion contagion, often using propagation models where node state transitions rely on preset probabilities. However, these methods introduce randomness, making them less reflective of real-world dynamics by failing to capture individual node behaviors and interactions in emotional networks. To address this, our study introduces a novel approach integrating text-based emotion recognition with propagation models, reconstructing emotion contagion at an individual level. This model enhances traditional nodes with multihop agents driven by text emotion analysis, where agents record and respond to neighbors’ emotional states. As a result, emotion spread becomes a deterministic process, with individualized infection rates reflecting node variability. We categorized nodes based on emotional states, creating corresponding agent types to form the dynamic agent-based emotion model (AEmo). Tests on real-world and scale-free networks show this method effectively predicts group negative emotion spread and provides insight into individual emotion evolution, validating the model’s effectiveness.

Abstract:
This article investigates the chaotic suppression problem of a chaotic system with uncertain parameters. To solve this problem, a dynamic surface constructed based on the adaptive backstepping control method is considered. First, a novel dynamic surface is introduced in the controller design process, which is utilized to alleviate the “complexity explosion” problem of classical backstepping. Then, piecewise functions are used to avoid the singularity of virtual controllers and real controllers, and the proposed control scheme can achieve state stabilization of chaotic systems based on the fixed-time theory. The results indicate that the chaotic state can converge to a small neighborhood near the origin. Finally, simulations are used to verify the validity of the proposed approach, and the control scheme is applied to a permanent magnet synchronous motor (PMSM) and suppresses its chaotic behavior.

Abstract:
In a rehabilitation exoskeleton, stable and safe operation is of central importance in rehabilitation training. This article develops a soft prescribed performance (SPP)-based reinforcement learning (RL) control method to address the conflict between performance constraints and system degradation, ensuring high accuracy and safe operation. First, a tunnel-type prescribed performance function is used to achieve faster convergence and smaller overshoot. Safety boundaries are used to define the tolerable error range, and an intermediate system links the safety and soft boundaries. The soft boundaries are dynamically adjusted to ensure safe operation by temporarily relaxing constraints during performance degradation. An RL approach based on an actor–critic (AC) structure is employed to handle unknown lumped disturbance. Theoretical analysis confirms the stability of the closed-loop system. Furthermore, a series of experiments is conducted on a self-built upper-limb rehabilitation exoskeleton robot driven by pneumatic artificial muscles to validate the effectiveness and robustness of the proposed method.

Abstract:
This article investigates the design of an adaptive fuzzy output-feedback decentralized controller for a class of nonlinear multiagent systems (MASs). The considered systems are subject to unmeasurable states and are vulnerable to denial-of-service (DoS) attacks. Unknown nonlinear functions are approximated using fuzzy logic systems (FLSs). Furthermore, a switching-type fuzzy state observer is introduced to estimate the unmeasurable states. By leveraging the adaptive backstepping design technique and the dynamic surface control method, an adaptive fuzzy output feedback decentralized controller is synthesized. By combining Lyapunov stability theory with the concept of average dwell time (ADT), we rigorously prove that the proposed adaptive fuzzy decentralized resilient controller ensures the convergence of tracking errors to a small neighborhood of the origin despite DoS attacks, while maintaining the semi-global uniform ultimate boundedness (SGUUB) of all closed-loop signals. The effectiveness of the control strategy is verified by a nonlinear inverted pendulum system model and a group of multinonholonomic mobile robots.

Abstract:
This work presents an estimator-based distributed preset-time algorithm that effectively addresses the equality-constrained optimization problem on directed graphs (digraphs). Initially, we propose an innovative distributed preset-time estimator to accurately estimate the global information related to the cost function. Building on this, we develop an estimator-based distributed robust preset-time optimization algorithm incorporating integral sliding mode control, which is specifically tailored for strongly connected networks. Compared with existing algorithms, the proposed algorithm features three key innovations: improved precision in convergence time, enhanced robustness against disturbances, and expanded applicability to network topologies. Finally, we validate the preset-time optimization algorithm through numerical simulations, demonstrating that its convergence rate significantly outperforms those of current finite- and fixed-time algorithms.

Abstract:
This article investigates the distributed online optimization problem in a zero-sum game between two distinct time-varying multiagent networks. At each iteration, the agents not only communicate with their neighbors but also gather information about agents in the opposing network through a time-varying network, assigning weights accordingly. Moreover, we consider quantized communication and bandit feedback mechanisms, with agents transmitting quantized information and adopting one-point estimators. At each iteration, agents make and submit decisions and then receive the cost function values near their decision points rather than the full cost function information. To guarantee the payoff of each network, we design an algorithm named quantized distributed online bandit optimization in two-network (QDOBO-TN). We use dynamic Nash equilibrium regret to measure the positive payoff discrepancy between the decision sequence produced by Algorithm QDOBO-TN and the Nash equilibrium sequence. Furthermore, we propose a multiepoch version of Algorithm QDOBO-TN. The regret bounds for both algorithms are sublinear with respect to the iteration count T. Finally, we conduct a series of simulation experiments that further validate the effectiveness of the algorithms.

Abstract:
Constrained consensus formation tracking of autonomous underwater vehicle (AUV) networks is a challenging problem to solve, especially when the networks are possibly subject to nonuniform, time-varying communication delays and marine disturbances. This article presents a systematic design framework to achieve formation objectives while ensuring network stability under such uncertainties. First, a coordinate transformation is applied to the AUV kinematics to address nonholonomic constraints. A distributed consensus protocol is then used to coordinate the motion of vehicles, and utilizing the transformed kinematic model, the desired linear velocity and approach angles are determined accordingly. By employing the graph representation and Lyapunov–Krasovskii functional method, a robust stability criterion is derived in terms of linear matrix inequalities (LMIs) for a delayed network with disturbances. To improve the quality of AUV motion control, on top of the conventional backstepping controller, a sequential optimization procedure is developed for the first time, which enables optimizing the robust performance online while respecting motion constraints. Moreover, the overall stability of the resulting formation system is established. Finally, comparative simulations are carried out to verify the effectiveness and superiority of the proposed method.

Abstract:
This article investigates the prespecified performance consensus problem for a class of nonlinear multiagent systems (MASs) with unknown actuator faults. By employing a sensor-triggered mechanism and neural estimation algorithm, a novel leader–follower consensus protocol is devised for the nonlinear MASs. The developed sensor event-triggered mechanism comprises two parts, the first one is sensor event-triggered sampling, and the second one is event-triggered information transmission. Due to the presence of the sensor-triggered mechanism, the system states cannot be available in real time. In order to solve this challenge, a signal decomposition and compensation strategy is constructed to balance the intermittent sensor-sampled signals and the real system inputs. Furthermore, the considered actuator faults in each follower are not limited to be finite, the time, frequency and mode of the faults are also unknown. To address the unknown actuator faults in the nonlinear MASs, a resilient fault management mechanism is developed for each follower. Based on the managed actuator faults dynamics, some bounded estimation signals are constructed and the issue of “explosion of complexity” in the backstepping design procedure is eliminated through the application of nonlinear filters with compensation terms. Finally, simulation results are given to illustrate the effectiveness of developed control protocol.

Abstract:
This article investigates quasi-projective synchronization (Q-PS) of discrete-time fractional-order delayed memristive neural networks (DFDMNNs) with uncertainties. Firstly, by virtue of some useful inequality skills and basic properties of discrete-time fractional calculus as well as fixed-point theorem, several sufficient criteria on the existence of solutions for DFDMNNs with uncertainties are derived. Furthermore, Q-PS of DFDMNNs is explored under the delayed state feedback controller, and corresponding Q-PS criteria are established. Finally, one numerical example is presented to verify the availability of the theoretical results.

Abstract:
Complex strategic interactions of rational agents are ubiquitous in decision-making groups which greatly influence the evolutionary dynamics of many real-life networked systems. Here, we study how individual decision-making behaviors evolve when the topology of network interactions is weighted, and how the network of mixed coordinating and anti-coordinating games is driven to an equilibrium. We prove that the weighted pure coordinating or anti-coordinating decision-making dynamics, under both asynchronous and partially synchronous updates, will converge to the Nash equilibrium after finite strategy switches. Moreover, it follows that the upper bound on the number of switches for the convergence depends on the number of agents and the weights’ distribution under asynchronous update. For mixed coordinating and anti-coordinating games, we find that network game dynamics can be decoupled into convergence and nonconvergence regions under certain conditions, in which the global convergence can be established by adding leaf vertices. For more general cases, we devise the incentive mechanisms for agents to achieve the convergence. We also extend the incentive performance of fully asynchronous updating to the partially synchronous updating. Our results provide hints on the typology and incentive mechanisms to induce the convergence of mixed gaming networks.

Affiliations: School of Mathematics and Statistics, Guangxi Normal University, Guilin, China; Interdisciplinary Research Institute for Intelligent Science, Ningbo University of Technology, Ningbo, Zhejiang, China; Department of Automation and the State Key Laboratory of Green Chemical Synthesis and Conversion, Zhejiang University of Technology, Hangzhou, China; Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education, East China University of Science and Technology, Shanghai, China

Abstract:
This article addresses the output feedback control problem for a specific class of discrete-time fuzzy singularly perturbed systems subjected to nonuniform sampling and a round-robin protocol. An innovative method for modeling nonuniform sampling periods through nonhomogeneous sojourn probabilities is proposed, offering a more intuitive and adaptable framework for system design and analysis. The round-robin protocol is applied to nonuniformly sampled outputs, optimizing information transmission efficiency and enhancing overall system performance. To tackle potential limitations in state data acquisition, a token-dependent static output feedback controller is developed that addresses the complexities introduced by nonperiodic sampling and asynchronous premise variables. Sufficient conditions are derived to ensure stochastic stability of the closed-loop system. Finally, two simulation examples are presented to validate and demonstrate effectiveness of the theoretical approach.

Affiliations: Engineering Research Center of Internet of Things Applications Ministry of Education, Jiangnan University, Wuxi, Jiangsu, China; Department of Earth and Space Science and Engineering, York University, Toronto, ON, Canada; School of Electrical Engineering, Engineering Research Center of Electrical Transport Technology, Ministry of Education, Southeast University, Nanjing, China; School of Computing, Engineering and the Built Environment, Edinburgh Napier University, Edinburgh, U.K.

Abstract:
This article deals with fully distributed data-driven bipartite formation control for nonlinear discrete-time multi-input–multi-output multiagent systems (MASs) with unknown dynamics models and quantized information. Initially, a distributed combined measurement error function (DCMEF) is developed for MASs characterized by cooperative and competitive interactions. This function is designed to transform bipartite formation challenges into traditional consensus problems. Subsequently, a distributed compact form dynamic linearization model is established based on the designed DCMEF and input–output data of the MASs, eliminating the need for a strongly connected communication topology. Following this, a logarithmic quantization scheme and a dynamic event-triggered communication mechanism are devised to reduce the communication burden and enhance convergence speed. Finally, a data-driven fully distributed dynamic event-triggered bipartite formation control method is proposed, and its convergence is rigorously proven. Simulation studies and hardware experiments are conducted to validate the effectiveness of the proposed method.

Abstract:
Centralized training and decentralized execution (CTDE) frameworks in cooperative multiagent reinforcement learning (MARL) address nonstationarity and scalability in dynamic environments. However, coordination among agents remains challenging due to limited observability, often leading to inefficient exploration of policy spaces and increased communication overhead. Existing communication mechanisms partially alleviate these issues but typically add complexity without adapting to changing conditions. We propose the signaling-driven incentive communication (SDIC) framework, a novel approach that integrates Markov signaling games (MSGs) into CTDE to enable more efficient and targeted interagent communication. By integrating value-based methods with sparse communication, SDIC reduces unnecessary exchanges while generating tailored signals that enhance policy alignment and improve coordination. Furthermore, SDIC incorporates partner modeling, allowing agents to anticipate the behavior of others and thus strike an effective balance between communication efficiency and computational complexity. Our experimental results, including extensive evaluations in StarCraft II and SUMO traffic simulations, demonstrate SDIC’s superior coordination, task success, and communication efficiency with manageable computational complexity. Ablation studies validate the critical roles of SDIC’s components in reducing overhead and ensuring effective policy alignment.

Abstract:
In this article, we investigate fault-tolerant and resilient control approaches for cyber-physical systems within a unified control and detection framework. Particularly, a novel strategy is presented to simultaneously detect and accommodate anomalies in cyber-physical systems subject to multiplicative physical faults and additive integrity cyberattacks. An observer-based cyber-secure system configuration is first analyzed by means of the coprime factorization technique, wherein multiplicative faults are characterized by coprime factor uncertainties. It is revealed that fault- and cyberattack-induced variations possess distinct attributes with respect to the closed-loop dynamics. This observation motivates a collaborative detection scheme to distinguish both types of anomalies. Specifically, a performance-based fault detector is implemented on the plant side, delivering fault detection results to the monitoring and control (MC) side, where an observer-based attack detector operates collaboratively. Subsequently, the local and remote controllers are reconfigured to enhance the fault tolerance and attack resilience against faults and cyberattacks. To provide more independent design freedoms, the residual signal derived from the controller dynamics is incorporated into the Youla parameterization-based stabilizing controller. Finally, the proposed scheme is verified on a leader–follower robot system.

Abstract:
This article introduces a study on the secure control of nonlinear multiagent systems (NMASs) that are vulnerable to denial-of-service (DoS) attacks, with the added complexity that system states are not directly observable. To tackle the inherent nonlinear dynamics, a fuzzy logic systems (FLSs) framework is employed as a modeling tool. Faced with the obstacle of inaccessible system states and outputs during DoS attacks, this article introduces a switching-type secure estimator. This advanced estimator is designed to accurately reconstruct the system state from sporadic output data, ensuring continuous monitoring despite interruptions. By seamlessly integrating the switching-type secure estimator with the average dwell time (ADT) method and leveraging Lyapunov stability theory, the authors have developed an output-feedback secure control strategy. This strategy not only maintains system stability but also guarantees the convergence of consensus tracking errors, even in the presence of unknown states and ongoing DoS attacks. Finally, in order to prove the effectiveness of the consensus security controller, the practicability and reliability of the proposed control scheme are verified by simulation experiments.

Abstract:
This article investigates the secure consensus control problem for multi-unmanned aerial vehicles (uncrewed aerial vehicles (UAVs)) attitude system under channel fading. By decomposing the attitude system, an attitude privacy protection scheme is proposed, enhancing communication security through the transmission of only partial attitude angles. Under UAV channel fading, a distributed observer incorporating a detection factor and compensation mechanism is proposed to ensure both transmission accuracy and observation precision. Furthermore, to enhance tracking performance, a secure prescribed performance control (PPC) strategy based on preset trajectory is proposed. This strategy achieves the PPC without relying on complete information of UAVs. Ultimately, a simulation example involving UAVs demonstrates the feasibility and effectiveness of the proposed control scheme.

Abstract:
This article proposes an adaptive fixed-time control strategy for uncertain high-order nonlinear cyber–physical system subject to deception attacks on both the sensor-to-controller (S-C) and controller-to-actuator (C-A) communication channels. First, to mitigate the impact of dual-channel attacks, mathematical tools are employed to decouple the high-order term induced by C-A channel attacks, and a robust controller is designed based on the compromised state information. Second, novel Lyapunov functions and an adaptive mechanism are constructed to transform nonlinear uncertainties into a linearly parameterized form with unknown parameters. This transformation effectively compensates for unknown control coefficients and mitigates the severe nonlinear growth caused by high-order dynamics under attacks. Third, a control strategy independent of the system’s powers is developed, which relaxes the requirement for prior knowledge of system powers and avoids singularities. Finally, the effectiveness and feasibility of the proposed strategy are confirmed via simulation results.

Abstract:
Recurrent neural network (RNN) is a neurodynamic method designed to tackle time-varying problems in various technical domains, which are widely derived from scientific research and practical applications. It should be noted that traditional models often lack an effective capability to suppress nonlinear time-varying noise during the design process, and thus may encounter many difficulties in practical applications. This article presents a novel RNN model for solving the continuous time-varying matrix pseudoinverse, which has a significant characteristic of double integral-reinforcing (DIR) term and is termed DIR continuous-time RNN (DIR-CT-RNN) model. Correspondingly, using the discretization formula, a DIR discrete-time RNN (DIR-DT-RNN) is presented for solving the discrete time-varying matrix pseudoinverse. The theoretical results present that the DIR-DT-RNN model converges toward the theoretical solution under the discrete time-unvarying constant (DTU-C) noise or discrete time-varying linear (DTV-L) noise interference. Under the discrete time-varying quadratic (DTV-Q) noise interference, the proposed model converges to a constant that relates to the design parameters. In addition, simulation results, including an application for trajectory tracking of three-link robotic manipulator, which come from practical engineering background, verify the effectiveness and superiority of DIR-DT-RNN model for solving the time-varying matrix pseudoinverse under various types of noise interference.

Affiliations: Intelligent Robotics Institute, School of Mechatronical Engineering, and the Key Laboratory of Biomimetic Robots and Systems, Ministry of Education, Beijing Institute of Technology, Beijing, China; Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, SAR, China; School of Electrical and Electronic Engineering and the LKC School of Medicine, Nanyang Technological University, Jurong West, Singapore; Department of Micro-Nano Systems Engineering, Nagoya University, Nagoya, Aichi, Japan

Abstract:
Precise motion control of magnetic microrobots in complex and dynamic environments remains a critical challenge for enabling key applications such as targeted therapy and micromanipulation. Purely manual teleoperation is prone to operator fatigue and error, while fully autonomous systems often lack the robustness and adaptability to handle. Here, we propose a human–machine shared cascade control method for magnetically driven microrobots, which effectively integrates human cognitive intelligence with machine autonomy for collision-free navigation in dynamic environments. The outer-loop hybrid shared control unit smoothly modulates control authority in response to real-time collision risk, dynamically integrating the operator instructions and the autonomous navigation system output guided by the enhanced artificial potential field method to formulate the guidance law. For the inner-loop motion tracking, a data-driven adaptive orientation controller is designed, which integrates a nonlinear feedforward compensator leveraging a Gaussian process regression (GPR) model with a linear feedback controller whose parameters are optimized using the virtual reference feedback tuning (VRFT) method, ensuring fast and precise tracking of the desired motion. The effectiveness of the proposed method was validated through both simulation and physical experiments. In human-subject studies conducted on a physical magnetic actuation platform featuring both static and dynamic obstacle scenarios, quantitative results demonstrate that the shared control strategy significantly outperforms both purely manual and fully autonomous modes across all key metrics, including success rate, task completion time, stability, and safety ( p \lt 0.001 ). Furthermore, successful navigation within a complex gastric model demonstrates the potential of the shared control system for practical application in unstructured environments.

Affiliations: School of Artificial Intelligence, Optics and Electronics, Northwestern Polytechnical University, Xi’an, China; School of Mechanical Engineering, Northwestern Polytechnical University, Xi’an, China; School of Automation, the Key Laboratory of Measurement and Control of CSE, Ministry of Education, and the Institute of Intelligent Unmanned Systems, Southeast University, Nanjing, China; School of Computer Science and Engineering, South China University of Technology, Guangzhou, China

Abstract:
Effective policy optimization in multiagent reinforcement learning (MARL) necessitates extensive exploration of high-dimensional state-action spaces. However, such exploration may not only trigger unsafe states but also compromise system stability, posing significant challenges for deployment in safety-critical systems. To address this challenge, this article proposes a safety-stability layer that integrates robust control barrier functions (RCBFs) and input-to-state stable control Lyapunov functions (ISS-CLFs) for multiagent systems operating in unknown environments with uncertain dynamics. Furthermore, by integrating safety-stability constraints with a MARL framework, during the training phase, we exclusively focus on goal-reaching objectives to expand the policy network’s exploration space, while in the deployment phase, policy outputs are filtered through a real-time safety-stability layer. In addition, an event-triggered mechanism for action compensation calculation is designed based on safety condition assessments to conserve computational resources. Finally, the effectiveness of the proposed method is validated through simulation experiments in dynamic multiunicycle environments. The results demonstrate that our approach not only ensures strict adherence to safety constraints but also significantly enhances the task execution efficiency of multiagent systems.

Abstract:
In this article, the attitude maneuver control with the arbitrary convergence time is investigated for rigid spacecraft. First, a time-varying sliding mode function expressed by a piecewise function is designed by using an exponential function. This designed sliding mode function contains two equilibria of the attitude control systems. Furthermore, an attitude control law is designed with the aid of this new sliding mode function such that the states of the closed-loop attitude system remain on the sliding mode surface from the initial time instant, and converge to the origin at an arbitrarily preset time. In addition, the unwinding phenomenon can also be avoided when the proposed control law is used.

Abstract:
This article investigates the problem of visual tracking of an unknown moving target by a network of robotic manipulators equipped with uncalibrated eye-in-hand cameras. The objective is to ensure that, for each robot, the target’s projection is maintained at a specified position on the image plane, despite the uncalibrated camera parameters and uncertain, time-varying feature depths. The target’s motion is assumed to be generated by a neutrally stable linear system, whose state and system matrix are not directly accessible to all robots. To address this problem, a distributed control scheme is developed in three steps. First, an adaptive distributed observer is introduced to estimate the motion of the moving target. Second, a novel image-space observer is designed for each robot to estimate the image-space position and to simultaneously provide the estimated image-space velocity, based on which the proposed distributed controller avoids using image-space velocity measurements. Third, by leveraging the linearly parameterized properties of the depth-independent image Jacobian matrix and the depth, adaptive laws are proposed to cope with uncertain parameters in cameras and robots. By using the Lyapunov stability theory, a rigorous analysis is provided to show the stability of the closed-loop system and asymptotic convergence of the image-space tracking errors. The effectiveness of the proposed scheme is illustrated through simulation with a group of three-DOF robotic manipulators.

Abstract:
This article aims to investigate relaxed local stabilization for discrete-time Takagi–Sugeno fuzzy systems with structural relaxation under guaranteed resilience. To mitigate the conservatism and computational burden associated with conventional multiple summation-type approaches for exploiting high-degree membership information, a novel Lyapunov function and nonparallel distributed compensation (non-PDC) control law are developed within an augmented membership-quadratic framework, which relaxes the symmetry constraints on the intertemporal cross terms. To overcome the limitations of existing resilient stabilization methods that rely heavily on a user-defined hyperparameter, a matrix-type threshold condition is introduced, enhancing both practicality and numerical efficiency. Based on orthogonal complements, new structural relaxation lemmas within the membership-quadratic framework are proposed for guaranteeing resilient stabilization. Finally, the effectiveness and reduced conservatism of the proposed method are validated through benchmark examples, demonstrating its computational efficiency and improved performance compared to existing approaches.

Abstract:
Solving constrained multiobjective optimization problems (CMOPs) by constrained multiobjective evolutionary algorithms (CMOEAs) has been a timely research topic in recent years. While various improvement strategies have been proposed in existing studies, the dominance-based and decomposition-based frameworks are usually used independently, despite their complementary characteristics on different problem types—dominance excels in feasibility handling while decomposition offers directional guidance—which could jointly enhance search performance when properly integrated. With this in mind, this article proposes a coevolutionary algorithm using both dominance-based and decomposition-based frameworks to coevolve two populations, thereby leveraging their respective advantages. Specifically, the dominance-based population optimizes a dynamic problem derived from the original problem and achieves diversity preservation through a tolerance-based selection strategy, while the decomposition-based population focuses on the unconstrained Pareto front in the early stage and the constrained Pareto front in the later stage through stage identification, objective switching, and relevance-based selection strategy, thereby directly addressing the limitation of isolated framework usage. In addition, populations with different frameworks are capable of sharing information between parents and offspring during offspring generation and environmental selection, respectively, enabling mutual reinforcement that existing single-framework or loosely coupled approaches lack. Experimental results with 11 state-of-the-art CMOEAs on four benchmark suites and five real-world CMOPs demonstrate the performance advantages of the proposed algorithm.

Abstract:
This article introduces a distributed deep neural network (NN)-based adaptive control framework for cooperative object manipulation in human–robot teams with unknown agent dynamics by using three distinct multilayer NN observers (MNNOs). The first observer, termed the reference point estimator, enables each robotic agent to estimate the object’s reference center using consensus-based learning, even without direct access to global reference trajectories. The second observer, referred to as the human force-to-trajectory estimator, uses human-applied forces to infer the intended position, velocity, and acceleration of the object, enabling real-time estimation of human intent. Together, these two observers allow distributed estimation of human-intended motion. In addition, a third observer, the distributed NN dynamics observer, is integrated into the control layer to simultaneously estimate the agent’s own state and unknown system dynamics while incorporating the state vector of all other agents. Weight update laws for the multilayer NN observers are developed using singular value decomposition (SVD), enabling stable and efficient parameter tuning in multiagent settings. The framework combines the observer estimates with a distributed online multilayer actor–critic NN controller to compute Pareto game theoretic optimal effort that coordinates robot actions while considering neighborhood interactions. Safety is enforced via barrier Lyapunov functions (BLFs) formulated using Karush–Kuhn–Tucker (KKT) conditions, which dynamically adjust safety constraints based on both the agent’s own state and its neighbor state vector. Simulation results demonstrate that the proposed approach achieves accurate intent estimation, robust control, and a 60% reduction in total cost compared to baseline methods.

Abstract:
This article addresses the time-varying distributed optimization problem (DOP) for networked multiagent systems (NMASs) operating over directed graphs, considering the impact of edge-based additive measurement noise (EBAMN). First, a finite-time stochastic stability framework is established to demonstrate the global stochastic practical finite-time attraction of the origin, enabling robust control design for stochastic nonlinear systems. The proposed method achieves faster convergence rates and provides bounded finite convergence time estimates, outperforming asymptotic methods. Second, a novel distributed optimization algorithm (DOA) is introduced, incorporating consensus-gain function, state-dependent optimization gains, and integral information of the gradient of local objective functions. Using the It \mathrm \hat o lemma and Lyapunov theory, the continuous-time DOA guarantees the p th moment convergence for all agents, ensures practical finite-time consensus in probability, and drives that states of NMASs converge to the time-varying optimal solution, even in the presence of EBAMN interferences. Furthermore, a new adaptive dynamic event-triggered mechanism (ETM) integrated with the DOA is proposed. This mechanism significantly enhances communication efficiency and reduces resource consumption throughout the process of tracking the optimal solution while preventing Zeno behavior. Finally, numerical simulations in multiuncrewed aerial vehicle (UAV) target tracking validate the effectiveness of the robust continuous-time DOA against random EBAMN.

Abstract:
Binary neural networks (BNNs) have been applied in limited resources and mobile devices because of their extreme model compression ability. However, manually designing suitable architectures is challenging given the specialized structure of binarized operations. Neural architecture search (NAS) provides a promising approach for designing high-performance BNN architectures. In practice, various situations require networks with different parameter sizes and performance levels. Therefore, this article proposes a multiobjective evolutionary NAS algorithm for BNNs based on a two-stage training strategy (MO-TS-BNAS) to solve these problems. First, the ApproxSign function is used to approximate the gradient error in the training of BNNs. To avoid the small model trap problem, two auxiliary objectives are introduced in nondominated sorting to retain larger models with similar errors. Then, a two-stage training strategy with flexible use of auxiliary objectives is proposed, forming the selection mechanism in environmental selection. The path dropout method is used in the second stage to prevent hypernetwork overfitting. In addition, the mini-batch gradient descent strategy is improved to speed up individual architecture evaluation and reduce time cost in the search process. Finally, the full precision baseline search space is binarized for general experimental comparison. Our MO-TS-BNAS algorithm balances the two different objective functions of the model size and error. A large number of experiments are carried out on the CIFAR10 and ImageNet datasets, and the results show the effectiveness of the proposed method.

Abstract:
In this study, we develop an event-triggered predefined-time sensorless prescribed and personalized compliant performance control scheme for teleoperation systems. In the absence of force/torque sensors, a predefined-time torque behavior estimator (PTTBE) is designed, and its estimated values are applied to both the admittance structure and the control law. Then, a variable stiffness parameter related to the operator’s surface electromyography (sEMG) signal is incorporated into the admittance structure. By integrating the PTTBE, predefined-time sliding manifold, predefined-time performance function, and event-triggered mechanism involving time-scaling, error-scaling, and muscle activation-scaling functions, the PTTBE-based event-triggered predefined-time control (PTTBE-ETPTC) scheme is proposed. This scheme ensures that not only does the tracking error converge to a residual set within a predefined time regardless of the system’s initial state, but also that the error constraints are not violated at any time. Compared with existing tracking control methods, the introduction of a variable stiffness parameter admittance structure, along with an event-triggered mechanism related to predefined-time parameters and a variable capable of reflecting the operator’s intention, greatly enhances the system’s flexibility, enabling a favorable balance between tracking performance for free motion and compliant performance for interaction/contact situations while reducing the control frequency. Simulations and experiments are carried out to demonstrate the effectiveness and practicality of the developed PTTBE-ETPTC scheme.

Abstract:
This article studies the decentralized impulsive control problem for nonlinear interconnected systems (NISs) based on the dynamic event-triggered mechanism. By the fuzzy logic system (FLS)-based backstepping approach, we first propose a dynamic event-triggered impulsive controller. Unlike traditional event-triggered control (ETC), our impulsive control scheme allows for the instantaneous regulation of system states only at some state-dependent impulse instants, thus avoiding control inputs between two triggering moments. Notably, the resulting closed-loop impulsive systems include hybrid dynamics, general nonlinear characteristics, and prescribed performance constraints simultaneously. Based on the Lyapunov analysis method, we prove that even under discrete impulsive controllers, all closed-loop states remain bounded, and the prescribed tracking performance is achieved, namely, the tracking error can converge to a prescribed bounded region within a desired finite time. Then, the proposed impulsive control approach is further extended to the output-feedback case, under which the impulsive control design is based on the observer states. Finally, we show two simulation examples to validate the effectiveness of impulsive control schemes.

Abstract:
This article investigates the smooth control problem of switched fuzzy systems, where the modes asynchronously switch under a partly stochastic sojourn time (PSST) switching signal, i.e., a duration of the sojourn time is governed by a random distribution. The formulated PSST switching signal is composed of a mode-dependent activated time and a duration subject to certain stochastic processes, which covers the conventional (average) dwell time (DT) switching signals or stochastic switching signals as special cases. Considering the measuring and computing delay in mode and membership degree identifying of the fuzzy switched systems, the asynchronous phenomena caused by unmatched case between control and system modes are included in the PSST switching signal, and a detected-mode-based Lyapunov candidate is formulated for the mean-square stability (MSS) and robustness analysis, which has not been considered before. To overcome the undesired control bump between adjacent modes, a multistage membership degree interpolation approach is proposed to obtain a smooth control transition after the asynchronous duration to carry out an anti-asynchronously stochastically smoothly switched fuzzy controller (A2S3-FC), unlike the existing literature that only considers part of the property of the practical systems. The effectiveness and the advantages of the proposed A2S3-FC are verified via a numerical example and a simulation of aerial manipulator attitude control.

Abstract:
This article investigates the mode cluster-based event-triggered control (MCETC) of stochastic Markovian jump systems (SMJSs) under denial-of-service (DoS) attack. First, a novel MCETC framework is designed by considering the interplay among subsystems, DoS attacks, and the event-triggered mechanism (ETM). In this framework, the controller mode is reconstructed, and the number of controller modes is reduced by reclustering the system modes. It significantly reduces the conservatism of the system compared to existing mode-dependent/-independent controllers. Second, a switching ETM is designed for scenarios with and without DoS attack activation, which can effectively save network bandwidth resources and reduce computational load. Third, a multi-Lyapunov function based on DoS attacks is proposed to ensure the stability of the closed-loop SMJSs. Then, the controller gains and event-triggered parameters are jointly solved via the linear matrix inequality (LMI) technique. Moreover, the maximum allowable sampling interval (MASI) is given such that the controller can restore the control signals as soon as a DoS attack ends, which enables faster stabilization of the closed-loop system. Finally, a numerical example is used to verify the effectiveness and superiority of the proposed method.

Affiliations: Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Electrical Engineering and Automation, Anhui University, Hefei, China; School of Electronic Science and Technology, Hainan University, Haikou, Hainan, China; Institute of Artificial Intelligence, School of Future Technology, Shanghai University, Shanghai, China; State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, the School of Electrical Engineering and Automation and Anhui Engineering Laboratory of Human Robot Integration System and Intelligent Equipment, Anhui University, Hefei, China; School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore

Abstract:
This article presents a sliding mode control (SMC) strategy to address the finite-time consensus problem of multiagent systems (MASs) under denial-of-service (DoS) attacks. Agents exchange information over network channels that are vulnerable to stochastic DoS attacks, which may disrupt communication and change the network topology. To capture these stochastic variations, a Markov jump model is employed to describe the switching of communication topologies. By introducing a disagreement vector, the consensus problem of the MAS within a finite-time interval is transformed into the stochastic finite-time boundedness (SFTB) problem of the disagreement error dynamic system. A feasible SMC law is developed to drive the disagreement error dynamic system onto a specified sliding surface within a finite time. Furthermore, a partitioning policy is used to ensure the SFTB of the system during both the reaching phase and the sliding phase. A reduced-order approach is used to resolve potential uncontrollability in the system, and sufficient conditions are established to ensure the SFTB of the disagreement error dynamic system under the proposed SMC strategy. Finally, a multiaircraft system example is provided to demonstrate the correctness and effectiveness of the proposed approach.

Abstract:
In this article, the distributed filtering issue is explored for time-varying state-saturated systems affected by Byzantine attacks over sensor networks. To regulate data transmission, a token bucket protocol (TBP) is utilized, in which the stochastic nature of token consumption arises from variations in packet sizes. Particularly, the measurements are transmitted to the filter only when the available tokens suffice to meet the required consumption. A Byzantine attack model is formulated in which Byzantine nodes arbitrarily alter the measurement signals transmitted to neighboring nodes. The primary objective is to construct an upper bound of the filtering error covariance (FEC) and to compute suitable filter gains by minimizing this bound. Furthermore, the boundedness of the proposed filtering error dynamics is rigorously analyzed via matrix-based theoretical analysis. Finally, numerical simulations are conducted to verify the effectiveness of the proposed algorithm.

Affiliations: National Pilot School of Software, Yunnan Key Laboratory of Software Engineering, Yunnan University, Kunming, China; National Pilot School of Software, Yunnan University, Kunming, China; Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China; Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, School of AI, Anhui University, Hefei, China; College of Computer Science and Electronic Engineering, Hunan University, Changsha, China; Tandon School of Engineering, New York University, Brooklyn, NY, USA; School of Software Engineering, Sun Yat-Sen University, Zhuhai, China; Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA

Abstract:
Deep learning-based models have been widely used to predict electronic health record (EHR) events by exploiting diagnostic characteristics. Despite significant progress, three limitations remain: 1) effectively modeling dynamic relationships among diseases, 2) fully leveraging diagnosis code ontologies from multiple perspectives, and 3) incorporating unstructured discharge summaries. To address these challenges, we propose a coarse-to-fine disease learning framework with patient notes for EHR event prediction, tailored to capture both dynamic and static disease characteristics. First, we construct a fine-grained dynamic disease graph by removing disease weakly correlated disease pairs based on co-occurrence distributions. Second, disease embeddings are refined by integrating coarse and fine-grained information within the hierarchical structure of ICD-9-CM codes. In addition, discharge summaries are combined with auxiliary patient notes for collaborative disease learning. Finally, gated recurrent units, location-based attention, and soft attention mechanisms are utilized to further enhance embedding representations. Experiments on two real-world EHR datasets, MIMIC-III and MIMIC-IV, demonstrate that our model consistently outperforms nine baseline methods in EHR prediction. The source code can be found at https://github.com/YNU-L/CCDLD

Abstract:
Effective deep feature extraction via feature-level fusion is crucial for multimodal object detection. However, previous studies often involve complex training processes that integrate modality-specific features by stacking multiple feature-level fusion units, leading to significant computational overhead. To address this issue, we propose a lightweight attention-guided self-modulation feature fusion network (LASFNet). The LASFNet adopts a single feature-level fusion unit to enable high-performance detection, thereby simplifying the training process. The attention-guided self-modulation feature fusion (ASFF) module in the model adaptively adjusts the responses of fused features at both global and local levels, promoting comprehensive and enriched feature generation. Additionally, a lightweight feature attention transformation module (FATM) is designed at the neck of LASFNet to enhance the focus on fused features and minimize information loss. Extensive experiments on three representative datasets demonstrate that our approach achieves a favorable efficiency–accuracy tradeoff. Compared to state-of-the-art methods, LASFNet reduced the number of parameters and computational cost by as much as 90% and 85%, respectively, while improving detection accuracy mean average precision (mAP) by 1%–3%. The code will be open-sourced at https://github.com/leileilei2000/LASFNet

Abstract:
In this article, an adaptive distributed predefined-time and bounded (PTB) sliding mode controller based on a novel super-twisting-like estimator is proposed for the formation control problem of underactuated uncrewed surface vehicles (USVs) subject to unknown disturbances. To leverage the advantages of the super-twisting estimator and achieve ultimate PTB stability in the formation control system, a novel distributed predefined-time super-twisting-like estimator is first proposed. This estimator achieves real-time estimation of the leader’s position and velocity within a predefined-time by collecting the neighboring USVs’ estimates of the leader’s position and velocity through switching interaction topologies, and it does not require the leader’s acceleration information. Next, an improved nonsingular PTB sliding surface is designed. By integrating this sliding surface with adaptive control techniques, a distributed PTB sliding mode formation controller is designed for underactuated USVs subject to unknown disturbances. Finally, the PTB stability of the formation control system is rigorously proven. Numerical simulations of both fixed and time-varying formations validate the effectiveness and robustness of the proposed method.

Abstract:
Grasping transparent objects remains challenging for robotic systems due to their reflective and refractive properties, which distort depth perception and introduce background noise. Unlike humans, who leverage life experience to perceive depth intuitively, robotic algorithms often fail to generalize across different object types. To address this, we propose a novel framework inspired by human perception for grasping transparent objects. Our approach extends features extracted by foundation models to implicitly learn reconstruction strategies for transparent objects without requiring segmentation priors. Crucially, our framework maintains strong performance across all types of objects and scenes, preventing catastrophic forgetting of opaque objects while learning to perceive transparent ones. By integrating affordance information, our method dynamically guides a five-finger dexterous hand to execute diverse grasping strategies based on human intent. To tackle the challenge of annotating transparent objects, we constructed a large-scale synthetic dataset with depth information, affordance data, and automated annotations. Our framework demonstrates strong generalization, achieving a 96% grasp success rate in real-world robotic experiments and proving its broad applicability across varied environments.

Abstract:
This study proposes an accelerated iterative learning control scheme using a fractional high-order update rule (FHUR) to improve the convergence rate for linear time-invariant systems. High- and low-order power update terms are used to handle large- and small-tracking errors, respectively, thereby accelerating convergence. Two learning mechanisms are proposed and shown to be optimal among various learning gain selections. The inherent nonlinearity in the FHUR poses significant challenges for the convergence analysis. To address this, a disturbed composite nonlinear mapping method is introduced. Using this method, the tracking errors are proven to converge either to an invariant set or to a set of limit cycles, depending on the underlying learning mechanism. Any desired tracking precision can be achieved by adjusting the parameters in the FHUR. Numerical simulations confirm that the FHUR presents a promising alternative to the commonly used proportional-type update rule for achieving accelerated convergence.

Abstract:
This article investigates optimization-driven learning techniques to address the critical challenge of balancing communication efficiency with convergence acceleration in distributed multiagent systems. While existing accelerated methods typically necessitate multiple internode communications per iteration, we propose two novel methods, heavy-ball exact fusion (HBEF) and Nesterov-accelerated exact fusion (NAEF), that maintain a single-communication operation while achieving enhanced convergence. By fusing momentum mechanisms with bias correction, the developed methods not only precisely preserve convergence guarantees but also demonstrate accelerated convergence compared to baseline exact diffusion and contemporary accelerated counterparts. A distinctive dual acceleration method is further proposed through momentum parameter coordination. Rigorous convergence analysis reveals the momentum parameter’s critical role in acceleration behavior. Extensive numerical evaluations across representative machine learning tasks validate the proposed methods’ superiority in both transient convergence speed and steady-state accuracy. Notably, they achieve state-of-the-art performance at half or one-third the communication cost, effectively bridging the long-standing gap between communication efficiency and rapid convergence in distributed learning.

Abstract:
In this study, we analyze the minimum control node set problem for Boolean networks (BNs) with degree constraints. Our major contribution is the derivation of nontrivial lower and upper bounds on the size of the minimum control node set through combinatorial analysis of four types of BNs (i.e., k - k -XOR-BNs, simple k - k -AND-BNs, k - k -AND-BNs with negation, and k - k -NC-BNs, where the indegree and outdegree of each node are both k , and the k - k -AND-BN with negation is an extension of the simple k - k -AND-BN that considers the occurrence of negation and NC means nested canalyzing). More specifically, four bounds for the size of the minimum control node set: general lower bound, best case upper bound, worst-case lower bound, and general upper bound are analyzed. By dividing nodes into three disjoint sets, extending the time to reach the target state, and utilizing necessary conditions for controllability, these bounds are obtained. Further, meaningful results and phenomena are discovered. Notably, all of the above results involving the AND function also apply to the OR function.

Abstract:
This article studies the distributed predefined-time formation control problem for a specific heterogeneous multiagent system. This system includes completely different unmanned autonomous helicopters (UAHs), unmanned ground vehicles (UGVs), and autonomous underwater vehicles (AUVs) in the presence of actuator faults. First, a distributed prescribed-time observer is developed for followers to estimate the leader states, which can decrease the network flow. Then, an adaptive predefined-time fault-tolerant optimal formation controller is constructed to continuously optimize performance index and approach optimal formation tracking. Moreover, in the designed control framework, adaptive updating laws are constructed for the unknown parameters of actuator loss of efficiency and the lumped uncertainty, respectively. Compared with the relevant finite/fixed-time cooperative tracking works, here the settling time is independent of any existing control gains and the initial conditions of the studied heterogeneous multiagent systems (MASs), thus it can be uniformly prescribed. Finally, the control performance of the designed method is further illustrated by a simulation experiment.

Abstract:
The study of the nicotine addiction mechanism is of great significance in both nicotine withdrawal and brain science. The detection of addiction-related brain circuitry using functional magnetic resonance imaging (fMRI) is a critical step in studying this mechanism. However, it is challenging to accurately estimate addiction-related brain circuitry due to the low signal-to-noise ratio of fMRI and the issue of small sample size. In this work, a graph diffusion-infused adversarial learning (GDAL) network is proposed to capture addiction-related brain circuitry accurately. The GDAL combines the graph convolution method with the diffusion model so that the model can fully capture addiction-related brain circuitry in non-Euclidean space. The diffusion reconstruction module (DRM) is designed to reconstruct the brain network to maintain the consistency of sample distribution in the latent space so that the brain circuitry can be detected more accurately. The proposed model reduces the search space by improving the conditional guidance of the DRM so that the model can better understand the latent distribution for the issue of small sample size. The experimental results demonstrate the effectiveness of the proposed method.

Abstract:
This article investigates the deception-eliminating design (DED) against false information attacks by deceptive agents in asynchronous optimal consensus control. We model the asynchronous interactions among agents as multistage games and establish a Tit-for-Tat rule to compel deceptive agents to turn to transmitting true state information. Furthermore, we design a false information counterattack rule under asynchronous updates by leveraging the invariance of the rank of equivalent matrices and the convexity of positive semidefinite quadratic forms. This design effectively intimidates deceptive agents that have transitioned to cooperation, ensuring they do not revert to transmitting false information. Subsequently, by utilizing the properties of Riccati differential equations, the integrating factor methods, the Minkowski inequality, and proof by contradiction, we theoretically analyze the impact of false information on consensus and provide an explicit upper bound for the strategy update periods of agents with different performance matrices. Theoretical proof shows that as long as the strategy update periods of all agents remain below this upper bound and the above two DEDs are implemented, the asynchronous consensus is guaranteed.

Abstract:
Actor-critic (AC) algorithms are model-free deep reinforcement learning techniques that have consistently demonstrated effectiveness across various domains. Enhancing exploration (action entropy) and exploitation (expected return) through more efficient sample utilization is pivotal to their success. A key strategy for a learning algorithm is to intelligently navigate the environment’s state space, prioritizing the exploration of rarely visited states over frequently encountered ones. However, conventional approaches rarely quantify a novel state’s utility for policy learning, which can lead to inefficient exploration. To address this, we propose an innovative approach to bolster exploration by employing an intrinsic reward based on a state’s novelty and the potential benefits of exploring that state, which we term plausible novelty. Our method seamlessly integrates with off-policy AC algorithms. By incentivizing the exploration of plausibly novel states, AC algorithms can achieve substantial improvements in sample efficiency and overall training performance. Empirical results demonstrate 19% improvement in training return and 30% reduction in standard deviation, averaged across comparisons of three benchmark algorithm pairs in five different environments.

Affiliations: College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China; School of Automation, the Key Laboratory of Intelligent Detection and Manufacturing Internet of Things, Ministry of Education, and Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing, Guangdong University of Technology, Guangzhou, China; School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore

Abstract:
This article addresses the predefined-time optimal motion control problem of an autonomous surface vehicle (ASV) with disturbances under dynamic self-triggered frameworks via reinforcement learning (RL). Initially, to eliminate the influence of disturbance on the ASV, a predefined-time second-order integral sliding mode control (SOISM) strategy is formulated by establishing a novel integral sliding mode (ISM) function and a terminal sliding mode function. Subsequently, a predefined-time approximate optimal motion (AOM) control strategy is further developed to ensure the ASV maintains a stable state. Furthermore, a single critic network is used to obtain an approximate solution of the Hamilton–Jacobi–Bellman (HJB) equation. The above two strategies are established under the dynamic self-triggered framework, which relies on the current information to predict the next updating time, effectively reducing the computational and communication burden while avoiding the continuous monitoring of the ASV state. In the theoretical analysis, the main challenges lie in the design of Lyapunov functions and triggered conditions to ensure the stability of the sliding mode dynamics and the disturbed ASV. By applying the Lyapunov stability principle and designing two novel Lyapunov functions and triggered conditions that both contain dynamic variables, we demonstrate that the developed control strategies can ensure the stability within the specified time frame. Ultimately, simulation results verify the efficacy of the proposed motion control approach.

Abstract:
This article proposes a unified suboptimal controller design method for unknown general nonlinear systems subject to multiple constraints, including state, input, and output constraints. All inequality constraints are transformed into equality constraints using slack functions and Pade approximation. An unconstrained augmented system is then defined to describe the dynamics of original system and the equality constraints, where the optimal controller of the augmented system can be viewed as a suboptimal controller for the original system. Furthermore, considering the unmodeled dynamics of the original system, neural networks (NNs) are utilized and a data-based solution strategy of integral reinforcement learning (IRL) is presented for the augmented system. Ultimately, the simulation results are given to reflect the effectiveness of the unified design method.

Abstract:
Multispectral remote sensing image (MSI) semantic segmentation faces challenges of limited labeled data and significant scene variability. Although domain adaptation (DA) and domain generalization (DG) methods alleviate these issues to some extent, they still have limitations. DA requires target domain (TD) data, and DG has limited task adaptability. The recently emerged segment anything model (SAM) demonstrates exceptional zero-shot generalization capabilities, yet its visible-light training data and interactive prompt requirements prevent direct application to MSI segmentation tasks. To address these challenges, this article proposes a single-source domain defect-aware adaptation and style-modulated generalization network (SDSnet), which integrates two key innovations: defect-aware prompt learning that automatically focuses on high-difficulty regions through entropy-based defect detection, and style generalization learning that enhances cross-domain adaptability via codebook-based style modulation. Through knowledge distillation, SDSnet enables efficient inference using only the base network, without additional computational overhead. Extensive experiments on three TDs demonstrate SDSnet’s superiority over state-of-the-art DA, DG, and SAM-based methods. Code will be available at https://github.com/zhaoboyu34526/SDSnet

Abstract:
The increasing labor costs in agriculture have accelerated the adoption of multirobot systems for orchard harvesting. However, efficiently coordinating these systems is challenging due to the complex interplay between makespan and energy consumption, particularly under practical constraints like load-dependent speed variations and battery limitations. This article defines the multiobjective agricultural multielectrical-robot task allocation (AMERTA) problem, which systematically incorporates these often-overlooked real-world constraints. To address this problem, we propose a hybrid hierarchical route reconstruction algorithm (HRRA) that integrates several innovative mechanisms, including a hierarchical encoding structure, a dual-phase initialization method, task-sequence optimizers, and specialized route reconstruction operators. Extensive experiments on 45 test instances demonstrate HRRA’s superior performance against seven state-of-the-art algorithms. Statistical analysis, including the Wilcoxon signed-rank and Friedman tests, empirically validates HRRA’s competitiveness and its unique ability to explore previously inaccessible regions of the solution space. In general, this research contributes to the theoretical understanding of multirobot coordination by offering a novel problem formulation and an effective algorithm, thereby also providing practical insights for agricultural automation.

Abstract:
This article investigates the distributed approximate optimal control problem for pursuit–evasion differential games (PEDGs) of multiagent systems (MASs). Initially, interactions between pursuer agents and the evader agents are formulated using a divide-and-conquer algebraic graph approach, where all agents desire to maintain cohesion with their teammates. Subsequently, a state event-triggered mechanism (ETM) is introduced to conserve communication resources. Meanwhile, a polymeric hierarchical sliding mode surface (HSMS) incorporating local neighbor errors is constructed such that the system response rate is improved. To enhance team coordination, a novel dynamic target allocation algorithm is designed to execute the rational allocation among pursuers. Furthermore, based on the adaptive dynamic programming (ADP) with a single-critic neural network (NN) architecture, the HSMS-based event-triggered optimal control policies are further designed via solving the coupling Hamilton–Jacobi–Bellman (HJB) equations. Finally, a simulation conducted in the representative two-pursuer-two-evader scenario is presented to validate the effectiveness of the proposed control scheme.

Abstract:
This article introduces a novel framework for achieving leader-steered (L-S) rigid formations within a multirobot vehicle system subject to nonholonomic constraints, while considering field-of-view (FOV) constraints. In contrast to the conventional separation-bearing leader-follower model, this framework incorporates a virtual leader model, established through topological and local agent connections. To achieve L-S rigid formations and address FOV constraints, a transformative approach is employed. In addition to forming L-S rigid formations, the framework ensures visibility maintenance between topologically connected vehicles using onboard cameras. This is achieved through the introduction of a continuous and continuously differentiable switching function, crucial in balancing visibility maintenance with formation adjustments, particularly when the global leader traverses trajectory segments with large curvature. To implement the framework, the distributed control protocol and the distributed observer are developed. Numerical simulations and real-world experiments demonstrate the framework’s capability to achieve L-S rigid formations while accommodating FOV constraints, showcasing its practical utility and effectiveness in real-world applications.

Abstract:
Continuum robots (CRs) show great potential in complex environments due to their excellent deformability. For practical applications, the position control of the CRs is an important research field. The common drives of the CRs are rigid motors with mature control schemes. However, the driving force of the rigid motors is often impactive, which may cause safety concerns during interaction. Soft drives based on pneumatic soft actuators (PSAs) can provide compliant driving force for the CRs robot bodies to solve this problem, but it is necessary to comprehensively consider the control of the soft drives and the robot bodies. This article takes a CR with soft drives as the research objective, and proposes a double closed-loop adaptive position control method to achieve the endpoint position control of the CR. This CR includes a length-variable robot body with millimeter-scale diameter and pneumatic soft drives. The kinematic model of the robot body is built based on the piecewise constant curvature (PCC) method, and the static models of the soft drives are derived from the three-element model. Based on these models, we propose a double closed-loop adaptive position control method. The inner loop is used to control the displacements of the soft drives, and the outer loop combines the endpoint position control with the nonsingular fast terminal sliding mode function to adaptively control the endpoint position based on the inner loop. By Lyapunov method, we prove the convergence of the endpoint position error. The effectiveness of the proposed control method is verified through experiments.

Abstract:
This article investigates the prescribed-time (PT) optimal formation control issue for second-order multiagent system. A novel formation scheme that integrates reinforcement learning with a fuzzy logic system is presented, incorporating actor, critic, and identifier components to estimate the optimal control, the optimal cost function, and the uncertain system dynamics (including unknown nonlinearities, external disturbances, and leader input), respectively. To achieve PT formation, we introduce a prescribed performance function and a filtered variable, which are then used to develop an error transformation function for the controller design. Unlike existing PT control approaches, this method eliminates initial value limitations, ensuring that both the prescribed performance function’s initial condition and the error transformation parameter are independent of the initial tracking error and system dynamics. We further demonstrate that the developed scheme ensures the prescribed performance of the filtered error, guaranteeing that all formation errors converge to a bounded region within the PT while achieving satisfactory transient performance. Finally, we illustrate the effectiveness of the scheme through two simulated examples.

Abstract:
This article addresses the distributed aggregative optimization (DAO) problem for high-order nonlinear systems with unknown pure-feedback dynamics over directed unbalanced networks, with the key contribution being the extension of DAO methods to high-order nonlinear systems. To achieve this, we first introduce auxiliary aggregative variables that integrate agent output and sampled neighbor information, progressively updated through a smoothing function. Using these variables and drawing inspiration from the dynamic average consensus-based approach, a pivotal theorem is introduced to facilitate the transformation of the DAO problem into a regulation problem, enabling the application of classical control methods to manage complex high-order dynamics. Furthermore, we present a control law based on prescribed performance functions and aggregative variables to solve the approximate aggregative optimization problem for high-order nonlinear agents with bounded disturbances. Finally, numerical examples are provided to validate the effectiveness of the proposed control scheme.

Abstract:
Large-scale optimization problem (LSOP) is an essential research topic in the field of evolutionary computation community. Many large-scale optimization algorithms often maintain a large population for diversity enhancement. However, updating such a large population consumes a significant number of fitness evaluations (FEs), which may lead to the insufficient evolution of the population. In light of this, this article proposes a small-scale learning particle swarm optimization (SSLPSO) for solving LSOPs. In the small-scale learning mechanism, only up to two representative individuals are updated in every generation to effectively save FEs and prolong the evolutionary generations, so as to refine the solution accuracy. Specifically, we first design a representative individual selection (RIS) strategy to select the convergence representative individual and the diversity representative individual for updating. Then, we develop a representative individual learning (RIL) strategy, which includes a convergence learning method and a diversity learning method for the convergence representative individual and the diversity representative individual, respectively. Meanwhile, we further propose an adaptive strategy adjustment (ASA) method based on evolutionary state assessment to determine whether the representative individuals should be updated, further achieving the adaptive adjustment of the evolutionary behavior in the population. Experimental results on the commonly used large-scale test suites, IEEE CEC2010 and IEEE CEC2013, show that the performance of SSLPSO is significantly better than, or at least comparable to other state-of-the-art large-scale optimization algorithms, including the winners of large-scale competitions. Finally, the application of SSLPSO to a large-scale constrained water distribution network optimization problem further demonstrates its real-world applicability.

Abstract:
This article investigates how Denial-of-Service (DoS) attacks impact the time and energy costs (ECs) associated with the emergence of flocking dynamics in the Cucker–Smale system. We propose resilient finite-time and fixed-time control protocols against DoS attacks and establish conditions under which the Cucker–Smale (C–S) system can achieve flocking within a bounded time. The attack patterns are modeled stochastically and are constrained by the effective duration of the attack. Explicit upper bounds for both time and ECs are derived, demonstrating their dependence not only on the group size and control parameters, but also on the duration of DoS attacks. Theoretical analysis and numerical simulations consistently demonstrate that shorter attack durations facilitate faster convergence and lower energy consumption. Additionally, our analysis uncovers a tradeoff between time cost and EC under DoS attacks, suggesting that optimal communication intensity should be carefully adjusted to meet specific performance requirements of practical applications.

Abstract:
physical human–robot collaboration (pHRC) requires strict safety and efficiency guarantees, imposing heightened demands on accurate human intent estimation and adaptive control in a stable manner. To address these challenges, we propose a novel two-loop adaptive passive control framework guided by multistep human intent estimation to reduce human–robot disagreement and improve robot assistance level, facilitating safety-aware efficient pHRC. In the framework, outer loop’s intent estimation guides the inner loop’s adaptive passive controller, ensuring real-time robot behavior adjustment based on multistep intention. Specifically, the outer loop incorporates a transformer-based human intent estimator (THIE) that integrates the Transformer with a conditional variational autoencoder (CVAE) for multistep predictions, accurately estimating motion and force to guide the robot. The inner loop incorporates a goal-oriented reinforcement learning (GoRL)-based adaptive impedance control, which constructs multistep rewards based on prediction and probability from THIE to adjust impedance parameters, thereby balancing disagreement and assistance, and promoting locally optimal robot behaviors. Furthermore, an energy tank-based passive model predictive control (ET-PMPC) is employed to limit robot stored energy, avoiding the impact of variable impedance on safety. Experiments validate that our framework outperforms state-of-the-art (SOTA) methods, significantly improving intent estimation accuracy, robot assistance level, and safety, highlighting its potential to advance pHRC.

Abstract:
This article investigates a multileader Stackelberg game where leaders lack critical information about the follower’s objective function and face random disturbances with unknown distributions. Unlike conventional approaches requiring complete follower information, we consider leaders who manipulate physical plant states while observing the follower’s strategy through private tracking responders. To address distributional uncertainty in the follower’s best response, we reformulate the game as a distributionally robust equilibrium-seeking problem and develop a fully distributed feedback learning algorithm. The proposed data-driven approach operates without prior knowledge of system models or disturbance distributions, enabling leaders to estimate states through neighbor communication and local gradient updates. We characterize equilibrium existence in nonconvex settings. The relationship between communication and gradient errors and the energy function of the dynamic system is established. The upper bound of the regret based on the proposed algorithm is rigorously analyzed. A case study demonstrates the framework’s effectiveness in achieving distributionally robust solutions against uncertain stochastic perturbations.

Abstract:
This article considers the observer-based multiobjective control problem of switched networked control systems (SNCSs) subjected to multipath packet dropouts and switching rule loss. Three mutually independent Bernoulli distribution random sequences are adopted to model the packet dropouts existing in the control input, the measurable output, and the switching rule, which have been rarely studied in existing works. To solve the problems caused by the multipath packet dropouts and switching rule loss, multiple hybrid strategies are adopted to design the observer-based controllers of SNCSs. First, a novel hybrid observer design scheme is used to design the dynamical equation of observers. Second, the mode-dependent and mode-independent hybrid observer-based controllers are designed. Then, based on the multiple Lyapunov functionals (MLFs) and average dwell time (ADT) technology, the multiobjective control problem of SNCSs is formulated as a problem to minimize the H_\infty disturbance attenuation level for the estimation error of observers and L_2-L_\infty disturbance attenuation level for the SNCSs at the same time. Through a two-step approach, new results based on linear matrix inequalities (LMIs) are deduced to determine the observer parameters and controller gains. Eventually, two examples are given.

Abstract:
This article explores predictor-based fractional-order sliding mode load frequency control for interconnected power systems, accounting for input delay. First, a predictor-based method is developed to deal with the input delay. By designing a predictor to accurately predict the future state, the delayed control input can be replaced by the delay-free control input. Then, a novel fractional-order sliding mode controller is designed, where the predictor is used rather than the system state, reducing the dependence on directly measurable system states and enhancing the dynamic response of the system. Furthermore, a disturbance observer is designed to estimate the disturbance, allowing the controller to correspondingly compensate for it, and the robustness of the system is improved. Finally, three cases are conducted to show the validity of the presented method.

Abstract:
This article is concerned with the problem of functional observer-controller (FOC) design when a complex unmeasurable premise variable (UPV) exists in the Takagi–Sugeno (T–S) fuzzy systems. Considering the nonlinearities in the UPV, a new transformation method is designed to linearize the premise variable (PV). Then, the PV could be estimated through the proposed FOC. The observer and controller gains are derived by deducing convex robust and stability conditions. Furthermore, a robust separation principle is utilized to make the estimate and control error system stable. Finally, simulation examples are provided to illustrate the effectiveness of the proposed method.

Abstract:
Massive multiagent systems typically involve a very large number of interactions and conflicts of interest among agents, which presents a significant challenge for achieving stable and efficient adaptive optimal consensus control in real-time. To fill this gap, this article develops a novel federated learning adaptive dynamic programming (FL-ADP) control scheme to solve the massive multiagent mean-field games (MFGs)-based optimal consensus problem. First, the complex interactions of each individual agent with all other agents can be approximated by an average or collective influence in the context of MFGs. Then, a novel undiscounted performance index function involving the mean-field coupling term, the tracking errors and their derivatives is proposed to circumvent the potential impact of the improper discount factor selection and achieve better control performance. By designing the critic–mass neural network structure, the coupled Hamilton–Jacobi–Bellman and Fokker–Planck–Kolmogorov equations are solved to derive the approximate optimal control policy and quantify the probability density function of the collective behavior simultaneously. Additionally, to comply with the required convergence condition of the MFG, a novel event-triggered federated learning mechanism is formulated, which achieves a balance between communication resource consumption and the guarantee of algorithm convergence. On the basis of Lyapunov’s direct method, the tracking errors and the weight estimation errors of all agents are guaranteed to be uniformly ultimately bounded. Simulation results of massive multi-uncrewed aerial vehicle systems affirm the rationality and effectiveness of the proposed method.

Affiliations: School of Information and Artificial Intelligence, the Anhui Province Key Laboratory of Smart Agricultural Technology and Equipment, and the Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing, Anhui Agricultural University, Hefei, China; Department of Automation, University of Science and Technology of China, Hefei, China; School of Mathematics, Hefei University of Technology, Hefei, China

Abstract:
This article first proposes a sliding flexible prescribed performance boundary-guided reinforcement learning (SFPPB-RL) control approach for input-constrained nonlinear systems (ICNSs). By designing a sliding flexible prescribed performance boundary, which not only can adaptively adjust the initial boundary according to the initial error, but also dynamically adjust the constraint relaxation according to the coupling correlation between the input constraint and the performance constraint, a novel prescribed performance control (PPC) approach is proposed. Compared with the existing “horn” shape performance boundary-based PPC methods, the limitation of having to repeatedly debug design parameters or sacrifice initial transient performance to meet different initial error requirements is eliminated. Meanwhile, the coupling effect between the input constraint and the performance constraint is also considered, and the balance between input safety and control performance is achieved by constructing an auxiliary system. Furthermore, combining identifier-critic-actor structure-based RL strategy and backstepping technique, a sliding flexible PPB-guided reinforcement learning (SFPPB-RL) optimal control algorithm is developed, which minimizes the cost function while ensuring input safety and prescribed performance indicators. The validity of the proposed algorithm is demonstrated via simulations.

Abstract:
This article investigates the practically predefined-time stabilization issue of fuzzy memristive neural networks (FMNNs) in the presence of stochastic disturbances and random deception attacks (RDAs). First, in this article, the concept of practically predefined-time stabilization in probability (PPDTSP) of FMNNs is introduced, and a novel Lyapunov-type criterion for PPDTSP is proposed. The novel criterion eases the restrictions on the differential operator of the Lyapunov function and can be reduced to the existing criterion of predefined-time stabilization in probability (PDTSP). Then, a simplified, practically predefined-time control scheme is constructed to ensure PPDTSP of FMNNs under the interference of stochastic disturbances and RDAs. Furthermore, by employing the simplified control scheme and in the absence of RDAs, some PDTSP results are presented as special instances of the PPDTSP conclusions given in this article. Finally, numerical simulations are conducted to validate the accuracy of the theoretical results.

Abstract:
Single-master multislave (SMMS) teleoperation systems can perform multiple tasks remotely in a shorter time, cover large-scale areas, and adapt more easily to single-point failures, thereby effectively encompassing a broader range of applications. As the number of slave manipulators sharing a communication network increases, the limitation of communication bandwidth becomes critical. To alleviate bandwidth usage, the try-once-discard (TOD) scheduling protocol and event-triggered mechanisms are often employed separately. In this article, we combine both strategies to optimize network bandwidth and energy consumption for SMMS teleoperation systems. Specifically, we propose event-triggered control and communication schemes for a class of SMMS teleoperation systems using the TOD scheduling protocol. Considering dynamic uncertainties, the unavailability of relative velocities, and time-varying delays, we develop adaptive controllers with virtual observers based on event-triggered schemes to achieve master–slave synchronization. Stability criteria for the SMMS teleoperation systems under these event-triggered control and communication schemes are established, demonstrating that Zeno behavior is excluded. Finally, experiments are conducted to validate the effectiveness of the proposed algorithms.

Abstract:
This article presents a novel curriculum framework named symmetric-response guided reinforcement learning (RL) for autopilot control of fixed-wing aircraft, driven by an adaptive bidirectional learning curve and a dynamic target scheduling mechanism. Unlike traditional methods with static or overly smoothed learning progressions, the proposed method dynamically adjusts the learning curve’s slope in both directions based on historical reward trends, allowing the learning intensity to increase or decrease as needed. This bidirectional adjustment ensures that the agent is neither overwhelmed by excessively difficult tasks nor stagnated by too-easy ones, leading to better stability and faster convergence. Furthermore, dynamic target generation within an episode from static target constraints enables both reward amplification and implicit enforcement of maneuver rate constraints, improving learning efficiency without manual reward shaping. Experiments on trajectory tracking tasks show that the proposed controller achieves faster convergence, reduced overshoot, and more accurate tracking under turbulence. Further tests on waypoint navigation and dynamic pursuit demonstrate its superiority over the baseline, achieving more precise and timely interception. These results highlight the robustness and applicability of the controller to complex aerial missions such as autonomous air combat.

Abstract:
This study introduces a k -step look-ahead active concurrent learning-based dual control of exploration and exploitation (KSLCL-DCEE) framework designed to address the challenges of auto-optimization in systems with unknown references and environments, inherently balancing parameter estimation and optimal reference tracking. The KSLCL-DCEE algorithm incorporates two loops that employ future gradients of the cost function to generate the subsequent control command by looking ahead k -steps: the inner loop generates k -step look-ahead gradients (i.e., estimated reference trajectory), while the outer loop utilizes the gradient at the k th step to generate the dual control commands which act on a general linear system. Active concurrent learning with a modified learning rate in the initial period is introduced to relax the reliance on the condition of persistent excitation and achieve faster convergence. A comprehensive stability analysis of KSLCL-DCEE is provided. The effectiveness and performance of KSLCL-DCEE are demonstrated through numerical studies and applications on photovoltaic (PV) arrays.

Abstract:
In this article, we investigate the problem of adaptive safe critic control design for stochastic multiagent systems (MASs) subject to asymmetric state and input constraints. To systematically address asymmetric state constraints, a unified transformation function (UTF) is proposed to convert the constrained consensus control problem into the stability analysis of an unconstrained error system. In addition, a nonquadratic cost function is incorporated to address input limitations effectively. Building upon these developments, a time-varying Hamilton–Jacobi–Bellman equation (HJBE) is formulated by integrating the Bellman optimality principle with Itô’s lemma, thereby accommodating stochastic disturbances and enhancing controller robustness. To improve data utilization and eliminate reliance on explicit drift dynamics, an integral reinforcement learning (IRL) algorithm is developed within this framework. Furthermore, a time-varying single-critic network is designed to approximate the solution to the HJBE and generate optimal control policies, thereby considerably reducing computational complexity. To further enhance learning efficiency and relax the persistent excitation (PE) condition, the experience replay (ER) technique is incorporated into the update process of the critic weight. Finally, two simulation examples are provided to verify the feasibility and effectiveness of the proposed approach.

Abstract:
This article focuses on the design of inverse optimal control (IOC) based on inverse reinforcement learning (IRL) for distributed parameter systems (DPSs) with unknown dynamic parameters. First, considering that the optimal policies may not display the expected performance when they are migrated to real-world DPSs due to model bias, the human-behavior learning (HBL) strategy is utilized to transfer the optimal strategy of the reference systems to the real-world DPSs. Furthermore, to avoid performance degradation caused by predefined reward-weight matrices during the optimal control process of the reference systems, the IRL policy iteration algorithm is employed to realize the IOC of the reference systems, and the equivalent reward-weight matrices and optimal control gains of the reference systems are solved. Finally, the effectiveness and superiority of the algorithms are verified in simulation.

Abstract:
This article investigates the problem of robust trajectory design for low-thrust spacecraft subject to state and observation uncertainties. An adaptive latent reinforcement learning (RL) scheme based on sequential latent variable models (SLVMs) is proposed to address this issue. First, an SLVM is employed for the representation learning of uncertain environments and for predicting future observations. Subsequently, by integrating representation learning based on the SLVM with proximal policy optimization (PPO), a stochastic latent PPO (SLPPO) scheme is introduced. Distinct from existing methods, the control policy is derived from learned stochastic latent variables rather than raw uncertain observations, which effectively mitigates the adverse impact of uncertainties on control performance. Furthermore, to enhance training efficiency, an improved dense reward shaping mechanism is designed based on the observation predictions from the SLVM and adaptive techniques. Finally, numerical simulations of two rendezvous missions validate the effectiveness of the proposed approach.

Abstract:
This article investigates the optimal containment control (OCC) problem of a class of nonlinear stochastic multiagent systems (MASs) under secure communication. A novel OCC strategy is designed, ensuring that all followers converge to the convex hull spanned by the leaders while maintaining secure information exchange and minimizing cost by the predefined performance function. To achieve this, an encryption and decryption mechanism is employed in the information exchange among agents, ensuring secure communication and preserving data integrity. Meanwhile, to solve the stochastic version of Hamilton–Jacobi–Bellman (HJB) equation arising in stochastic factor, a simplified adaptive dynamic programming (ADP) framework is introduced under the conditional expectation. Specifically, a single critic network weights tuning rule is developed based on the experience replay technique (ERT). The use of ERT relaxes the traditional persistence of excitation requirement. Theoretical analysis guarantees the uniform ultimate boundedness of the closed-loop system. The simulation results confirm the effectiveness of the designed OCC strategy.

Abstract:
Optimization problems in real-world applications often involve dynamic environmental changes, requiring algorithms to adapt quickly, track optimal solutions, and maintain efficiency. Existing dynamic multiobjective optimization evolutionary algorithms (DMOEAs) typically rely on fixed or limited dynamic response mechanisms, which are often insufficient to handle complex and varied dynamic environments. To overcome these limitations, this article proposes an adaptive dynamic response-based DMOEA (ADR-DMOEA), which employs a subpopulation-level adaptive mechanism to coordinate diversity-driven, prediction-driven, and memory-driven strategies. The strategy weights are dynamically adjusted according to the static optimization distance of each subpopulation, ensuring that appropriate strategies are adaptively deployed in different environments. This design overcomes the inefficiency of fixed assignments and the instability of individual-level perturbations, enabling coordinated and stable evolution. Extensive experiments on DF benchmark functions and a blast furnace (BF) ironmaking case study demonstrate that ADR-DMOEA achieves superior convergence, diversity, and robustness compared to state-of-the-art algorithms, effectively supporting real-world decision-making under dynamic conditions.

Affiliations: Hangzhou International Innovation Institute, Beihang University, Hangzhou, China; School of Automation Science and Electrical Engineering, Beihang University, Beijing, China; College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore; Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China; AI Atlas Inc.,, Burlington, ON, Canada

Abstract:
This article introduces a novel hybrid method to enable the self-evolution of equipment digital twins (DTs), allowing them to continuously and accurately mirror their physical counterparts. Self-evolution is the process by which a DT autonomously updates its models using real-time sensor data, adapting to dynamic real-world behavior. To enhance this process, we propose a data-physics driven approach that synergistically integrates meta-learning and continual learning. Our method begins by designing an extended residual model using a Koopman autoencoder (KAE) neural network. This component bridges the gap between an imperfect analytical physics model and actual equipment behavior. Next, we employ the Reptile meta-learning algorithm to train offline a versatile foundation model on historical data, endowing it with strong adaptability for rapid learning from new information. A key innovation is a periodic event-triggered mechanism, which monitors the DT’s simulation accuracy against a fixed time window. When a performance discrepancy is detected, it automatically triggers a self-evolution cycle. The foundation model is then updated through a fine-tuning strategy based on continual learning with random reinitialization. This fusion of offline meta-learning and online continual learning allows the DT to quickly adapt to new, unseen scenarios, ensuring it reflects the physical equipment’s state in real-time. We validate the effectiveness and improved performance of our proposed framework through a comprehensive robot simulation case study.

Abstract:
Robots performing collaborative long-horizon dexterity cell micromanipulation tasks are challenging and practically significant, such as peeling cell membranes, which is considered one of the most technically demanding procedures. The imitation learning (IL) approach is expected to address the challenges of multitask coupling and object modeling difficulties in long-horizon tasks. Existing IL algorithms suffer from compounding error as they perform only a simple mapping of the task environment space to the action space. In this article, we propose a skill information representation IL (SIRIL) algorithm for long-horizon dexterous robot micromanipulation tasks. First, SIRIL extracts the discrete latent codes of the expert video frames by the VQ-GAN encoder, and the distribution of the latent codes is modeled by an autoregressive transformer. SIRIL quantifies the representation of the expert’s skill information by computing the log-likelihood of the latent discrete codes, which allows for the extraction of safe action constraints. Finally, SIRIL predicts actions by integrating actions from previous time steps, and actions that satisfy the safety constraints are executed, which effectively suppresses compounding error. Real experiments show that the SIRIL algorithm can complete the deformable zebrafish embryonic cells dexterous membrane stripping surgery. Ablation studies further confirmed SIRIL’s high efficiency in various subtasks, including PushCell, GraspCell, and PeelCell, which achieves an average accuracy of 86.7% and a high final success rate of 64.7%, significantly outperforming existing algorithms. Code is available at https://github.com/zycrobot/SIRIL

Abstract:
This article addresses the lateral dynamics control problem for autonomous vehicle systems under randomly perturbed sampling (RPS) periods and the FlexRay communication protocol. To capture vehicle nonlinearities under variable-velocity conditions, a T–S fuzzy model is constructed using longitudinal velocity as the premise variable. The random sampling behavior caused by hardware aging and environmental disturbances is modeled as a Markovian process. Then, measured outputs are transmitted under the FlexRay protocol (FRP) that integrates both time-driven (static) and event-driven (dynamic) scheduling characteristics. By fully analyzing the situation of static and dynamic scheduling, a unified compensation strategy is employed to build a new switching output model reflecting the impact of the FRP on the measured outputs. Based on this output model, a sampling-mode-dependent fuzzy controller is designed to handle random sampling and hybrid scheduling issues, which results in a membership asynchronous phenomenon between the autonomous vehicle model and controller. By using the asynchronous constraint technique, sufficient conditions with low conservatism are derived to guarantee stochastic stability and H_\infty performance of the closed-loop system. Furthermore, a comprehensive optimization problem (OP) is established, and a corresponding genetic algorithm (GA) is presented to provide a solution-solving scheme. Simulation results confirm the effectiveness and superiority of the proposed control strategy under complex communication environments.

Abstract:
Sedentary behavior (SB) is a major global health concern, necessitating accurate physical activity (PA) intensity monitoring. Conventional machine-learning (ML) methods using accelerometers struggle to generalize due to variability across populations, sensors, and activities, leading to inconsistent real-world performance. This study presents XNet, a dual-domain deep learning (DL) model for classifying PA intensity and estimating energy expenditure. XNet features a hierarchical multihead architecture that independently extracts temporal and frequency features from multiple sensors, then integrates them via a novel attentional feature fusion (AFF) module applied in two stages: first aggregating sensor features, then fusing domain embeddings. This hierarchical approach outperforms single-stage fusion and provides interpretable attention weights revealing sensor and domain contributions. Frequency-domain features are essential for generalization: in cross-dataset evaluations, XNet achieved the highest F1-score of 70.5 while maintaining robust sedentary detection (88% TPR), and in open-set scenarios, it achieved an F1-score of 77.0, surpassing all DL and hand-crafted baselines. We validated XNet on multiple public datasets and a new dataset of 105 participants. Furthermore, our analysis shows that lightweight 1D-convolutional spectral encoders yield better out-of-distribution generalization than transformer and graph attention (GAT) network alternatives, while benchmarking confirms that AFF outperforms nine fusion strategies in balancing accuracy, efficiency, and robustness to sensor failure. The model adapts to physiological signals (heart rate and ECG) and exhibits low inference latency (~25 ms), making it suitable for on-device deployment. A complementary visual analytics framework uses attention weights to facilitate expert auditing, thereby promoting transparent and equitable health monitoring.

Abstract:
This article introduces the physics-embedded neural network (PENN), an enhanced physics-informed neural network (PINN) architecture tailored for visual servoing applications of multirotors. Classical PINNs, while interpretable and data-efficient due to their incorporation of physical laws in the training loss function, often suffer from poor convergence and sensitivity to network initialization and activation functions (AFs). To overcome these challenges, this work proposes two improved architectures: the layer-wise PENN (L-PENN) and the neuron-wise PENN (N-PENN). These architectures embed nominal physical dynamics directly into the structure of the network, thereby improving both training efficiency and predictive accuracy. A spectral analysis of the Hessian matrix is conducted to rigorously demonstrate the enhanced convergence behavior of the proposed architectures compared to traditional PINNs. The proposed methods are experimentally validated on a visual servoing task using a multirotor platform, with performance evaluated in terms of tracking performance and training time. The results are also benchmarked against existing literature, confirming that both L-PENN and N-PENN significantly outperform classical PINNs and other learning-based control strategies. The article concludes by outlining selection criteria for choosing between the two architectures based on specific characteristics of the application.

Abstract:
The sparse identification of nonlinear dynamics (SINDy) approach can discover the governing equations of dynamical systems based on measurement data, where the dynamical model is identified as the sparse linear combination of the given basis functions. A major challenge in SINDy is the design of a library, which is a set of candidate basis functions, as the appropriate library is not trivial for many dynamical systems. To overcome this difficulty, this study proposes SINDy with a library optimization mechanism (SINDy-LOM), which is a combination of the sparse regression technique and the novel learning strategy of the library. In the proposed approach, the basis functions are parametrized. The SINDy-LOM approach involves a two-layer optimization architecture: the inner layer, in which the data-driven model is extracted as the sparse linear combination of the candidate basis functions, and the outer layer, in which the basis functions are optimized from the viewpoint of the recursive long-term (RLT) prediction accuracy; thus, the library design is reformulated as the optimization of the parametrized basis functions. The dynamical model obtained by SINDy-LOM has good interpretability and usability, as this approach yields a parsimonious closed-form model. The library optimization mechanism significantly reduces user burden. The RLT perspective improves the reliability of the resulting model compared with the traditional SINDy approach, which can only ensure the one-step-ahead prediction accuracy. The effectiveness of the proposed approach is verified through numerical experiments.

Abstract:
Human–robot collaboration (HRC) assembly necessitates precise mutual cognition to guarantee safe and efficient execution. In this context, human assembly intention recognition (HAIR) serves as a critical approach to achieving this mutual understanding. However, most current HAIR approaches struggle to extract sufficient spatiotemporal information from limited industrial data, particularly under complex conditions like varying scales and visual occlusions. Thereby, this article proposes an ensemble encoder approach to extract and fuse spatial and temporal features from visual and skeleton streams of the HRC assembly process, thus significantly improving HAIR accuracy and efficiency. First, an RGB feature extraction encoder is designed to model spatiotemporal dependencies of the assembly process with different scales of features from flexible input RGB encoders (RGBEs). Distinctively, a cross-attention module is utilized to fuse information from different-scale RGBEs, ensuring comprehensive assembly action representation with different granularities. Second, to address the occlusion challenge, a mask-aware skeleton feature extraction encoder is devised. By utilizing frame and joint masking strategies, it robustly models the relationship between operator pose evolution and assembly actions, maintaining high performance even under occlusion. Third, a global feature fusion encoder integrates and aligns features from RGB and skeleton feature extraction encoders. Experimental results demonstrate the state-of-the-art performance of the proposed approach, which achieves the highest accuracy of 99.12%, 99.23%, and 84.59% on MCV-Intention, HA4M, and HA-VID datasets, respectively. Six ablation studies demonstrate the performance effects of fusion positions, the number of depth channels, cross-attention fusion module, occlusions, illuminations, and computational efficiency.

Abstract:
The repetitiveness prerequisite of iterative learning control has always been the main obstacle to promoting its practical applications. In this article, a novel adaptive iterative learning reliable control scheme is proposed for the nonrepetitive systems with multiple iteration-varying parametric uncertainties, where actuator faults and state delays are considered simultaneously. During the design of the controller, the class- k_\infty function is leveraged to dispose of the unmodeled lumps of systems through neural networks, and the transformation of control signals is established to compensate for the negative impact of the inefficient actuator. The technical features of our approach lie in an innovative parametric estimation mechanism that integrates the hyperbolic tangent function and an auxiliary sequence is presented to accommodate the nonrepetitive uncertainties, thus achieving the zero-error convergence of output. As the main merits, the proposed control scheme is promising to manifest better performance and practicality than the existing methods, owing to the weak assumptions on the system dynamics, the little prior knowledge of parametric uncertainties, and the strong learning ability of the controller.

Abstract:
A fan-powered tailsitter is capable of operating in both rotary-wing and fixed-wing flight modes. The transition between these modes is critical due to strong disturbances and considerable control complexity. This article investigates a predefined-time stability tracking control problem for tailsitters subject to parameter uncertainties and external disturbances. Based on the second-order dynamic model and high-order fully actuated (HOFA) system approach, a high-order robust controller is first developed to address the limitations of existing mode transitions, particularly in terms of control accuracy and disturbance suppression capabilities. On this basis, a novel predefined-time HOFA scheme is proposed by introducing adjustable parameters, which enables the system states to converge into a small neighborhood of the desired equilibrium within a prescribed time, while providing flexible tuning of the convergence time to adapt to varying mission and environmental requirements. Theoretical analysis and numerical simulations demonstrate that the proposed scheme achieves enhanced control accuracy, faster convergence, and improved robustness compared with conventional approaches. In contrast to existing approaches, the proposed HOFA-based predefined-time framework allows explicit tuning of the convergence time and provides robustness guarantees under parameter uncertainties, an aspect that has not been sufficiently addressed in the current literature.

Affiliations: School of Intelligence Science and Technology, the Institute of Artificial Intelligence, and the Key Laboratory of Intelligent Bionic Unmanned Systems, Ministry of Education, University of Science and Technology Beijing, Beijing, China; College of Automation and Institute of Artificial Intelligence, Beijing Information Science and Technology University, Beijing, China; National Key Laboratory of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China

Abstract:
This article addresses the switching law design problem for switched nonlinear time-delay systems (SNTDSs). The existing switching laws, such as dwell time, average dwell time (ADT), and mode-dependent ADT (MDADT), depict the switching frequency by linear functions of switching interval length, which may insufficiently characterize the switching numbers and features of SNTDSs. To effectively ensure the system stability of SNTDSs and relax the conservatism of stability criteria, two novel switching laws, average switching density and mode-dependent average switching density (MDASD), are first proposed to illustrate the switching frequency of SNTDSs. Meanwhile, under the new switching laws, by constructing the proper multiple Lyapunov–Razumikhin functions, relaxed integral inequalities, and the trajectory-based approach, stability criteria are presented for SNTDSs, which can encompass and include certain aspects of prior research. Moreover, we apply the new switching laws and theoretical results to switched neural networks. Ultimately, we present two examples to confirm the effectiveness of the approaches we have developed.

Abstract:
The problem of command-filter-based adaptive fixed-time tracking control is investigated for nonlinear systems with time-varying uncertain parameters and disturbances in this article. Existing fixed-time control strategies via an adaptive approach are primarily bounded-error, trajectory tracking-oriented. Different from previous results, we propose a new fixed-time stability lemma utilizing an exponential decay function. Then, by leveraging the proposed lemma and command filtered backstepping technique, a novel adaptive fixed-time control scheme is constructed, which can reduce the computational complexity and completely counteract uncertain parameters. We demonstrate that the tracking error enters a neighborhood near zero within a fixed-time and ultimately converges to zero. Furthermore, through the incorporation of a piecewise function into both the filter error compensation system and virtual control laws, the second-order derivability of virtual control laws is guaranteed, thereby ensuring the validity of the command filter. Finally, the proposed strategy’s effectiveness is confirmed through simulation results.

Abstract:
This article investigates the problem of secure state estimation for multitarget tracking systems based on Kalman consensus filtering. In the existing distributed Kalman filters, the filter gain and consensus structure rely on the independence of tracked targets, which cannot maintain the estimation performance when encountering coupled measurements across multiple targets. Moreover, the existing researches mainly focus on the security in single-channel systems, whereas such efforts fail to consider potential attacks in multichannel scenarios. In this case, by establishing a target-dependent augmented system and a link-unreliable composite directed graph, the coupling features and multichannel attacks are depicted. Then, a modified Kalman consensus filter is proposed by specifically designing consensus structure and gain terms to account for the impacts of coupled measurements and attacks. Furthermore, by scaling the Lyapunov function through the Riccati difference equation and matrix inequalities, sufficient conditions are established to ensure the boundedness of estimation errors. Numerical simulations are conducted to demonstrate the effectiveness of the filter.

Affiliations: The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China; Institute of High Performance Computing, A*STAR, Fusionopolis, Singapore; Hubei Luojia Laboratory, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China; School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China; Department of Computing, School of Design, The Hong Kong Polytechnic University, Hong Kong, China; School of Computer Science and Engineering, South China University of Technology, Guangzhou, China

Abstract:
Federated learning (FL) enables multiple clients to learn collaboratively in a distributed way, allowing for privacy protection. However, the real-world nonindependent and identically distributed (non-IID) data will lead to client drift, which degrades the performance of FL. Interestingly, we find that the logit difference between the local and global models increases as the model is continuously updated, which is the primary factor behind performance degradation. This is mainly due to catastrophic forgetting caused by non-IID data between clients. To alleviate this problem, we propose a new algorithm, named FedCSD, a class-prototype similarity distillation in a federated framework to align the logits of local and global models. FedCSD does not simply transfer global knowledge to local clients, as an insufficiently trained global model cannot provide reliable knowledge, i.e., class similarity information, and its wrong soft labels will mislead the optimization of local models. Concretely, FedCSD leverages the similarity between local logits and the global prototype to refine the global logits, thereby enhancing its class similarity information. Furthermore, FedCSD adopts an adaptive mask to filter out the terrible soft labels of the global models, thereby preventing them from misleading local optimization. Extensive experiments demonstrate the superiority of our method over the state-of-the-art FL approaches in various non-IID settings. Code is publicly available at https://github.com/IAMJackYan/FedCSD

Abstract:
As large-scale industrial processes evolve toward greater complexity, the increasing interdependence of networked and dynamic process data has a critical impact on product quality, creating significant challenges for quality-related fault diagnosis. Causal graphs (CGs) are effective in modeling structural relationships among nodes in large-scale industrial processes. However, traditional causal discovery methods are limited in their ability to represent hierarchical and dynamic causal structures with spatiotemporal features. To overcome these limitations, a dynamic causal entropy (DCE)-spatiotemporal convolutional network is designed in this article. First, the proposed DCE method enables the construction of hierarchical dynamic CGs that accurately represent dynamic interactions among process variables, effectively mitigating confounding factors and enhancing interpretability. Second, a 3-D squeeze-and-excitation (SE) convolutional neural network is designed to adaptively recalibrate channel-wise information and deeply analyze the spatiotemporal characteristics embedded in the hierarchical dynamic CGs. Furthermore, a local–global quality-related fault detection approach is introduced, along with a novel causal anomaly vector that facilitates precise recognition of fault root causes across multiple hierarchical levels. Finally, the effectiveness and practical advantages of the proposed method are thoroughly demonstrated using both numerical simulations and real-world data from a hot strip mill process (HSMP), achieving a fault detection accuracy of 95.78%.

Abstract:
Multiple heterogeneous agents are popular for executing pickup and delivery tasks for multiple pairs of customers. The scheduling solutions of agents are expected to complete each task within time windows, even under disturbances. Existing problem models tend to evaluate solutions through multiple simulations based on disturbances. This is time-consuming and implicit. In contrast, this article defines a robustness optimization objective based on the relationship between the agent’s arrival time and the time windows for explicit evaluation. Taking robustness together with makespan and cost, the problem is modeled as a triobjective optimization problem. To solve the problem, this article proposes matrix-learning particle swarm optimization (MLPSO) to obtain diversified and high-quality solutions for decision-makers. In MLPSO, solutions are represented as an adjacency matrix of task sequences and an allocation matrix of agents to tasks. Corresponding to the matrix-based representation, solutions are constructed by planning the task order for execution and assigning agents to tasks. A matrix-distance-based learning (MDL) strategy is developed to select neighbors in the decision space for particle update. In this way, good task segments and allocation pairs can be extracted from learning exemplars and current positions to provide stable updating directions for generating high-quality solutions. To further enhance solution convergence and diversity, a dual-space local search (DSLS) is performed on elite and sparse nondominated solutions. Experimental results on 36 instances with various scales show that the proposed MLPSO is significantly better than state-of-the-art algorithms in terms of solution quality and diversity.

Abstract:
This article proposes a novel reinforcement learning (RL)-based secure control policy for nonlinear Markov jump systems (MJSs) subject to false data injection attacks (FDIAs). First, the Takagi–Sugeno (T–S) fuzzy model is applied to describe the nonlinear MJS. A min–max strategy and an off-policy homotopic Q-learning (HQ) scheme are then introduced to design a secure control policy without requiring knowledge of the system dynamics. The proposed approach offers two main advantages: it does not require an initial stabilizing control gain, and it guarantees unbiased learning under persistently excited conditions. Furthermore, a rigorous stability analysis of the overall closed-loop system under FDIAs is presented. Finally, the effectiveness of the proposed approach is demonstrated using a tunnel diode circuit.

Abstract:
This article proposes a data-driven distributed Kalman filter (DKF)-based sensor fault isolation and estimation scheme for large-scale interconnected dynamic systems, composed of heterogeneous subsystems coupled through a directed topological graph. A local diagnosis unit (LDU) is established for each subsystem, where the data-driven DKF-based residual generator is constructed using local and neighboring process data, effectively decoupling the totally unknown interaction component. Subsequently, fully distributed sensor fault isolation is realized at the subsystem and element levels in simultaneous-fault cases. Both local and neighboring sensor fault isolation can be realized in the LDU, allowing the global system sensor fault isolation with only several key LDUs. Then, the data-driven DKF-based estimator is built in each LDU to estimate sensor faults occurring in multiple subsystems. The distributed Kalman gain is computed in a fully distributed manner, with stability analysis performed locally without overall system knowledge. Finally, the effectiveness and performance of the proposed scheme are validated through case studies on the power network system.

Abstract:
This article investigates the fully distributed output feedback consensus-tracking control problem for multiple wheeled mobile robots (multi-WMRs) subject to dual-actuator faults (DAFs) under the directed graph. First, a fully distributed estimator is designed to asymptotically estimate the leader’s states with nonzero input under event-triggered communication. Next, novel filters are introduced to compensate for unmeasured velocity information in the presence of DAF, and output feedback fault-tolerant controllers are developed to ensure asymptotic consensus tracking despite the faults of actuators. Each robot in the considered multi-WMR system is equipped with two controllers that are co-designed in a unified framework. The final control laws are obtained by solving a set of equations, for which the existence of a unique solution is rigorously established. The proposed scheme not only enables output feedback control under partial loss-of-effectiveness (PLOE) faults in dual actuators, but also ensures fully distributed consensus tracking with event-triggered communication. The simulation results validate the effectiveness of the proposed approach.

Abstract:
This article proposes a finite-time prescribed performance control (FTPPC) method for interconnected nonlinear systems with input saturation. By adding nonnegative auxiliary signals to the setting time of finite-time prescribed performance functions (FTPPFs), we present saturation-tolerant FTPPFs, which are easy to observe the convergence time. Compared with traditional FTPPFs, saturation-tolerant FTPPFs are able to expand from or restore to the expect constraint boundaries based on the input saturation error as well as whether the system enters the collision avoidance regions. Thus, the potential conflicts between input saturation and FTPPFs are resolved. Combined with saturation-tolerant FTPPFs, a low-complexity control algorithm is proposed, which omits the need for a function to estimate the unknown terms and reduces the computation. With the designed control scheme, the boundedness of all closed-loop signals is strictly proved when the feasibility condition is satisfied. Ultimately, simulations are presented to show the capability of the designed controller.

Affiliations: School of Mathematics and Statistics, Guangxi Normal University, Guilin, China; Systems Research Institute of Polish Academy of Sciences, Warsaw, Poland; Department of Automation and the State Key Laboratory of Green Chemical Synthesis and Conversion, Zhejiang University of Technology, Hangzhou, China; Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education, East China University of Science and Technology, Shanghai, China; Guangxi Botanical Garden of Medicinal Plants, Nanning, Guangxi, China

Abstract:
This article addresses the challenges posed by multimode denial of service (DoS) and deception attacks in observer-based sliding mode control (SMC) for fuzzy nonlinear systems. A novel multimode DoS attack model is introduced, incorporating time-varying sojourn probabilities to provide a more accurate and computationally efficient representation of the stochastic nature of these attacks. This model overcomes the limitations of traditional Markov-based models by capturing dynamic attack behaviors. Deception attacks are modeled as unbounded nonlinear functions, and adaptive neural networks (NNs) are employed to approximate their complex behaviors, significantly reducing their detrimental impact on system stability. A fuzzy sliding surface is designed based on the switching rule for sojourn probabilities, and an observer-based SMC law is proposed to ensure the mean square estimation upper bound of the fuzzy nonlinear systems, guaranteeing stability despite the presence of cyberattacks. Finally, the validity and superiority of the proposed control strategy are demonstrated through a tunnel diode circuit model.

Abstract:
In this article, the multisensor particle filtering problem is investigated for a class of nonlinear complex networks with multirate heterogeneous measurements. The underlying complex networks are subject to non-Gaussian noises and randomly switching couplings, while the multirate heterogeneous measurements (including fast-rate binary measurements and slow-rate integral measurements) are transmitted to remote filters via imperfect wireless communication channels. Both the deterministic and stochastic channel gains, along with possible transmission failures, are taken into account to characterize the properties of wireless communication channels. The purpose of this article is to propose a channel-related filtering scheme in the particle filtering framework to address these engineering-oriented complexities. To achieve this, a mixture distribution is established to reflect the effects of randomly switching couplings and generate new particle candidates. By utilizing the Monte Carlo approximation method, two types of update expressions for importance weights are explicitly derived based on the channel properties and the likelihood functions. Finally, numerical simulations are presented to demonstrate the viability and effectiveness of the proposed particle filtering algorithms.

Abstract:
This article explores an adaptive security formation control issue for nonlinear multiagent systems (MASs) against unknown deception attacks. The stable operation of multiagent formation is highly dependent on effective communication transmission between agents. To realize the formation control task, first, a state observer is developed to estimate the states under FDI attacks. Then, the nonlinear state-dependent function is introduced to cope with the asymmetric constraints to ensure a safe and stable operation environment of the agent formation. Furthermore, with the help of coordinate transformation and fuzzy logic systems (FLSs), a fuzzy adaptive formation control scheme with an attack compensation mechanism is developed so that various desired formation patterns are achieved with free collision. Under the proposed scheme, the resulting formation tracking error is uniformly ultimately bounded, and the state constraint of the multiagent system is always maintained, even if the agents are subjected to malicious unknown deception attacks. The effectiveness of the control method is validated through simulation examples.

Abstract:
In human–machine (autonomous vehicles and robots) interaction scenarios, pedestrians often appear in groups. Pedestrian groups provide richer information compared to individuals, which helps address occlusion problems in pedestrian–machine interactions. However, the randomness and spatiotemporal complexity of pedestrian activity make pedestrian group activity recognition (PGAR) a highly challenging task. This article provides a detailed description of the PGAR task. For the first time, a definition of pedestrian group and activity for autonomous vehicles and robots is provided. Existing datasets and methods are systematically summarized. Furthermore, the unique challenges and trends in PGAR for autonomous vehicles and robots are outlined. Although some related surveys have been published, there has not yet been a survey specifically focused on PGAR in autonomous driving and robotics scenarios. Therefore, the goal of this article is to narrow the gap in this topic and provide a comprehensive reference for researchers in this field.

Abstract:
This article explores the problems of the attack-defense framework of power systems; first, an innovative voltage-sensitivity-based (VSB) attack scheduling method is proposed from the perspective of the attacker, with the aim of maximizing disruption to the target bus in the power system. To counteract the introduced VSB attack strategy, a digital second-order generalized integrator phase-locked loop (SOGI-PLL) compensatory mechanism is established to mitigate the adverse effects of the disruption. In the initial phase, the relationships between bus voltages and currents are analyzed, forming the basis for calculating the sensitivity of the target bus to each bus. Building upon this analysis, a novel VSB attack strategy is introduced, allocating higher attack energy to more sensitive buses with the purpose of maximizing the attack disruption of the target bus. Subsequently, a detection–compensation defense framework is established to find and make up for the malicious attack. Specifically, a SOGI-PLL compensation method is introduced to mitigate the negative effect of the attack. Finally, the effectiveness of the attack design method and defense strategy is validated through simulation experiments conducted on the IEEE 14-bus and 39-bus systems.

Abstract:
Multiagent hierarchical reinforcement learning (MAHRL) has been studied as an effective means to solve intelligent decision problems in complex and large-scale environments. However, most current MAHRL algorithms follow the traditional way of using reward functions in reinforcement learning (RL), which limits their use to a single task. This study aims to design a multiagent cooperative algorithm with logic reward shaping (LRS), which uses a more flexible way of setting the rewards, allowing for the effective completion of multitasks. LRS uses linear-time temporal logic (LTL) to express the internal logic relation of subtasks within a complex task. Then, it evaluates whether the subformulas of the LTL expressions are satisfied based on a designed reward structure. This helps agents to learn to effectively complete tasks by adhering to the LTL expressions, thus enhancing the interpretability and credibility of their decisions. To enhance coordination and cooperation among multiple agents, a value iteration technique is designed to evaluate the actions taken by each agent. Based on this evaluation, a reward function is shaped for coordination, which enables each agent to evaluate its status and complete the remaining subtasks through experiential learning. Experiments have been conducted on various types of tasks in the Minecraft World and Office World. The results demonstrate that the proposed algorithm can improve the performance of multiagents when learning to complete multitasks.

Abstract:
This article focuses on prescribed-time distributed robust Nash equilibrium seeking for monotone games impacted by unknown and time-varying disturbances. First, a regularization term with a prescribed-time decaying parameter is introduced to compensate for the absence of strong monotonicity in the merely monotone game. Based on the regularization technique, a new prescribed-time signum-based distributed Nash equilibrium seeking algorithm incorporating an integral sliding mode method, a leader-following consensus protocol, and a gradient algorithm is presented for monotone games with unknown but bounded disturbances. Then, to dispose of the unknown bounds of disturbances, a prescribed-time distributed adaptive integral sliding mode based Nash equilibrium seeking strategy is devised. On the basis of the proposed strategies, some sufficient conditions are obtained to guarantee that the players’ actions are capable of converging to the least-norm Nash equilibrium of the monotone games in a prescribed time. In the end, numerical simulations on least-distance formation control of a network of players testify to the performance of the proposed seeking strategies.

Abstract:
In this article, the high-order fully actuated (HOFA) system approach is applied to study the matrix threshold strategy dynamic event-triggered control problem of a single-link flexible joint robot system (SFJRS). First, the SFJRS is transformed into an HOFA system model by using the recursive “ascending dimension and descending order” method. On this basis, different from the traditional method based on the state-space model, a novel matrix threshold strategy dynamic event-triggered control scheme based on the HOFA system approach is proposed, which not only simplifies the control design but also greatly saves communication resources. It is proved that the closed-loop systems are asymptotically stable under the proposed control strategy. Finally, the superiority of the HOFA system approach and the matrix threshold strategy dynamic event-triggered control method is demonstrated through two different simulation experiments.

Abstract:
This article addresses the integration of model-driven and data-driven approaches for robust hybrid-driven state estimation under limited data and model uncertainties. An unsupervised hybrid estimation framework, termed adaptive model-driven and data-driven (AMD), is proposed. AMD employs an adaptive cross-coupled prior mechanism within the Bayesian inference paradigm to integrate prior information. A two-stage fusion strategy is introduced: an initial hard fusion of model pseudomeasurements and data-driven priors, followed by an adaptive soft fusion that adjusts model influence based on reconstruction discrepancies, thereby enhancing robustness to imperfect model priors. To capture complex nonlinear transition dynamics, a dynamic bilinear recurrent module has been developed, tailored to the system’s underlying behavior. The AMD framework adopts a nonidentical training–testing strategy and an unsupervised hybrid learning objective inspired by the information bottleneck principle, enabling accurate parameter learning without access to ground-truth states. Extensive experiments on multiple nonlinear chaotic systems have demonstrated that AMD consistently achieves competitive or superior estimation accuracy compared to state-of-the-art model-based and hybrid approaches, particularly under underdetermined estimation, model mismatch, and dynamic disturbances. These results demonstrate AMD’s capability to effectively leverage limited information through complementary fusion, thereby enhancing both data representation and model robustness. This adaptability positions AMD as a powerful solution for challenging state estimation problems.

Abstract:
Pedestrian trajectory prediction is an important research area with significant applications in autonomous driving and intelligent surveillance. However, existing studies on pedestrian trajectory prediction often suffer from a noticeable discrepancy between predicted and actual trajectories, due to incomplete extraction of pedestrian trajectory features and the randomness of the pedestrian walking process. The key objective of this article is to address this issue by proposing a method that can reasonably simulate the randomness of pedestrian walking and comprehensively extract pedestrian trajectory features. To achieve this, a novel social informer model built upon the informer model is proposed in this article. The social informer utilizes a transformer encoder-based interaction module to comprehensively extract pedestrian trajectory features, which are input into the informer model for further processing. Additionally, an adaptive variance mechanism is proposed to determine the optimal variance and accurately simulate the random nature of pedestrian walking. Finally, the proposed model is evaluated in a comparative experiment on ETH and UCY datasets, with results demonstrating that the proposed model outperforms other models, exhibiting improved accuracy and performance.

Abstract:
To elevate the robustness and optimality of helicopter formation, this article proposes the incremental fully actuated system approach (FASA) integrated with reinforcement learning (RL) for the formation control of multiple helicopters with faulty swash plates. First, the helicopter model encompassing aerodynamics, flapping dynamics, and swash plate dynamics under actuator faults is established. Then, the entire helicopter formation is reinterpreted and stabilized by the incremental FASA that offers the replacement of model information, the suppression of lumped uncertainty, and the rearrangement of system dynamics, with mitigated reliance on model accuracy and computing resources. Next, considering the influence of the actuator faults of a single helicopter on the convergence of the entire formation, RL is applied to pursue the optimal control strategy against fault impact through the critic network, which updates along the dynamics revised by the incremental FASA, ensuring satisfactory formation performance throughout the flight, augmenting the cost efficiency of the control scheme, and relieving any means of identification or approximation on helicopter dynamics. Finally, the stability of the control scheme is proved, and numerical simulations are conducted to illustrate it is efficiency.

Abstract:
This article investigates a conflict-constrained control method for switched multiagent systems with nonaffine nonlinear faults. Existing studies on state constraints often assume that the reference signal always stays within the constraint set. However, in practice, constraints may be dynamically detected during system operation and conflict with predefined reference signals, causing brief violations of the constraint boundaries. When the reference signal cannot remain within the prescribed range, many backstepping control methods based on barrier Lyapunov function and nonlinear transformations become ineffective. To address this, a new safe reference signal is constructed by using a virtual circle approach, and a conflict-constrained control method is proposed. By combining a common Lyapunov function and the radial basis function neural network, the effects of switching behavior and nonaffine nonlinear faults can be effectively compensated. A shift function is also introduced in the coordinate transformation to further relax constraints on initial values. The proposed method is validated through multiple simulation experiments.

Abstract:
Nonstationarity in industrial processes, guided by factors, such as equipment aging and changing upstream load demands, inherently exhibits heterogeneous characteristics. This complex overlay of homogeneous stationarity poses great difficulty in process monitoring and analysis. Therefore, this study presents a new model (Hs- \mathrm H_\mathrm n ) that peels the homogeneous and heterogeneous nonstationarity, which has four components: a differentiated learning network (DL-Net), a peeling network (Pe-Net), an adaptive reweighting network (AR-Net), and a global decoder network. DL-Net obtains the differentiated representation by leveraging a new differentiated learning approach to unique inputs, which is based on the cognitive understanding and derivation of functional specialization and content learning during network training. The aim is to maximize functional diversity and minimize content overlap. Furthermore, Pe-Net extracts the stationarity and nonstationarity (S-N) components from each differentiated scale, formulated as an encoder–decoder–encoder architecture with an integrated identity subtraction skip connection. A min–max S-N constraint regulates the peeling process and controls the extracted content. AR-Net additionally refines homogeneous stationarity across each scale and reweights the individual components to adaptively adjust their contributions. Last, reweighted components are fused and input into the global decoder to facilitate unsupervised learning. Experimental results on three processes demonstrate the effectiveness of Hs-Hn.

Affiliations: State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai, China; Department of Automation, Technical University of Cluj-Napoca, Cluj-Napoca, Romania; Department of Automation and Applied Informatics, Politehnica University of Timişoara, Timişoara, Romania; Department of Mechanical Engineering, Washington University in St. Louis Campus, St. Louis, MO, USA; Research and Innovation Centre, Óbuda University, Budapest, Hungary

Abstract:
Conventional fault-tolerant control (FTC) schemes typically assume the exponent of the faulty input to be 1, overlooking its impact on actuator power. In this article, we propose a novel FTC strategy that extends the exponent to any positive odd integer, thus capturing higher-order fault effects. In addition, by integrating a Gaussian function to modify the constraint boundaries, a novel suction-cup-type prescribed performance function is proposed. Unlike existing prescribed performance functions, this design uses a suction cup module to regulate output overshoot without requiring asymmetric design. This design is globally effective, eliminating the initial feasibility conditions. Simulation results validate the effectiveness of the proposed scheme.

Abstract:
Most output-constrained methods necessitate reference command within a predefined safe region, without considering cases where the command itself may conflict with safety boundaries. To handle this problem, this article proposes a predefined-time safe cooperative control scheme for multiagent systems under output constraints, privacy preservation and unknown disturbances. At the communication layer, an encryption–decryption mechanism is developed to safeguard information exchange among agents, preventing internal states from being identified by eavesdroppers. At the control layer, to ensure strict adherence to output constraints regardless of whether the original command complies with safety limits, an improved boundary protection method is explored to generate a safety reference trajectory, which is subsequently used in the controller design. Adaptive laws are then formulated to counteract the effects of unknown nonlinearities and disturbances. Finally, by leveraging predefined-time stability theory, a predefined-time safe cooperative controller is designed to ensure error convergence within a user-defined settling time. Theoretical analysis rigorously confirms the closed-loop stability, and simulations verify the effectiveness of the proposed method.

Abstract:
A key aspect of decentralized multirobot coordination is communication. However, beyond simple signaling, there are only few reports in the literature on the successful evolution of communication, with successes largely dependent on specific tasks and evolutionary setups. Thus, there is a lack of standardized communication frameworks that can be applied to different tasks without the need to redesign, rebuild, or re-evolve the entire system for every new task. In this article, we propose a novel communication module that does not need to be modified for its use in different tasks. Each robot has a coordinate (state) in a virtual communication space. The communication space is partitioned into virtual regions, and each region is linked to a physical behavior, such as seeking resources, phototaxis, or recharging the battery. A robot’s individual behavior is determined by the region to which its current communication state belongs. Since robots can navigate the communication space and continually broadcast their coordinates to neighbors within range, robot swarms can effectively coordinate their behavior in a self-organized manner. We demonstrate that the same evolved communication module is effective in three swarm robotics tasks: 1) the physical aggregation of the robots into groups of a desired size; 2) the formation of desired swarm geometries; and 3) a foraging task based on temporal role allocation. The results show that the communication module provides good and scalable performance in all tasks, representing a significant step toward a task-agnostic communication framework for robot swarms.

Abstract:
This article introduces the Bayesian probabilistic fuzzy neural network (BPFNN), a unified architecture designed to overcome the challenges of conventional fuzzy clustering and neural networks in terms of uncertainty, noise, and interpretability. At its core, the Bayesian probabilistic fuzzy C -means (BPFCMs) algorithm is employed to define the hidden-layer nodes, extending traditional FCM through non-Gaussian modeling and posterior inference via Markov chain Monte Carlo (MCMC). By combining Metropolis–Hastings (MHs) for membership updates with Gibbs sampling for parameter estimation, BPFCM yields probabilistic memberships that capture uncertainty in the antecedent rules more effectively than deterministic approaches. Since the hidden-layer activations represent only similarity values between inputs and cluster centers, the original input features are not directly preserved. To compensate, the hidden-to-output connections are formulated as linear functions of the input, ensuring recovery of discriminative information in the consequent rules. These functions are optimized using a generalized cross-entropy (GCE) objective, with iteratively reweighted least squares (IRLSs) employed for efficient and regularized updates. Extensive experiments on benchmark datasets and high-dimensional laser-induced breakdown spectroscopy (LIBS) spectral data confirm that BPFNN consistently surpasses both classical fuzzy systems and contemporary deep learning models, providing improved accuracy, robustness, and interpretability.

Abstract:
This work studies the problem of data-driven event-triggered control of continuous-time multiagent systems (MASs) with communication delays. A hybrid system approach is proposed to address this problem, hybrid dynamic event-triggering mechanism (DETM) is utilized to ensure strong Zeno-freeness and estimated system matrix is introduced to design time-varying state estimator. By using several auxiliary variables, the closed-loop MAS is described into hybrid system form, that can completely describe the flow dynamics and jump dynamics of the MAS in the presence of communication delays. Then, data-based controller gain matrix design is developed and an estimator is designed to estimate unknown system matrix. After that, based on derived model-based stability conditions and combined with data-driven representation of MAS, data-based stability analysis and event-triggering mechanism (ETM) design results are obtained. The main advantages of the proposed approach in contrast with existing works are that accurate system model is not needed and strong Zeno-freeness is ensured under the scenario with communication delays. Finally, the effectiveness of the proposed method is verified by simulation example.

Affiliations: Institute of Industrial Intelligence and Data Engineering, School of Artificial Intelligence, Taizhou University, Taizhou, Zhejiang, China; School of Microelectronics and Control Engineering, Changzhou University, Changzhou, China; School of Electronics and Information Engineering, Wuhan Donghu University, Wuhan, China; Department of Foundational Mathematics, School of Mathematics and Physics, Xi’an Jiaotong-Liverpool University, Suzhou, China

Abstract:
This article delves into the exploration of state-space methods applied to the modeling and estimation of systems with time-varying parameters. While typically existing approaches rely on the assumption that the parameters satisfy the Markov evolution and require the knowledge of the transfer matrix, this article develops an explicit autoregressive (AR) model for time-varying parameters in which the invariant matrix represents the dynamic changes in the parameters. Unlike the previous work, the state-space model is constructed by stacking the invariant matrix and time-varying parameters into the unknown state vector. Then, the joint state estimation (JSE) algorithm is deduced based on the Kalman filtering principle, aiming to reduce the dependence on the prior knowledge of the invariant matrix. Through the numerical simulation and Monte Carlo test, it is indicated that the developed algorithm maintains reliability under various random white noises. In addition, the practical estimation results with the real-time series also verify the validity.

Abstract:
Distributed formation tracking control with obstacle avoidance of multiagent systems (MASs) under random switching topologies and external disturbances is considered in this article. To achieve the complex objective, an effective control strategy is developed in three steps. First, under the transition probability (TP)-based mode-dependent average dwell-time (MDADT) switching topologies, a distributed objective trajectory achieves almost sure global exponential tracking of the desired formation trajectory. Second, a safe objective trajectory approach is designed by geometrically projecting the unsafe parts of the existing formation trajectory onto the boundary of the obstacle region. Finally, an integral-multiplicative barrier Lyapunov function (IMBLF) is proposed to allow agents to track the safe objective trajectory, where the IMBLF can further guarantee the safety of the MASs. One of the interesting merits of our results is that the impulsive increasing of Lyapunov function at switching instants which is necessary for classical analysis methods has been removed. The feasibility of the proposed formation control method with obstacle avoidance is verified by simulations.

Affiliations: College of Information and Communication Engineering, Key Laboratory of Advanced Marine Communication and Information Technology (Ministry of Industry and Information Technology), National Key Laboratory of Underwater Acoustic Technology, Harbin Engineering University, Harbin, China; School of Information Science and Engineering, Dalian Polytechnic University, Dalian, China; School of Electrical and Information Engineering, Jiangsu University of Technology, Changzhou, China

Abstract:
Translating the complex dynamics of biological nervous systems into engineered models is crucial for understanding the essence of intelligence and creating human-like artificial intelligence. This article presents a four-dimensional memristive Morris–Lecar model, constructed by coupling a locally active memristor (LAM) with the Morris–Lecar model, which features fast-slow dynamics. Through stability analysis of equilibrium points, the potential mechanism is qualitatively investigated by which three types of equilibrium points trigger neuronal oscillatory activity. Different dimensions of bifurcation diagrams and other numerical techniques reveal that neuronal firing activity and its dynamic characteristics are regulated by three factors: 1) LAM; 2) the slow variable; and 3) ion channels. Based on bursting activity, the fast-slow variable analysis method is employed to study fold and Hopf bifurcations, and the fast-slow dynamics under synergistic control are elucidated. Notably, coexisting attractors are discovered and found to be closely related to LAM. Finally, the neuronal model is implemented on an FPGA to generate firing activities with diverse dynamic characteristics.

Abstract:
In this article, the problem of practical prescribed-time (PT) cooperative path following (CPF) is investigated for underactuated autonomous surface vehicles (ASVs), which are not equipped with velocity sensors and subject to unmodeled dynamics and actuator saturation. First, a practical PT velocity observer (PTVO) is designed to estimate unmeasurable velocity information, which is then employed in the design of the guidance law and controller. At the kinematic level, a cooperative guidance law based on aperiodic intermittent communication is developed for synchronized path following, effectively saving communication resources. At the dynamic level, an aperiodic intermittent controller incorporating neural networks (NNs) is designed to approximate unmodeled dynamics and effectively avoid continuous operation of actuators with input saturation. Meanwhile, the intermittent adaptive law is constructed to estimate the optimal weights of the NNs, thereby reducing their complexity. The closed-loop system is verified to converge to a residual set within a PT interval. Finally, we conduct numerical simulations to demonstrate the effectiveness of the proposed algorithms.

Affiliations: School of Information Science and Technology, Beijing Laboratory of Smart Environmental Protection, Beijing Key Laboratory of Computational Intelligence and Intelligent System, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China; College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, China; Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen, China

Abstract:
This article addresses the issue of output synchronization via intermittent dynamic event-triggered sampled-data (IDETSD) security control of reaction–diffusion neural networks (RDNNs) under spatially local averaged measurements (SLAMs) subject to both delays and random deception attacks, where a Bernoulli distribution is utilized to describe whether channels suffer from the cyberattacks. An IDETSD security control method under SLAMs and random deception attacks is presented to achieve the output synchronization of delayed RDNNs. Compared with time-triggered intermittent sampled-data (SD) control strategies, a dynamic event-triggered (ET) mechanism to more effectively mitigate the impact induced by random deception attacks that intentionally tamper with the state transmission signals from sensors to controllers is introduced in this article. Moreover, new output synchronization criteria are established by applying an ET-dependent switched Lyapunov functional (LF) and inequality techniques. Then, the desired IDETSD controller is obtained by solving linear matrix inequalities (LMIs). To validate the efficacy of the proposed approach, simulation outcomes from two numerical studies are presented.

Abstract:
A fundamental challenge in car-following (CF) modeling lies in accurately representing the multiscale complexity of driving behaviors, particularly the intradriver heterogeneity where a single driver’s actions fluctuate dynamically under varying conditions. While existing models, both conventional and data-driven, address behavioral heterogeneity to some extent, they often emphasize interdriver heterogeneity or rely on simplified assumptions, limiting their ability to capture the dynamic heterogeneity of a single driver under different driving conditions. To address this gap, we propose a novel data-driven CF framework that systematically embeds discrete driving regimes (e.g., steady-state following, acceleration, cruising) into vehicular motion predictions. Leveraging high-resolution traffic trajectory datasets, the proposed hybrid deep learning architecture combines gated recurrent units (GRUs) for discrete driving regime classification with long short-term memory networks (LSTMs) for continuous kinematic prediction, unifying discrete decision-making processes and continuous vehicular dynamics to comprehensively represent interdriver and intradriver heterogeneity. Driving regimes are identified using a bottom-up segmentation algorithm and dynamic time warping (DTW), ensuring robust characterization of behavioral states across diverse traffic scenarios. Comparative analyses demonstrate that the framework significantly reduces prediction errors for multiple metrics while reproducing critical traffic phenomena, such as stop-and-go wave propagation and oscillatory dynamics.

Abstract:
This article presents a novel prescribed-time fuzzy adaptive consensus control scheme for nonlinear photovoltaic (PV) energy systems with dead-zone and actuator faults. The PV panels are controlled to track the maximum power point so that the considered systems can efficiently operate under different complex conditions. To quickly regulate the voltage to a desired reference, a novel prescribed-time performance function is presented to guarantee systems states convergence within a specified time. Besides, dead zones and faults are serious nonlinearity constraints in practical grid-connected PV systems. Thus, a finite-time tracking controller and the adaptive laws are designed to compensate for the effect of unknown nonlinear constraints. By applying fuzzy logic systems, the difficulty of dealing with unknown nonlinear dynamics is overcome. The stability of the closed-loop system is rigorously proven using Lyapunov stability theory, demonstrating the uniformly ultimately boundedness of all signals. Finally, extensive simulation experiments validate the effectiveness and superiority of the proposed approach.

Abstract:
In distributed machine learning scenarios, the difference in data distribution among different nodes is a key issue that cannot be ignored. However, existing methods make it difficult to autonomously adjust model parameters for dynamically changing data distributions, leading to inflexible global decision boundaries with insufficient local adaptation. To address this problem, we propose a distributed hybrid support vector machine (SVM) based on the adaptive ensemble selection of regularization parameters, DHS-AE. The model utilizes the data structure information to cut the data space and thus identify data distribution characteristics. The SVM, integrated with regularization parameters that are adaptively determined within specific ranges, is utilized in the local subspace to enable real-time adjustment of decision boundaries in response to distribution changes, thereby further reducing the computational overhead. The generalization bound of DHS-AE is theoretically established using covering numbers, and the fast convergence speed and consistency are derived. In practical applications, we verify the excellent performance of the DHS-AE using a large number of real datasets.

Abstract:
The stability analysis of networked switched systems becomes highly challenging when multiple factors—such as frequent switching, denial-of-service (DoS) attacks, transmission delays, and actuator faults—coexist under an event-triggered mechanism (ETM). These intertwined factors cause complex timing mismatches that invalidate most synchronization-based control frameworks. To address this challenge, this article proposes a resilient event-triggered fault-tolerant control strategy that captures multisource asynchrony by classifying multiple key instants and modeling their interactions through a Lyapunov-based scheme. Unlike most existing studies that rely on synchronized switching assumptions or oversimplify the timing structure by ignoring delays and DoS attacks, this work explicitly incorporates these asynchronous phenomena into a unified analytical framework. First, to ensure timely packet transmission, a hybrid ETM is designed by combining time-triggering and event-triggering conditions. A switched Lyapunov function is then constructed by classifying different intervals, thereby unifying the analysis of asynchronous behaviors and DoS-induced disruptions. Furthermore, a resilient codesign strategy is developed, where the event-triggered parameters and fault-tolerant control gains are jointly designed under an explicit trade-off among the average dwell time parameter of switching signals, DoS attack parameters, and the sampling period. Under the proposed framework, global exponential stability with H_\infty performance is guaranteed despite the presence of transmission delays, actuator faults, and DoS attacks. Finally, the effectiveness of the proposed method is demonstrated using a quarter-vehicle suspension system.

Abstract:
This article studies the 3-D dynamic rendezvous control problem for coordinated heterogeneous marine vehicles, including an uncrewed underwater vehicle (UUV) and an autonomous surface vehicle (ASV). An observer-based safety-preserving rendezvous control approach is proposed to robustly stabilize the rendezvous errors under the port-Hamiltonian (PH) framework. First, an interconnection and damping assignment passivity-based control (IDA-PBC) method is adopted to provide a basic stabilizing control framework. In this problem, both vehicles are faced with hydrodynamic model uncertainties and unknown external disturbances. Then, to preserve the rendezvous safety under uncertain dynamics, the prescribed performance control (PPC) transformation is implemented for the ascending motion to get the equivalent approaching-constrained PH system. The intuitive design procedure provided by the IDA-PBC method, along with the collision-free rendezvous safety guaranteed by the auxiliary PPC technique, reduces the controller design complexity while providing a smooth rendezvous trajectory. Besides, a structure-keeping uncertainty observer algorithm is designed and incorporated to simultaneously handle model uncertainties and environmental disturbances without destroying the interconnection structure. Under the proposed approach, the UUV-ASV rendezvous errors can be effectively stabilized with rigorous closed-loop stability analysis. Finally, both simulations and comparative experiments are conducted to demonstrate the effectiveness and advantages of the proposed approach.

Abstract:
The inverse dynamic games problem is to model expert demonstrations by identifying the underlying cost functions of multiple agents from observed trajectories of their dynamic game interactions. This article investigates discrete-time, finite-horizon linear-quadratic (LQ) problems where both the state weight matrix and input weight matrix are unknown, with the presence of both process noise and observation noise. In addition, each player’s cost function incorporates a player-specific, unknown linear term with respect to the state. Under this framework, first, sufficient conditions are established for the solvability of the weight matrices. Subsequently, it is proved that the inverse dynamic games problem involving heterogeneous unknown target states is structurally identifiable, unaffected by process noise. Building on the necessary conditions for Nash equilibrium solutions in forward problems, the estimation of the cost function parameters is formulated as a nontrivial solution to a homogeneous linear estimation problem, which can be implemented in a distributed manner. Furthermore, the proposed estimator achieves statistical consistency under the influence of observation noise. The effectiveness is illustrated through a multivehicle spring-coupled dynamic game and an interactive steering control scenario.

Abstract:
This article aims to investigate the neural network (NN) nonsingular fixed-time adaptive consensus control issue for nonlinear multiagent systems (MASs) with parameter uncertainties. By introducing a generalized intermediate-variable-based disturbance observer (IVBDO), a novel distributed fixed-time NN adaptive controller is constructed based on the quartic Lyapunov function method. Under this protocol, the mismatched external disturbances of each agent are real-time online estimated; meanwhile, the singularity phenomenon during the fixed-time design process can be effectively eliminated. The presented control algorithm not only guarantees that the controlled system is semi-globally uniformly ultimately bounded (SGUUB) but also that the distributed output tracking errors converge to an adjustable compact set of the origin within a fixed-time interval. Simulation results are displayed to check the effectiveness of the suggested approach.

Abstract:
A novel thruster fault detection (FD) strategy is investigated in this article for unmanned marine vehicles (UMVs) under external disturbances and aperiodic denial-of-service (DoS) attacks. To address the challenge of the inability to timely detect DoS attacks, the UMV under consideration and its corresponding filters are initially modeled under the framework of an asynchronous switched system. Then, sufficient conditions guaranteeing the system to be exponentially stable and with the prescribed performances are derived by leveraging the model-dependent average dwell time (MDADT) and piecewise Lyapunov functions (PLFs). Simultaneously, the lower bound of the tolerable sleep interval and the upper bound of the DoS attack interval are rigorously calculated. The design criteria of the FD filters are subsequently obtained through the employment of some decoupling techniques. Finally, the simulations on a UMV demonstrate the effectiveness of the proposed methods.

Abstract:
In this article, we investigate the task optimization for fixed-time control of intermittent human–robot interaction, where a human operator assists the robot intermittently in selecting the most appropriate Pareto solution. First, as for the Lyapunov fixed-time stability criterion inequality with and without the constant term, we all derive the Lyapunov stability conditions with time-varying exponents and coefficients, providing us with more flexibility and freedom to shape the contour of the convergence near the Lyapunov stable equilibrium. We then use them to propose a hierarchical fixed-time event-triggered optimization (HFTEO) algorithm based on human-oriented scheme, where the so-called human-oriented scheme means that the components constituting task information are known only to the human operator, but not to the robot, which is beneficial to ensure the confidentiality and security of the task. Simulation results are given to show the effectiveness of the proposed Lyapunov stability conditions and algorithm.

Abstract:
The coal mine integrated energy system dispatch problem (CMIES-DP) is a constrained multiobjective optimization problem (CMOP) with the characteristics of multiple objectives, high-dimensional decision variables, and multiple constraints, which makes it challenging for existing methods. On the one hand, existing constrained multiobjective evolutionary algorithms (CMOEAs) are prone to falling into local optima when facing problems with high-dimensional variables. On the other hand, the relationship between objectives and constraints of CMIES-DP has not been fully analyzed to guide the design of targeted solving techniques. Therefore, this article proposes a time-division-based CMOEA (TDCEA), where the characteristics of CMIES-DP are analyzed to design two main strategies. First, by analyzing the temporal relationship of objectives and constraints, CMIES-DP is decomposed into multiple subproblems with fewer variables and constraints, and these subproblems are sequentially solved to obtain better decision variables. Then, a random concatenation method is designed to combine the decision variables output from subproblems into a solution set with complete decision variables, and the new solution set will be further optimized to find feasible Pareto optimal solutions. Second, the relationship between constraints and objectives is analyzed to guide the design of evolving populations, so as to improve the search ability of the algorithm. In the experiments, the proposed algorithm is used to solve a real-world CMIES-DP case, and results demonstrate that compared with other advanced algorithms, the proposed algorithm achieves better performance regarding diversity, convergence, and distribution.

Abstract:
This article investigates the security control issue of delayed coupled fuzzy inertial neural networks (FINNs) under deception attacks. Aiming to alleviate the influence of deception attacks, a fuzzy sampling data security controller is designed. A theoretical structure is formulated to analyze the behavior of the closed-loop system under deceptive interference. On this basis, by constructing a suitable set of Lyapunov functionals (LKFs) and employing inequality techniques, criteria guaranteeing exponential synchronization are established using linear matrix inequalities (LMIs). Finally, the effectiveness of the proposed method is demonstrated via numerical simulations and encryption and decryption analysis. Results show that, affected by deception attacks, the coupling FINNs can achieve exponential synchronization through our developed security control approach.

Abstract:
Control barrier functions (CBFs) provide a rigorous framework for enforcing safety in control-affine systems by ensuring system states remain within predefined safe sets. However, practical deployment faces fundamental challenges that limit real-world applicability. This review analyzes recent progress in CBF methodologies across three interconnected domains: uncertainty handling, structural optimization, and feasibility assurance. For uncertainty, we distinguish strategies tailored to unknown dynamics, modeling discrepancies, and dynamic environments, spanning robust theoretical methods and learning-based approaches. For structural design, we examine class- \mathcal K function selection, parameter tuning, and advanced modifications that jointly address conservatism and feasibility. For feasibility, we identify the root causes of CBF-QP infeasibility and survey solution strategies, including constraint relaxation, structural redesign, and mathematical guarantees. By synthesizing these directions into a unified framework, this review highlights key interdependencies and outlines future research opportunities for advancing CBF-based safety-critical control in robotics, autonomous systems, and beyond.

Abstract:
Gaussian processes (GPs) have attracted considerable attention in assisting evolutionary algorithms (EAs) to solve computationally expensive optimization problems (EOPs) because they can directly provide information about the uncertainty of their predictions. However, the computational complexity of GPs grows cubically as the amount of data increases, which severely limits their computational efficiency in high-dimensional expensive multiobjective optimization problems (EMOPs). To address this limitation, we propose a surrogate-assisted evolutionary algorithm (SAEA) that integrates multilayer perceptron (MLP) grouping with sparse GPs, referred to as MLPSGP-SAEA. First, the MLP grouping selects a subspace from the original space by evaluating the impact of each decision variable on the objective functions. Then, for each objective function, a sparse GP model is employed, and the locations of pseudo-input points are optimized to enhance computational efficiency while improving model accuracy. Moreover, an adaptive sparse and diverse (ASD) infill criterion is proposed, based on the characteristics of the sparse GP model predictive distribution, to better balance exploration and exploitation. Finally, extensive experiments are conducted on four benchmark suites and an aerodynamic design optimization problem. The experimental results demonstrate that MLPSGP-SAEA exhibits significant competitive advantages over the state-of-the-art SAEAs.

Abstract:
Analyzing conflicts between multiple objects within fuzzy information systems (ISs) and providing effective conflict resolution are challenging tasks due to the complexity and uncertainty of the real world. This article proposes a three-way conflict analysis and resolution model for intuitionistic fuzzy ISs (IFISs) based on three-way concept analysis (3WCA). First, the straight and vertical distances between intuitionistic fuzzy values (IFVs) are defined to obtain an intuitionistic fuzzy probability–credibility distribution. Second, intuitionistic fuzzy optimistic and pessimistic formal contexts are proposed based on two novel binary relations of intuitionistic fuzzy information. Afterward, two intuitionistic fuzzy concept lattices are obtained to analyze the marginal conflict degrees among multiple objects via consistency, inconsistency, and uncertainty attribute sets. By introducing three pairs of thresholds, the trisections of object pairs, objects, and attributes are derived through the three-way decision (3WD) process. Specifically, the maximal alliance unit, minimal conflict unit, and feasible strategy set are identified according to the three-way conflict analysis results. Subsequently, the consistency measure extracted from the intuitionistic fuzzy distance matrix is utilized to rank all feasible strategies. Finally, the experimental results are conducted to verify the effectiveness, superiority, and feasibility of the proposed model.

Abstract:
Asymptotic state regulation of fully actuated systems (FASs) with time-varying unknown parameters, perturbed input matrices, and nonlinear uncertainties is considered. Compared to the closely related results on FASs with time-varying parameters, the requirement that the time-varying parameters are differentiable and the assumptions imposed on their derivatives in those works are no longer needed in this article, which means that many types of time-varying parameters that were difficult to handle by previous methods, such as those that are continuous and bounded but not differentiable, can now be handled. Furthermore, inspired by the congelation of variables method, a novel robust adaptive method is proposed, which achieves the global asymptotic convergence of the state variables instead of the global boundedness obtained in previous methods, and guarantees the global boundedness of the estimation. In the developed controller, the adaptive part compensates for time-varying parameters, and the robust part overcomes the effects of incomplete compensation and other remaining uncertainties. Moreover, a parallel extension of the developed method to the disturbed case and a discussion on parameter selection are given. Finally, the proposed method is successfully applied to the control of resonant circuit systems and Norrbin ship steering systems.

Abstract:
This article investigates the sliding mode control (SMC) problem for a class of Markov jump systems (MJSs), in which the system states are sampled randomly and nonuniformly according to Markov chain. Besides, the transmission of sampled states through the shared network channel is inevitably subject to deception attacks obeying Markov model. In order to facilitate the subsequent design and analysis, the encountered three Markov chains are first mapped into one, meanwhile, a suitable mode detection scheme is put forward to simultaneously detect the partially inaccessible modes including the controlled system modes and attack modes. And then, a detected-mode-dependent sliding mode controller is designed to effectively cope with the stochastic features of sampling processes and attack occurrences. Furthermore, the reachability of the specified sliding surface and the mean-square exponential ultimate boundedness of the closed-loop system are analyzed and the corresponding conditions are derived. Finally, two simulation examples are provided to illustrate the designed control method.

Abstract:
In this article, the accelerated intelligent critic tracking predictive control with data experience replay (AICTPC-DER) framework is constructed to address the trajectory tracking problem of the nonlinear systems with unknown dynamics. The receding optimization mechanism of model predictive control and the intelligent critic scheme are deeply integrated to realize real-time optimization of online policies. First, the time-series data of the unknown system is collected to establish a deep neural network as the prediction model. Afterward, in order to improve the efficiency of solving optimization problems online, the accelerated critic architecture with experience replay via collecting tracking error data is established based on the conventional adaptive critic designs. Simultaneously, the theoretical properties of the AICTPC-DER algorithm are comprehensively analyzed. Finally, a large number of simulation results verify the effectiveness and progressiveness of the AICTPC-DER algorithm in solving tracking problems, among which the advantages of the accelerated factor and the DEP mechanism are apparent. From the comparative experiments, it can be seen that the developed algorithm exhibits superior control performance.

Abstract:
Enhancing large language models (LLMs) with external knowledge base retrieval in the fashion manufacturing industry can provide more reliable technical support and decision-making assistance, significantly improving process control and boosting intelligent production efficiency. However, the field of fashion manufacturing involves highly specialized terminology, logically complex technical knowledge, and intricate query tasks. Existing simple query-matching techniques often return a large number of contextually loose and redundant document chunks, severely impacting the model’s understanding and response quality. To address this issue, this article proposes a retrieval optimization framework based on a dynamic capsule routing network with embedded semantic graph (SGDCR), which models semantic relations among multiple retrieved documents by simulating a team collaboration mechanism. Specifically, the framework consists of two steps: filtering and reranking. First, a capsule routing mechanism embedded in a semantic association graph dynamically captures complex contextual relationships among coarse-grained document blocks, learns contribution scores for multiple documents, and filters irrelevant or redundant documents based on ranking. Subsequently, the filtered documents are matched with the query through deep semantic similarity measurement, and the documents are reranked by integrating relevance scores and contribution scores and generating efficient, accurate, and contextually coherent document prompts. Experimental results on publicly available dense open-domain QA datasets and a constructed fashion manufacturing process QA dataset demonstrate the effectiveness and superiority of the proposed method over existing reranking approaches in the fashion manufacturing knowledge QA system.

Abstract:
This study investigates the problem of achieving consensus within a prescribed time for general linear multiagent systems (MASs) operating over directed communication graphs, particularly when agents can only access relative output data via their onboard sensors. Under the assumption of strong observability, we design a periodic delayed output measurements-based distributed observer to recover the relative state information. Leveraging the reconstructed states, a linear time-varying control protocol is developed to ensure consensus is attained within the desired time. In contrast to conventional approaches, our method brings several key benefits. Most importantly, it removes the requirement for direct data exchange over the network, making the system inherently robust against cyber-attacks. Furthermore, the protocol is entirely distributed, which enhances adaptability to dynamic communication structures. At last, since the proposed method utilizes linear state feedback, it avoids the need for real-time solutions of system-related differential equations, thus reducing computational overhead. Numerical simulations demonstrate the efficacy of the proposed strategy.

Abstract:
The article focuses on the design of event-triggered decentralized asynchronous (ETDA) control for positive interconnected switched systems (PISSs) subject to a mode-dependent minimum dwell-time (MDMDT) constraint. First, a novel 1-norm-based event-triggered mechanism (ETM) and a decentralized asynchronous control strategy (DACS) are proposed to facilitate the design of an ETDA control framework. Next, a sufficient positivity criterion is presented for PISSs in a closed-loop. Then, by constructing a newfangled discretized linear copositive Lyapunov function (DLCLF) for MDMDT switching, and utilizing the matrix decomposition approach for ETDA controller gains, a feasible mode-dependent ETDA control scheme with a tractable linear programming (LP) approach is presented for PISSs. Further, the provided ETDA control scheme can degenerate into three exceptional cases: event-triggered decentralized synchronous (ETDS) control, time-triggered decentralized asynchronous (TTDA) control, and time-triggered decentralized synchronous (TTDS) control. Finally, comparisons are conducted to exemplify the significance and feasibility of the designed control scheme.

Abstract:
This article is concerned with the human behavior identification problem for linear human-in-the-loop (HiTL) systems in adversarial environments. By modeling the human as an optimal controller that minimizes his/her individual cost function and the adversarial environment as an opponent to maximize the cost function, the HiTL system is formulated as a linear-quadratic zero-sum differential game that consists of two players that are the human and adversarial environment. Then, the human behavior identification is transformed to an inverse reinforcement learning (IRL) problem. Accordingly, the main works carried out in this article can be summarized as follows: 1) an integral concurrent learning (ICL) law is proposed to estimate the feedback matrix of the human and 2) based on the estimated feedback matrix, the weighting matrices in human cost function are retrieved by minimizing a residual. The main focus of the developed human behavior identification method is to remove the persisting excitation constraint and the demand for measuring the control input of humans that are universally required in existing online learning approaches. Finally, the results of simulation and experiment on the lane keeping scenario of a vehicle verify the validity of the proposed adaptive-IRL-based human behavior identification strategy.

Abstract:
This article introduces a novel integration of deep model-based learning with modular state-based Stackelberg games (Mod-SbSG) for distributed self-optimization in manufacturing systems, using a sample-efficient approach. Model-free Mod-SbSG requires frequent interactions with real systems to find optimal solutions, which can be costly, time-consuming, and risky in industrial settings. Prior studies handled this by using digital representations to train Mod-SbSG players, but accurate representations are often difficult to develop. Hence, our framework replaces digital representations with deep learning methods that learn system dynamics, optimize policies within Mod-SbSG, and reduce real-world interactions. The method includes two main steps: 1) designing deep learning models to predict system dynamics and 2) training Mod-SbSG players in virtual environments. We evaluate single- and multistep predictors and demonstrate network reuse for transfer learning in adaptable systems, which reduces real system interactions by 77.78% in a laboratory testbed industrial control scenario.

Abstract:
This study explores the progression of artificial intelligence (AI) systems through the lens of complexity theory, challenging conventional linear projections of advancement toward artificial general intelligence (AGI). We posit the existence of critical points, akin to phase transitions, where increasing system complexity may not lead to greater capability, but rather to performance plateaus or instability. To investigate this hypothesis, we used agent-based modelling (ABM) to simulate the evolution of AI systems, using evaluation benchmark performances as a proxy for complexity. Our simulations modeled the possible characteristics that systems could exhibit when crossing a critical threshold, transitioning from predictable improvement to a regime of erratic, volatile behavior. Practically, we introduced and validated a methodology for detecting these simulated critical transitions algorithmically. We proposed a heuristic Stochastic Gradient Descent-based approach and compared it with established CUmulative SUM (CUSUM) and Lyapunov exponent techniques, to show that different signatures of instability—from abrupt shifts to gradual volatility ramps—can be identified. We contextualized these findings with real-world phenomena, arguing that the empirically observed —“Jagged Capability Frontier” in large language models (LLMs) illustrates the kind of nonlinear performance boundaries that could be sharply accentuated by the onset of criticality. This research contributes not only a novel theoretical framework for understanding potential limits to AI scaling but also a practical, validated methodology for monitoring the systemic stability of AI systems, offering a new dimension to AGI evaluation and safety.

Abstract:
In this article, we address the error estimation problem of quasi-synchronization for a class of multilayer dynamical networks. The proposed network model simultaneously accounts for interlayer and intralayer time-varying coupling structures, network directionality, and interlayer communication delays. To achieve synchronization in a cost-effective manner, we design a novel pinning impulsive control strategy that leverages large-scale impulse delay information together with the number of pinned nodes. By employing an iterative algorithm, we establish a new delay-dependent impulsive differential inequality, which precisely characterizes the convergence domain and provides flexibility in the choice of impulse delays. Then, some quasi-synchronization criteria are derived to guarantee convergence of multilayer networks within a prescribed error level, and explicit analytical expressions for the synchronization error bounds are obtained. Finally, to demonstrate the practical applicability, the proposed criteria are applied to the synchronization of multilayer single-link robot arm networks under error bounds, with numerical examples validating the effectiveness of the method.

Abstract:
As typical and complex mechatronic system, health state of the wind turbine (WT) is of significant importance to the sustained and reliable service. However, it is noted that influenced by the seasonal or fitful wind, WTs unavoidably serve in the dynamically varying environment. In this event, most of the currently available indicators expose deficiency in regard of the false or missed alarms due to the coupled condition interference. To address this issue and improve the reliability of the mechatronic system, a novel statistic discrepancy oriented cyclo-non-stationary (CNS) indicator is developed in this article. First, characteristics of the recorded degradation samples are revealed by a multiparametric model, during which the consistency is verified and improved by the hypothesis test. Second, a specific speed-dependent slicing (SDS) operator is then designed, aiming to alleviate the varying-speed-induced modulation interference at the different degradation stages. With this developed SDS operator, a CNS indicator, which can well adapt to the dynamically varying environment during the operating process, is subsequently developed by incorporating the resampling-based statistic discrepancy evaluating mechanism. Experiments indicate that the proposed method can effectively characterize the health state of the transmission parts of the industrial WT under varying speed conditions.

Abstract:
This article investigates the robust nonfragile leaderless consensus control issues of nonlinear multiagent systems (MASs) in the presence of controller gain perturbations, external interferences, and switching directed networks. A novel distributed nonfragile consensus controller is first devised. Subsequently, on the basis of the property that an MAS directed network’s Laplacian matrix can be broken down into the product of two particular matrices, the conversion from the consensus control issue to the asymptotic stability control issue is achieved via two variable substitutions related to the above property. Additionally, a sufficient condition, which can guarantee the MASs’ asymptotic stability, is proposed and proved by Lyapunov stability theory and algebraic graph theory. Finally, the validity of the devised method is demonstrated by a simulation example.

Affiliations: Key Laboratory of Intelligent Computing and Signal Processing (Ministry of Education), School of Electronic Information Engineering, and the Anhui Engineering Laboratory of Human–Robot Integration System and Intelligent Equipment, School of Electrical Engineering and Automation, Anhui University, Hefei, China; Anhui Engineering Laboratory of Human–Robot Integration System and Intelligent Equipment, School of Electrical Engineering and Automation, and the Key Laboratory of Intelligent Computing and Signal Processing (Ministry of Education), School of Electrical Engineering and Automation, Anhui University, Hefei, China; State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, School of Electrical Engineering and Automation, and the Anhui Engineering Laboratory of Human–Robot Integration System and Intelligent Equipment, School of Electrical Engineering and Automation, Anhui University, Hefei, China; Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Institute of Automation, Jiangnan University, Wuxi, China; School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Perth, WA, Australia; Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, School of Artificial Intelligence, Anhui University, Hefei, China

Abstract:
This article is concerned with the asynchronous H_\infty control design based on model-free policy iteration (PI) algorithm for a class of discrete-time hidden Markov jump system, where a hidden Markov model is developed to characterize the asynchronous phenomenon between the controller modes and the system modes. A pair of zero-sum asynchronous control and disturbance strategies are constructed to achieve a tradeoff between value function and control performance. The presented approach shows two pivotal aspects: 1) the asynchronous PI algorithm is not dependent on strict temporal alignment between the controller and the system’s dynamics, enhancing flexibility of the control scheme and 2) it relies on the collected data to solve the algebraic Reccati equation iteratively, which avoids the need for system-internal and transfer probability information, and circumvents the interference of coupled terms. Subsequently, it is verified that the designed PI algorithm monotonically converges to an optimal solution and the system based on this optimal solution is stochastically stable in the mean-square sense. Finally, the effectiveness of this approach is validated by conducting a simulation experiment on a DC motor device system.

Abstract:
This article addresses the event-triggered consensus tracking control problem for complex heterogeneous multiagent systems with multiple unknown. The systems under consideration involve fully unknown time-varying control directions (CDs), unknown time-varying input delays (UTVDs) and functions, making the problem particularly challenging. To reduce the effects of UTVDs, an auxiliary system is constructed to produce a compensation signal. Building upon this, a novel adaptive proportional-integral (PI) control approach is developed through the backstepping method and a series of Nussbaum functions. It is demonstrated that the tracking error can meet predefined transient and steady-state performance criteria, ensuring asymptotic tracking and global boundedness of all signals in the closed-loop system. The key advantage of this solution lies in its simplicity of controller design and improved control performance, without requiring prior information about the unknown functions. Finally, a simulation example validates the validity of the proposed approach.

Abstract:
Recent efforts have yielded substantial progress in backstepping platoon control for connected and automated vehicles (CAVs). While most existing studies focus on guaranteeing individual vehicle stability and string stability, their deployment in nonlinear vehicle platoons may face challenges from the so-called “butterfly effect.” That is, even with guaranteed string stability, potential instantaneous spacing changes may imply unpredictable, uncomfortable fluctuations in vehicular velocity and acceleration. To address this issue, a parallel error-fluctuation suppression control framework is proposed in this work. Specifically, tunable triple-layered error boundaries (i.e., spacing, velocity, and acceleration) are constructed to reactively confine all propagated errors within predefined envelopes. By integrating a Barbalat-lemma-enhanced filtering-compensating mechanism and an adaptive approach based on the approximation capability of radial basis function neural networks (RBFNNs), asymptotic error tracking is realized to proactively suppress potential fluctuations. An adaptive backstepping control approach—integrating proactive and reactive suppression strategies—is then proposed to mitigate the unquantifiable “butterfly effect.” Theoretical analysis and simulations demonstrate the validity and superiority of the proposed approach.

Abstract:
For the frequency regulation and power allocation problem for ac microgrids, the multiple constraints of load frequency restrictions, nodal active power injections, and power-flow balance that guarantee transient stability are as crucial as the final consistent steady-state results. This article investigates a class of droop-controlled ac microgrids with the abovementioned constraints, and it presents sufficient and necessary conditions to improve system robustness and reliability under load fluctuations. By integrating the Kuramoto oscillator model into the primary control law, cyber-physical coupling dynamics for ac microgrids are established. A novel communication-network-based secondary distributed control approach is presented, which considers physical nodes with different characteristics of power generation and load units. By using invariant theory and nonquadratic Lyapunov techniques, the bounded input–output stability of microgrids can be guaranteed under certain conditions, which is especially pertinent in active power allocation. The theoretical results are verified through numerical case studies of both public and self-built power test systems, demonstrating the obvious improvement in robustness and reliability against variable power generation and load demand.

Abstract:
Role-based collaboration (RBC) has become a crucial computational approach for task allocation and team coordination, yet three critical research gaps remain unresolved. First, while existing methods treat role importance uniformly, real-world scenarios require differentiated prioritization of roles, which is a gap addressed through role weight vectors that dynamically adjust task significance. Second, current qualification matrices that directly specify agent capabilities lack mechanisms to handle assessment uncertainties, leading this article to propose a novel determination method using intuitionistic fuzzy numbers for robust capability modeling. Third, the absence of systematic conflict categorization frameworks motivates our three-way conflict analysis (TWCA) method that classifies conflicts through hierarchical comparisons of agent competency. Drawing from these considerations, the article presents the weighted group role assignment (GRA) with conflicting constraints problem, aiming to overcome the identified challenges through environments—classes, agents, roles, groups, and objects (E-CARGO) framework. The proposed approach is tested and validated through a series of experiments and comparative analyses to demonstrate its efficacy.

Abstract:
Flexible and efficient wide-load tracking in coal-fired power generation systems (CPGSs) is crucial for integrating renewable energy. To address the challenges arising from the dynamic characteristics and task distribution differences during the wide-load operation of thermal power units, this article proposes a novel hierarchical model-agnostic meta reinforcement learning (HMAMRL) framework. This framework combines inner meta-learning for quick adaptation within task categories and outer meta-learning for sharing general task knowledge, ensuring robust generalization under different load conditions. Meanwhile, an adaptive multicriterion reward function design method is proposed to dynamically balance load tracking costs, coal consumption costs, and input fluctuation costs. Moreover, a truncated proximal policy optimization (TPPO) algorithm ensures precise load control within physical constraints. Experimental results on the 160 and 1000 MW CPGSs demonstrate the effectiveness and superiority of the proposed algorithm.

Affiliations: School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, China; State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangdong University of Technology, Guangzhou, China; Shien-Ming Wu School of Intelligent Engineering, South China University of Technology, Guangzhou, China; Department of Systems Engineering, City University of Hong Kong, Hong Kong, China; School of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology, Hong Kong, China

Abstract:
In mechanical fault diagnosis (MFD), intelligent fault diagnosis (IFD) methods perform excellently regarding diagnosis accuracy. However, those methods are generally constructed with an excessive number of unprincipled parameters, resulting in uninterpretable architecture, ambiguity in the diagnosis process, and unclear decision-making basis. Thus, a traceable algorithm unrolling (TAU) network for interpretable MFD is proposed to overcome the above limitations. First, a mechanism-driven feature extractor (FE) is constructed by unrolling the iterative algorithm of sparse coding, aiming at encoding interpretable features from vibration signals. Second, a theory-based feature clustering (FC) algorithm is executed through the dynamic routing mechanism of the capsule network (CN), where the inner product serves as a measure for the association between input and output features. Finally, a post hoc interpretability strategy based on the coupling matrix is introduced to investigate how the TAU generates diagnostic results from the learned features and to verify whether these features are associated with faults, thereby enhancing the credibility of the diagnosis results. In addition, the simulation and experiment are designed to verify the decision-making mechanism and diagnostic performance of TAU. The results demonstrate that TAU makes diagnostic decisions based on the high-dimensional feature mapping associated with fault characteristic frequencies. Meanwhile, TAU outperforms the compared methods in fault diagnosis performance.

Abstract:
Task allocation in multiagent systems is a critical challenge due to the heterogeneity of tasks and agents, where tasks have varying resource requirements and agents possess differing resource supplies. During execution, agents’ resources deplete while tasks’ requirements dynamically decrease. This problem has broad applications, such as optimally deploying UAVs equipped with diverse medical supplies in disaster rescue scenarios to minimize casualties. To address this, this article proposes a coalition formation game model, formulated as a potential game. We theoretically prove the submodularity of both the coalition utility function and the global utility function. Based on this submodularity, we establish that the efficiency lower bound of any Nash equilibrium in the proposed game model is given by e / (2e-1) , significantly outperforming the 50% bound reported in prior studies. Furthermore, we introduce an inertia-based log-linear learning algorithm enhanced with a multiagent cooperative exchange mechanism, which enables the system to escape from suboptimal equilibria and improve global utility. In addition, we extend the algorithm to accommodate local communication constraints and dynamic allocation scenarios. Extensive experimental evaluations demonstrate that our proposed method achieves superior performance across diverse scenarios compared to existing algorithms.

Abstract:
In multiagent coordination tasks, motion trajectories are required to satisfy a range of constraints that present significant implementation challenges due to the limited onboard sensing and communication capacities. This article introduces distributed control laws that integrate nonholonomic motion constraints into bearing-based designs to enable time-varying formation tracking with minimal onboard resources. Unlike state-of-the-art formation control solutions, this approach maintains formation shape through relative bearing feedback and orientation alignment rather than tracking global target locations or regulating interagent relative positions and velocities. This distributed controller design has been validated in two deployment scenarios: 1) leaderless nonhierarchical formations and 2) leader–follower hierarchical formations. In hierarchical formations, follower agents employ a speed estimator within the orientation alignment framework to reach velocity consensus with the leader agent. The proposed controllers guarantee accurate tracking of time-varying reference trajectories, preserve the desired formation structures, and achieve velocity consensus for both nonhierarchical and hierarchical formations, as established by analysis and validated through simulations and experiments.

Abstract:
This article studies the stealthy attack design problem on cyber–physical systems (cyber–physical system), where the ( \epsilon , \delta )-stealthiness, a more fine-grained quantification of the attack stealthiness, is considered. Under the ( \epsilon , \delta )-stealthy constraint, the optimization problem is nonconvex. By analysing the relationship between the two stealthy parameters, the nonconvex problem is transformed into the one with only equality constraints, which can be solved directly in one step with more simplified solution process. Furthermore, a general linear attack model is considered, and the optimal attack strategy is given analytically, which achieves greater attack performance but under a more stealthy level than the existing results. In addition, the constraint that the output matrix needs to have full rank rows in the existing works has been removed, and the completely analytical forms of the optimal attack parameters rather than numerical forms are presented. Finally, numerical simulations are given to show the effectiveness of the method and comparison results.

Abstract:
This article focuses on the prescribed-time full-state consensus control of feedforward multiagent systems (MASs), and a new framework and analysis are presented. First, to deal with the obstacle arising from inherent feedforward nonlinearity, a crucial aspect of the design is to creatively construct the coordinate transformation at each step and the prescribed-time function as a scaling factor. Subsequently, a novel prescribed-time homogeneous domination framework for feedforward MASs is developed. The significant advantage is that this framework combines the low complexity of homogeneous domination control method design with the simplicity of stability analysis for state-scale schemes. Then, based on the recursive techniques, a distributed prescribed-time full-state consensus controller is designed, which drives the consensus errors to reach equilibrium at any prescribed time and ensures the stability of the entire time interval. Finally, the proposed algorithm is validated through the liquid-level control resonant circuit (LLCRC) system.

Abstract:
The rapid deployment of advanced metering infrastructure facilitates the development of data-driven attack detection methods in smart grids, which typically rely on large amounts of labeled data for training. However, when new types of attacks or faults emerge, security analysts may only intercept limited malicious samples. The scarcity of samples makes it difficult for data-driven methods to learn effective decision boundaries, leading to degraded detection performance. In this work, we bridge the gap by learning class prototype representations from limited samples and learning to match unlabeled samples with corresponding prototypes. Specifically, we propose a meta-learning-based framework termed Learning to Match Prototype (L2MP), which consists of a prototypical network (ProtoNet) that learns prototype representations by aggregating features from labeled samples, and a matching network that assesses the matching degree between unlabeled samples and prototypes for classification. Through episodic training designed to simulate the few-shot setting, L2MP learns to adapt to novel attack and fault types with only a few samples per class. Moreover, we utilize a bilevel optimization strategy to ensure efficient training of both networks. Extensive case studies on smart grid datasets demonstrate that L2MP achieves robust performance under harsh learning conditions and has practical utility in real-world scenarios.

Abstract:
This article investigates an aggregative game with local closed convex set constraints over time-varying unbalanced communication graphs, and aims to compute the Nash equilibrium (NE) in a distributed manner. To this end, we propose a distributed discrete-time NE seeking algorithm. It combines the average tracking technique and the push-sum protocol to estimate the global aggregate over time-varying unbalanced graphs, and incorporates the method of feasible direction to handle the set constraints. Based on the small gain theorem, we establish the linear convergence of the proposed algorithm and provide explicit estimates for the step-size upper bounds. Finally, numerical simulations of a Nash-Cournot game are given to confirm the effectiveness of our algorithm.

Abstract:
Most research on flexible job shop scheduling assumes constant processing speeds. However, in real production, machines need to operate at variable speeds to achieve energy-efficient scheduling, which requires balancing multiobjective between production efficiency and green development. Such tradeoffs thus trigger the phenomenon in which massive solutions converge to identical objective values (i.e., the multimodal property), which is often neglected in scheduling problems. To address the above challenges, this work introduces a knowledge-enhanced evolutionary multitasking memetic algorithm (KEMMA) to solve the multimodal multiobjective flexible job shop scheduling problem considering speed (MMFJSP-S). First, self-paced learning motivated us to construct a simple auxiliary task and employ an evolutionary multitasking (EMT) framework to tackle the complex MMFJSP-S. Moreover, a knowledge enhancement and explicit transfer strategy is designed to reduce the effects of negative transfer by reinforcing and sharing beneficial knowledge across tasks. Finally, a mapping transformation mechanism is proposed to handle the multimodal property of the MMFJSP-S in the decision space. By comparing with ten advanced algorithms, the experimental results verify the remarkable superiority of the proposed KEMMA in solving MMFJSP-S and reveal the significance of studying the multimodal property.

Abstract:
This article proposes a resilient control framework for securing cyber-physical systems (CPSs), specifically addressing nonlinear descriptor systems operating under communication constraints and subject to sensor and actuator attacks. We integrate Takagi–Sugeno (T–S) fuzzy models with a Q-learning-based event-triggered mechanism (ETM) and adopt a sliding-mode control strategy to establish a resilient security architecture that adaptively balances operational efficiency with robust protection against cyber-physical threats. A major contribution of this work lies in designing an adaptive fuzzy sliding-mode observer (SMO) with mismatched premise variables for the estimation of compromised system states. Additionally, a sliding-mode controller (SMC) is synthesized to maintain closed-loop admissibility and ensure the reachability of sliding surfaces. We advance beyond the existing approaches by employing the secretary bird optimization algorithm (SBOA) to optimize controller and observer gains, thereby solving the nonconvex optimization challenges present in controller and observer design. The effectiveness of the proposed method is validated through extensive Monte Carlo simulations on a truck-trailer system. These simulations demonstrate the efficacy of the approach in maintaining system stability and performance under various attack scenarios, thereby making a significant contribution to the security of nonlinear systems in networked environments.

Abstract:
This research endeavors to design the perching maneuver and control in ornithopter robots. By analyzing the dynamic interplay between the robot’s flight dynamics, feedback loops, and the environmental constraints, we aim to advance our understanding of the perching maneuver, drawing parallels to biological systems. Inspired by the elegant control strategies observed in avian flight, we develop an optimal maneuver and a corresponding controller to achieve stable perching. The maneuver consists of a deceleration and a rapid pitch-up (vertical turn), which arises from analytically solving the optimization problem of minimal velocity at perch, subject to kinematic and dynamic constraints. The controller for the flapping frequency and tail symmetric deflection is nonlinear and adaptive, ensuring robustly stable perching. Indeed, such adaptive behavior in a sense incorporates homeostatic principles of cybernetics into the control system, enhancing the robot’s ability to adapt to unexpected disturbances and maintain a stable posture during the perching maneuver. The resulting autonomous perching maneuvers—closed-loop descent and turn—have been verified and validated, demonstrating excellent agreement with real bird perching trajectories reported in the literature. These findings lay the theoretical groundwork for the development of future prototypes that better imitate the skillful perching maneuvers of birds.

Abstract:
Accurate online detection or prediction of key quality variables provides critical reference information for optimizing and controlling operating variables in industrial processes. However, frequent fluctuations in raw material properties and environmental conditions often give rise to multiple data distribution modes within the same production process. Moreover, the inherent uncertainties and the energy-material coupling characteristics of industrial processes make it particularly challenging to uncover the underlying topological relationships among process variables. To address these issues, this article proposes a novel jointly shared-specific variational graph attention autoencoder (JSS-VGATE) model for spatial topological feature extraction and key quality variable prediction in multimode industrial processes. Specifically, a variational graph attention autoencoder is first constructed, which combines graph attention mechanisms with the variational inference architecture to adaptively learn the dynamic correlation strengths between adjacent nodes, thereby capturing complex variable interactions. Subsequently, a comprehensive loss function is designed to achieve high-fidelity extraction of representative latent feature distributions. Furthermore, a cross-mode jointly shared-specific learning framework is developed to simultaneously capture global shared features across modalities and preserve local specific features of each modality, while a learnable gated fusion mechanism is introduced to balance modality invariance and heterogeneity, thereby enhancing cross-mode information integration. Finally, the effectiveness and superiority of the proposed JSS-VGATE are validated on two representative real-world industrial datasets compared to other state-of-the-art methods.

Abstract:
This study investigates the extended dissipativity analysis for uncertain delayed genetic regulatory networks (GRNs) within an interval type-2 (IT2) Takagi–Sugeno (T-S) fuzzy framework. To the best of our knowledge, this is the first attempt to capture the complex dynamics and parameter uncertainties of GRNs via IT2 fuzzy sets, providing a robust representation through lower and upper membership functions. By constructing a novel Lyapunov–Krasovskii (L-K) functional, explicit derivations of the maximum admissible delay bounds are obtained. A unified analytical framework is established to verify \mathcal L_2 – \mathcal L_\infty performance, H_\infty attenuation, passivity, and dissipativity. To further reduce conservatism, a membership-function-dependent (MFD) stability criterion is developed that fully exploits the characteristics of IT2 fuzzy sets. Numerical examples demonstrate that the proposed approach significantly outperforms existing methods in terms of less conservative stability conditions and improved dissipativity indices under uncertainties and delays. This work advances theoretical understanding and practical design of robust control strategies for GRNs, with potential applications in synthetic biology.

Abstract:
This article investigates the adaptive tracking control strategy for a class of nonlinear systems subjected to false data injection (FDI) attacks, incorporating an improved event-triggered mechanism. A significant breakthrough of this study lies in the challenge that, after FDI, not all states of the system can be utilized for stability design, thereby making it more complicated to achieve tracking control. This article eliminates the restrictive assumption, required in some existing results, that the attack signal at the first step must be known. Instead, we propose to estimate the tracking error directly. This approach not only facilitates the tracking control of nonlinear systems but also enhances the generalizability and practical applicability of the solution. To conserve system resources, an improved event-triggered condition is proposed that utilizes the triggered attacked-output. Consequently, the controllers and adaptive laws are implemented using the sampled states rather than continuous real-time states, thereby minimizing unnecessary computations and communications. By constructing Lyapunov functions, the proposed control strategy ensures that all signals in the closed-loop system are globally bounded. Finally, the simulation results are displayed to validate the effectiveness of the proposed control strategy.

Abstract:
This article proposes a distributed Lagrange alternating gradient descent (LAGD) algorithm with a fixed step size for constrained optimization over a multiagent communication network. Interconnected by multiagent networks, agents optimize their own objective function subject to local constraints cooperatively, and the whole network shares globally coupled constraints. All agents reach consensus on the estimations of multipliers via the network communication to handle the globally coupled constraints, and the decision variable vectors converge to the optimal solution along the Lagrange gradient direction. The convergence of the algorithm is proven under the condition of fixed step sizes subject to a theoretical upper bound. An economic dispatch problem in a power system and a numerical example are elaborated to verify and demonstrate the effectiveness of the algorithm.

Affiliations: School of Mathematics, China University of Mining and Technology, Xuzhou, China; School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China; School of Information Science and Technology, East China University of Science and Technology, Shanghai, China; College of Electrical Engineering and Control Science, Nanjing Technology University, Nanjing, China; School of Computer Science and Technology, Jiangsu Normal University, Xuzhou, China; Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology at Sydney, Sydney, NSW, Australia

Abstract:
This article investigates the mean square exponential stability for dynamic memristor-neutral stochastic cellular neural networks with time-varying delays (DM-NSDCNNs). Unlike general neural networks (NNs) analyzed in the voltage–current domain, DM-NSDCNNs are studied in the flux-charge domain, offering a significant advantage: all current, voltage, and power consumption vanish when the system reaches a steady state. In particular, dynamic memristor store the results of computation. To better utilize these properties, two distinct stochastic stability analysis techniques are considered, depending on the memristor’s constitutive relations. For piecewise linear constitutive relation, the stability criteria are obtained by a novel approach based on the comparison principle and reductio ad absurdum. Moreover, the stability criteria for cubic nonlinear constitutive relation are established via stochastic analysis employing Lyapunov functional techniques. Finally, several numerical examples with different constitutive relations of DM-NSDCNNs are provided to verify the effectiveness and potential of the proposed results.

Abstract:
Balancing optimality and robustness is the key to solving expensive robust multiobjective optimization problems (ExRMOPs) by evolutionary algorithms. However, existing studies usually design algorithms based on either the average perspective or the worst perspective, overlooking the complementarity of these two perspectives—the former prefers optimality, whereas the latter prefers robustness. Therefore, this article proposes a Kriging-assisted evolutionary algorithm with dual perspectives and dual indicators (called KPI) to solve ExRMOPs. In KPI, we develop a dual-perspective aggregation function (DPAF) as the replaced objective to guide the evolutionary search. Specifically, in terms of each original objective, DPAF of each solution is defined as the weighted sum of the performance evaluated from the average perspective and the worst perspective. The weight used in DPAF is related to the stability level of the current population, enabling DPAF to adaptively balance optimality and robustness. In addition, we design a dual-indicator candidate selection strategy to identify high-quality candidates from the final population of the evolutionary search for expensive function evaluations. In this strategy, we first eliminate solutions with poor robust optimality by the proposed robust optimality indicator. Subsequently, based on the robust optimality indicator and a common diversity indicator, several solutions with good robust optimality and diversity are selected as candidates from the remaining solutions. Extensive experiments on two test suites and a real-world application verify the superiority of KPI.

Abstract:
In this article, the encoding-decoding-based state estimation problem is investigated for a class of continuous-time nonlinear complex networks (CNs) subject to communication bandwidth constraints. Based on the sampled outputs from a subset of network nodes, a novel dynamic event-driven encoding mechanism is integrated into the design of state estimator, where a time-varying auxiliary parameter is utilized to modulate the triggering condition in a dynamical fashion, enabling the event detector to decide whether the data packet should be released at the periodic sampling instants. Specifically, when the dynamic triggering condition is satisfied, the data are first encoded into a codeword and subsequently transmitted to the estimator through a digital communication channel. The Zeno behavior can be naturally prevented due to the periodic feature of the proposed event detector. By leveraging the Lyapunov theory and the matrix inequality techniques, sufficient conditions are established to ensure the exponential stability of the estimation error system. In addition, a convex optimization approach is employed to design the estimator gain with the goal of maximizing the allowable bound of the sampling intervals. Finally, an illustrative example and a practical example involving a three-area power system are provided to showcase the effectiveness of the proposed state estimation method.

Abstract:
With the improvement of data collection capabilities and the increase in data volume, multiview multilabel feature selection has gained widespread attention. In multiview multilabel feature selection, it is inevitable to consider both the consistency and complementarity information between views. However, many existing methods tend to independently extract consensus and complementary information, and this fragmented approach often leads to ambiguity in the information partitioning, which in turn generates noise. Furthermore, existing methods do not consider the correlation between views and labels when estimating the effectiveness of different views, which can affect the accuracy of view weights. To address these issues, we propose a multiview multilabel feature selection method that integrates a noise-resistant strategy with fuzzy mutual information for jointly learning commonality and individuality label structures. Specifically, first, we learn the commonality label matrix using nonnegative matrix factorization to explore the consistency between views. This matrix not only captures shared patterns across views but also helps the model better fit the ground-truth labels. Second, we learn individuality label matrices to capture the complementary information of each view, and introduce view noise label matrices to mitigate the impact of inherent noise in the true labels and noise labels generated by partitioning. Third, we incorporate view weights based on fuzzy mutual information, which can accurately reflect the correlation between views and labels to enhance important views while reducing the contribution of noise. Finally, we design a sparse model-based multiview multilabel feature selection method and provide theoretical proof of its convergence. Extensive experiments on multiple benchmark datasets are conducted to demonstrate the effectiveness of our approach.

Affiliations: College of Mechatronics and Control Engineering and the College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China; Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada; Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen, China; College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, China

Abstract:
This study investigates the mean-square reachable set (RS) consensus of nonlinear Markov-switched multiagent systems (MASs) with time-varying delays, in which a multirate sampled-data consensus (MRSDC) control scheme is designed for the first time under general uncertain semi-Markov transition (GUST) switched topologies. First, the nonlinear Markov-switched MAS is transformed into quasilinear subsystems by applying the Takagi–Sugeno (T–S) fuzzy modeling technique, where the GUST-based Markov model characterizes both the operation mode and abrupt variations in the communication network topologies among all agents. Second, an aperiodic MRSDC control strategy is developed to reduce the sampling frequency of certain sensors below the single-rate threshold by adaptively adjusting their sampling rates, thereby enhancing flexibility and improving consensus performance. Furthermore, a new free-weighting integral inequality is introduced to handle the integral quadratic term involving time-varying delay bounds. Subsequently, an appropriate looped-side Lyapunov functional is designed, leveraging aperiodic multirate sampling and time-varying delay characteristics. Next, by combining the constructed Lyapunov functional with the proposed integral inequality and an improved reciprocally convex combination inequality, sufficient conditions are derived in the form of linear matrix inequalities (LMIs). These conditions not only ensure the mean-square leaderless consensus of the resulting MASs but also guarantee that all reachable states remain confined within ellipsoidal attracting-like regions under the MRSDC scheme. Finally, numerical validations are conducted to demonstrate the effectiveness of the proposed MRSDC control strategies using interconnected single-link robot arm systems (SLRASs), while a comparative numerical example further illustrates the superiority of the proposed method.

Abstract:
This article addresses the fundamental issues of solvability and normalization in singular Boolean networks (SBNs) from a new perspective based on the admissible and normal initial state sets. It presents novel results and removes the restrictive conditions found in existing literature. First, the state transition matrix of SBNs is constructed by defining a new operator, and the admissible initial state set with the normal initial state set, of SBNs is introduced. Second, the problems of the solvability and uniqueness of the solution to a general SBN are converted into computing its admissible and normal initial state sets, which can be analytically computed using the derived formulas. Third, based on the normal initial state set, a necessary and sufficient condition for solving the normalization problem of general SBNs is established for the first time, which removes the restrictions in the existing literature. Finally, the results obtained are compared with existing literature and illustrated with examples.

Affiliations: College of Control Science and Engineering, Bohai University, Jinzhou, China; National Research Base of Intelligent Manufacturing Service and the Chongqing Engineering Laboratory for Detection Control and Integrated Systems, Chongqing Technology and Business University, Chongqing, China; Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China; Antal Bejczy Center for Intelligent Robotics, University Research, Innovation and Service Center, Óbuda University, Budapest, Hungary

Abstract:
This article investigates the issue of composite anti-disturbance and attack control for networked systems under unknown actuator attacks and external disturbances. First, a double-ended event-triggering mechanism is designed to reduce unnecessary data transmission in the feedforward and feedback channels. Second, an augmented observer is designed to estimate the system states and disturbances. The intermittent estimation signal is then used to compensate for external disturbances through a novel trigger sampling mechanism. Third, the fuzzy logic system is used to approximate the unknown attack signal, and an adaptive output feedback controller is employed to mitigate its impact on the system. Based on these three key techniques, a novel functional dependent on the sampling instants is constructed to analyze semi-global uniform ultimate boundedness of the closed-loop system and obtain the criterion condition of low conservatism. Additionally, the event-triggering matrix and gains are explicitly solved by matrix transformation. Finally, the feasibility and effectiveness of the proposed method are validated via a visual servo control system and a third-order system.

Abstract:
Lung cancer, with high morbidity and mortality rates, requires tailored treatment based on pathological subtypes, clinical staging, and individual performance scores. multidisciplinary treatment (MDT) is supposed to improve patient prognosis, making the treatment generation process a multiattribute multiexpert decision-making (MAMEDM) problem. Traditional MAMEDM models often necessitate experts with differing opinions to conform to group consensus, neglecting experts’ willingness to adjust opinions. To address this issue, this study proposes an MAMEDM framework which can maximize experts’ willingness for opinion transformation. Initially, a linguistic scale function is used to preprocess linguistic evaluations. A fuzzy clustering algorithm is introduced to cluster experts. The weights of subgroups are determined based on the network centrality and the professional titles of experts. Expert opinions within subgroups are aggregated based on the principle of maximizing the willingness of experts for opinion transformation, and then the ORESTE method is implemented to rank treatment options. A case study on lung cancer treatment option generation demonstrates the effectiveness of the proposed framework. Results show that considering experts’ willingness to revise evaluations significantly enhances decision acceptance and reduces the impact of noncooperative behaviors.

Abstract:
Selecting targets to attack and assigning weapons are among the most critical decisions on the battlefield. The decision problem is represented as a dynamic weapon-target assignment (DWTA) problem. While deep reinforcement learning (DRL) is the state-of-the-art approach for DWTA, previous studies have limitations in three key aspects: 1) representing topological relationships on the battlefield; 2) scalability to increased problem sizes; and 3) performance metric relevance. To overcome these limitations, this study aims to solve the DWTA problem by leveraging DRL and graph neural networks (GNNs), with a novel partially observable Markov decision process (POMDP) design, including graph-based action representation, observation features, and reward design. Experiments are conducted across multiple military domains, including naval and ground combat, comparing the proposed approach with existing heuristic and meta-heuristic methodologies. The effectiveness of the GNN and decision-making pattern is extensively analyzed through comprehensive experimental validation.

Abstract:
Semi-supervised learning (SSL) has gained significant attention in the domain of sea state estimation (SSE) due to its capacity to alleviate the reliance of deep learning models on extensive labeled datasets. While existing semi-supervised SSE methodologies leveraging pseudo-labeling have achieved promising results, they often overlook the challenges posed by high class imbalance and the prevalence of missing data in ship motion datasets, which restricts their broader applicability. In this article, we propose a novel SSL approach BalanceSSE based on the class-imbalanced ship motion data for SSE. This approach consists of three main modules: 1) the dynamic imputation (DIT); 2) the imbalance temporal-frequency learning (ITFL); and 3) the ClusterProx classifier (CL). The DIT module dynamically imputes incomplete ship motion data by assigning different weights to various dimensions data. The ITFL module employs time-frequency collaborative learning to generate pseudo-labels and integrate an adaptive confidence strategy to select high confidence pseudo-labels. This process is further enhanced by the CL module to produce better estimates. Experimental tests on UCR datasets and ship motion datasets demonstrate that BalanceSSE outperforms state-of-the-art methods. Ablation studies highlight the critical role of each module in BalanceSSE.

Affiliations: Department of Mathematics, College of Engineering and Technology, SRM Institute of Science and Technology, Chennai, India; College of Mechatronics and Control Engineering and the College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China; College of Mechatronics and Control Engineering and the National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China; School of Mathematics and Statistics, Hunan Normal University, Changsha, China; Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen, China

Abstract:
This work reports design problem of the memory sampled-data (SD) controller for interval type-2 fuzzy singular systems (SSs) with external disturbances. First, an improved free-weighting matrix inequality is introduced for concerning fuzzy SSs to reduce conservatism of the integral terms. Then, a novel looped-functional-based Lyapunov–Krasovskii functional (LKF) is constructed that incorporates the data from sampling interval \mathbf z(t) to \mathbf z(t_k) . With the help of improved integral inequality and novel LKF, a new set of admissibility conditions is developed in the form of linear matrix inequalities (LMIs). The developed criteria based on the memory SD controller ensure that the proposed systems is admissible with an H_\infty attenuation level. Finally, numerical simulations are given to illustrate the usefulness and benefit of the proposed methods.

Abstract:
The process industry is a continuous manufacturing system that comprises intricate physical and chemical reactions. Given the increasing constraints on resources and energy, it is urgent to optimize process indicators by maintaining an efficient reaction atmosphere. Reinforcement learning (RL), using trial and error to learn control strategies, has become a topic of interest in the control community. However, practical implementation reveals that the mapping between observed state variables and the reaction atmosphere is subject to uncertain disturbances, which seriously affect the reliability of process indicator control. To address these issues, a robust RL (RRL) control method based on knowledge-constrained adversarial perturbation is proposed. It applies the adversary to perturb the observed state to characterize the uncertain disturbance. First, the insight of composite modeling for the process industry is presented to factorize the inherent and external uncertainties. Based on this insight, a reaction atmosphere indicator surrogate model is built to quantify the inherent uncertainty. Second, by leveraging the variation boundary information of the surrogate model, a dynamic state perturbation set and its update policy are proposed to ensure the rationality of the state perturbation. Last, an external uncertain time series generation method with continuity constraints is proposed to incorporate reasonable external uncertainty in the training process. Case validation in zinc electrowinning demonstrates that the proposed method effectively enhances control performance in uncertain scenarios.

Affiliations: College of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China; School of Electrical Engineering, Southeast University, Nanjing, China; School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China; Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China; College of Electrical and Electronic Engineering, Wenzhou University, Wenzhou, China; Department of Electrical and Electronic Engineering, Imperial College London, London, U.K.

Abstract:
Deep reinforcement learning (DRL)-based volt-var control (VVC) in active distribution networks (ADNs) is prone to cyberattacks; malicious attackers can design adversarial attacks to tamper with the real-time measurements and bypass the bad data detection (BDD) mechanism, causing voltage limit violations. Previous work in this area predominantly focuses on designing suitable attack vectors, assuming unlimited attacker resources and neglecting the BDD mechanism. To this end, a new objective as a function of attack timing is designed to maximize the frequency of voltage violation of ADNs with the fewest number of attacks. Furthermore, perturbation set transformation is implemented on the attack vectors to bypass the BDD, ensuring the stealthiness of the attack. For solving the attack optimization with complex constraints, this article reformulates the adversarial attack on DRL-based VVC agents as a hybrid-action state-adversarial Markov decision process (MDP) and proposes a novel knowledge transferred DRL-based adversary to launch strategically timed (when) and stealthy (how) adversarial attacks. Case studies are conducted to verify that the strategically timed adversarial samples generated by the adversary significantly impact the voltage regulation capability of VVC agents while ensuring stealthiness against the BDD mechanism, through benchmarking against existing baseline adversarial attack methods.

Abstract:
In this article, a robust adaptive tracking control scheme is developed for fully actuated systems (FASs) in the presence of nonlinear uncertainties, input disturbances, and multiplicative input matrices perturbation, capable of achieving the adjustable transient and steady-state performance. In comparison with the conventional and finite-time prescribed performance control (PPC) methods subject to the initial value constraint, the proposed prescribed-time PPC scheme blends the FAS approach with the speed transformation, guaranteeing the full-state asymptotic tracking with prescribed-time prescribed performance. First, a basic fully actuated controller is introduced, yielding a closed-loop tracking error system with a linear dominant part. Second, the speed transformation is applied to the closed-loop system, converting the initial PPC problem into the asymptotic convergence problem of the transferred error system and completely eliminating the initial value constraint. Third, the auxiliary control input and adaptive law embedded with positive integrable time-varying functions are devised, ensuring the boundedness of all closed-loop signals and the desired performance. Simulation studies are conducted to demonstrate the effectiveness and superiority of the presented control strategy.

Affiliations: State Key Laboratory of Synthetical Automation for Process Industries and the College of Information Science and Engineering, Northeastern University, Shenyang, China; State Key Laboratory of Synthetical Automation for Process Industries and the Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China; State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China; School of Control Science and Engineering, Dalian University of Technology, Dalian, China

Abstract:
This article investigates the event-triggered anti-disturbance control for multiagent systems (MASs) subjected to multiple disturbances and time-varying transmission delays (TDs). Unlike existing studies that only consider the abrupt changes in parameters or communication topologies, this work employs the dual-Markov jumping processes with a switching signal to describe stochastic behaviors based on a novel mapping technique. The dynamic event-triggered protocol (DETP) is established to reduce communication burdens by incorporating a packet loss schedule (PLS). Additionally, the composite anti-disturbance controllers are developed based on disturbance observers (DOs) and extended dissipative performance analysis. By employing Lyapunov–Krasovskii functional (LKF) and the Finsler lemma, the stabilization conditions of the switched dual-Markov jumping MAS (SDMJMAS) are derived. Finally, the effectiveness of the proposed methods is validated through comparative experiments.

Abstract:
Rotating machinery often operates under varying working conditions, which poses significant challenges to achieving reliable bearing fault diagnosis using traditional deep learning-based models. To enhance the diagnostic performance for rolling bearings across diverse operational conditions and noisy environments, a data-selective multiscale dual transfer network (DSMDTN) with a data selector (DS), multiscale concatenation U-Net (MCU-Net), and dual classifier (DC) is proposed. The DS module employs a comprehensive scoring mechanism that integrates math, entropy, and anomaly scores to selectively identify high-quality source samples for model training. Meanwhile, the MCU-Net module incorporates gated convolutional (gated-conv) blocks and convolutional blocks to extract multiscale domain-invariant features and dynamically adjust feature importance. In addition, the DC module comprises separate source and target classifiers that jointly minimize distribution discrepancy and classification loss. The effectiveness of the proposed DSMDTN is validated through experiments on the public Case Western Reserve University (CWRU) dataset and the proprietary PT dataset collected from a PT500mini test bed. The experimental results demonstrate that DSMDTN achieves higher accuracy and exhibits stronger transfer capability compared to several state-of-the-art intelligent models across various transfer tasks and under different noise levels.

Affiliations: National Research Base of Intelligent Manufacturing Service, Chongqing Technology and Business University, Chongqing, China; School of Mechanical Engineering, Chongqing Technology and Business University, Chongqing, China; College of Control Science and Engineering, Bohai University, Jinzhou, China; Institute of Architecture Engineering, Guangxi City Vocational University, Guangxi, China; Department of Computer Science and AI, Andalusian Research Institute in Data Science and Computational Intelligence, University of Granada, Granada, Spain; Department of Mechanical Engineering, Washington University in St. Louis Campus, St. Louis, MO, USA

Abstract:
This article proposes a novel observer-based adaptive neural network-based resilient consensus control approach to address hybrid cyberattacks, disturbances, and nonlinear dynamics in nonlinear leader-following multiagent systems (MASs). Specifically, a dimension expansion methodology is developed to dynamically model and compensate for false data injection (FDI) attacks, while denial-of-service (DoS) attacks are probabilistically characterized via Bernoulli variables, forming a comprehensive hybrid attack mitigation strategy. Then, a cascaded observer is designed, integrating dimension-extended system modeling with disturbance decoupling to simultaneously estimate system states and external disturbances with high precision. Furthermore, an adaptive neural network-based approximation scheme is employed to handle system nonlinearities, eliminating the conservatism of Lipschitz-based methods while enhancing robustness in complex environments. Finally, the simulation result validates that the proposed control method achieves resilient consensus of leader-following MASs under hybrid cyberattacks, disturbances, and nonlinear dynamics.

Abstract:
This article addresses the problem of prescribed-time fault-tolerant tracking control for a class of nonlinear multiagent systems (MASs) subject to parameter uncertainties and external disturbances. To improve tracking precision, the trajectory reconstruction approach based on cubic spline interpolation is proposed, which effectively reconstructs the discrete reference signals. Then, a class of prescribed-time regulators is meticulously designed to formulate the fault-tolerant tracking controller, ensuring that the outputs of the controlled system converge to the reconstructed trajectory with arbitrary accuracy within the prescribed tracking time. Finally, stability analyses and a simulation example are presented to demonstrate the effectiveness of the proposed prescribed-time fault-tolerant tracking control strategy, validating its theoretical significance and practical applicability in engineering systems.

Affiliations: Ninth Institute, China Electronics Technology Group Corporation, Mianyang, China; School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China; School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, China; School of Electronic Information and Electrical Engineering, Chengdu University, Chengdu, Sichuan, China; Center for Robotics, School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China; School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore

Abstract:
Output tracking control has been extensively applied in the cooperative control of multiagent systems (MASs), including mobile robot obstacle avoidance and autonomous aerial vehicle formation. This article investigates the H_\infty output consensus tracking problem of interval type-2 (IT2) fuzzy heterogeneous MASs subject to multiple-channel denial-of-service (DoS) attacks. First, in the presence of DoS attacks on both leader–follower and follower–follower communication channels, a fully distributed adaptive compensator is designed to approximate the convex hull of the leader’s state. Then, to address DoS attacks occurring in the compensator–controller and observer–controller channels, an observer-based fuzzy switched controller is developed for each follower agent to accomplish the tracking objective. Furthermore, a two-layer hierarchical hybrid event-triggered mechanism (ETM) is established to significantly reduce the communication burden of the MAS network. In the proposed ETM, asynchronous communication and Zeno behavior are rigorously excluded, while the triggering frequency is effectively decreased. Moreover, a sufficient condition is derived to guarantee the exponential stability of the tracking error with a prescribed H_\infty performance. Finally, simulation results are provided to demonstrate the feasibility and superiority of the proposed approach.

Abstract:
Clustering provides a powerful technique for data analysis and data interpretation in the current complex background. Fuzzy clustering has gained significant attention in both research and applications due to its effectiveness in capturing the inherent uncertainty of real-world data. Among these methods, fuzzy C-means (FCM) stands out as one of the most representative and widely used approaches. This study develops a novel nonlinear transformation strategy to restructure data in order to improve the classification performance of FCM, and the transformed data structure, achieved through the developed nonlinear techniques, exhibits highly effective in enhancing the performance of FCM-based classifiers. In the proposed scheme, the original dataset is first partitioned into multiple subsets (matrix blocks) based on the original labels, with distinct weights assigned to each feature within these subsets. This process constructs a more separable dataset, referred to as the “expected high-performance dataset.” Then, multiple nonlinear transformation models are constructed for the original dataset and for each feature of the constructed “expected high-performance dataset” with the support vector regression (SVR) method. During these operations, weight optimization is performed using particle swarm optimization (PSO), ultimately enhancing intraclass compactness by amplifying the similarity among samples within the same class. A comprehensive analysis of the proposed method was conducted, and experimental results on public datasets demonstrate its effectiveness and feasibility. The classification accuracy of the proposed method on multiple datasets has been improved by varying degrees compared with FCM, with an average improvement of 16.029% and a maximum improvement of 57.365%.

Abstract:
A low-pass filter is essential for stabilizing strictly proper repetitive-control systems, but it inevitably degrades steady-state tracking accuracy due to gain attenuation and phase lag. This article presents a new filter design and optimization method that improves both transient response and steady-state accuracy in continuous-time repetitive-control systems. First, the gain and phase characteristics of conventional filter-based repetitive controllers are rigorously analyzed to reveal the relationship between filter parameters and tracking performance. Based on this analysis, a new filter structure is designed to precisely compensate for gain attenuation and phase delay, specifically at the fundamental frequency, by minimizing the error term without increasing the filter bandwidth. A guideline for selecting the filter parameters for varying periodic trajectories is also provided. In addition, according to the one-to-one mapping between control and learning behaviors and their respective gains, dual performance indices are constructed to account for tracking error and control effort across multiple learning cycles. A multiobjective optimization framework is then developed to directly tune these gains subject to stability constraints, achieving an optimal balance between rapid transient convergence and control energy efficiency. Experimental results validate the effectiveness and superiority of the design.

Abstract:
Given the high coupling of state variables in second-order chaotic systems, the projective synchronization control schemes for first- or fractional-order chaotic systems are not applicable in second-order chaotic systems. Also, the current control schemes on second-order chaotic systems are difficult to tradeoff between convergence and robustness. To address the above issues, this article develops a predefined-time robust neural dynamics controller (PTRNDC). First, a predefined-time nonsingular terminal sliding mode variable (PTNTSMV) is designed to control the coupling of errors in the projective synchronization of second-order chaotic systems, ensuring the nonsingularity and convergence. Hence, a predefined-time double-integral zeroing neural dynamics (ZNDs) design formula based on a time-base generator (TBG) is devised to ensure that the sliding mode variable attains the desired sliding mode surface swiftly and robustly. The theorems about the stability, convergence, and robustness of the projective synchronization under the PTRNDC are analyzed rigorously, and the comparative simulations further verify the effectiveness of the PTRNDC. In addition, the chaotic sequences generated by the projective synchronization between the second-order chaotic systems are successfully applied in the image encryption, making the original image possess excellent visual distortion.

Abstract:
The problem of reinforcement learning (RL)-based fuzzy control for nonlinear systems with unknown dynamics via parallel composite policy iteration (PCPI) scheme is studied in this article. The main objective of this article is to solve the fuzzy algebraic Riccati equation (FARE), which is inherently complex and cannot be easily solved by traditional mathematical formulas. Policy iteration (PI) and value iteration (VI) algorithms proposed have been widely used to address this problem. However, these algorithms have the disadvantages of an initial stabilizing control policy, the persistent excitation (PE) condition, and huge amounts of data. To effectively alleviate these drawbacks, a novel PCPI algorithm is proposed in this article. Specifically, for each fuzzy subsystem, an adaptive parameter is designed to eliminate the requirement of an initial stabilizing control policy. In addition, an online model-free PCPI algorithm is proposed for the situation where the dynamic information of the fuzzy system is difficult to obtain. By substituting the stored historical data with online data, the PE condition is relaxed to the initial excitation (IE) condition. Concurrently, the corresponding algorithm can be executed independently and concurrently under each fuzzy rule, thereby fully exploiting the available computational resources. Finally, the effectiveness of the algorithms set forth in this article is verified through a single-link robot arm and quarter-car active suspension (QCAS) experiment.

Abstract:
This article develops a self-triggered prescribed-time (PT) smooth bipartite formation tracking control (BFTC) strategy for uncertain nonlinear multiagent systems (NMASs) operating over directed graphs. An adaptive backstepping framework is employed for formation control design. To enhance the applicability of distributed protocols, we investigate practical BFTC for multiagent systems (MASs) with followers that are subject to unknown nonlinear dynamics, external disturbances, and actuator faults within cooperative–competitive interaction topologies. Radial basis function neural networks (RBFNNs) are employed to approximate these uncertainties, leveraging their universal approximation capability and localized response characteristics. Importantly, in contrast to previous studies, this work achieves user-defined tracking performance suitable for practical NMAS implementations. The proposed bipartite formation tracking controller guarantees compliance with the user-specified settling time without reliance on initial conditions. Furthermore, considering the constraints imposed by limited communication bandwidth, a distributed dynamic self-triggered control (DSTC) mechanism is developed to enhance transmission efficiency. Unlike traditional strategies, the proposed DSTC dynamically adjusts triggering intervals based on bipartite formation tracking errors (BFTEs). This adaptability facilitates a real-time balance between communication load and system performance. Simulation results validate the efficacy of the proposed control strategy.

Abstract:
Note that the available barrier Lyapunov function (BLF) design considers that the precondition of the specified function must be a smooth convex function, which is relatively harsh for most models. In this article, built on proportional–integral (PI) theory, an adaptive neural network (ANN) PI iterative learning tracking control method for fractional-order nonlinear systems (FONSs) with full-state constraints is presented. A new type of BLF is built that only requires finding a derivative of this function needs to be monotonic under the fractional Lyapunov direct method. To meet the needs of reducing computational complexity and data volume, the designed backstepping controller based on PI control consists of a series of constant gains and dynamic variables with basic linkage relationships. Moreover, it also incorporates iterative learning algorithm that can achieve continuous or discontinuous self-learning and updating. The results indicate that all closed-loop signals of FONSs are semi-globally ultimately uniformly bounded and the constraint is not violated. Theoretical analysis and numerical simulation have verified the rationality of this study.

Abstract:
In order to enable the mobile parallel manipulator to avoid obstacles and achieve repetitive motion as well as avoid velocity spikes, a bi-criteria obstacle avoidance scheme synthesized by time-varying penalty strategy (BCOA-TVPS) neural network is proposed and designed. To do so, first, the bi-criteria are composed of repetitive motion criterion and infinite norm velocity minimization criterion, and the constraints consider the vector-based obstacle avoidance constraints. Second, the bi-criteria obstacle avoidance scheme is reformulated as a constrained time-varying quadratic programming (QP) problem. Third, a time-varying penalty strategy (TVPS) neural network is adopted to solve the QP problem. Finally, two kinds of trajectory tracking experiments verify the effectiveness and applicability of the proposed BCOA-TVPS scheme.

Abstract:
The distribution discrepancy metrics are the core foundation of achieving domain confusion. Therefore, they mainly determine the performance of deep transfer diagnosis models. However, their effectiveness relies on the stability of data local distributions, making them unsuitable for cross-domain machine diagnosis tasks under continuous time-varying conditions. Hence, a new integrated-dispersion manifold distance (IDMD) is proposed to enhance the discrepancy representation capability in dynamic data structures. The maximum entropy-based local distribution (MELD) selection mechanism is designed to represent the global distribution information of time-varying monitoring signals adaptively. Furthermore, the ensemble Grassmann manifold geodesic (EGMG) measurement is constructed to characterize the intrinsic distribution discrepancy information due to complex nonlinear structures of high-dimensional data. The proposed IDMD distribution discrepancy metric is validated against two fault transfer diagnosis experiments under time-varying conditions, including laboratory planetary gearboxes and actual wind turbine bearings. The experimental results demonstrate its effectiveness and advantage over the existing advanced methods.

Abstract:
This article presents a data-driven control method to address the local asymptotic stabilization problem of discrete-time neural networks (DNNs) under input saturation. To reduce communication load, a memory-type event-triggered mechanism (MEM) is first designed to mitigate the superfluous triggers. Then, a memory-dependent Lyapunov function (MLF) is constructed to accommodate the memory term introduced by the MEM. Based on the designed MEM, the MLF and two data-based system representations, a data-based stabilization criterion is developed, and an estimated region of attraction (ERA) is determined. Simultaneously, the feedback gain and the trigger matrix are co-designed to guarantee the local stability of the closed-loop system. A notable feature of the proposed approach is that the proposed stabilization criteria rely solely on accessible data, without necessitating full knowledge of the system matrices. It makes the approach well-suited for practical applications where precise modeling is difficult or infeasible. Furthermore, a hybrid optimization scheme combining the linear objective minimization method and the particle swarm optimization (PSO) algorithm is presented to maximize the size of the ERA. Finally, two numerical simulations are given to validate the effectiveness of the proposed optimization algorithm, illustrate the influence of data size, and demonstrate the advantages of the designed MEM in stabilizing DNNs.

Abstract:
A chain-patterned approach is proposed to achieve the novel leader-following consensus (LFC) with prescribed time-bound and order for multiagent system under directed chain interaction with increasing scales. Using chain-patterned polynomial encodings, this approach confines all effects of scale variation, thereby accommodating increasing scales without requiring prior knowledge of every interaction at all open moments, like the existing studies. Moreover, time-bound-based generator are embedded in this approach to guarantee the novel LFC with prescribed time and bound, while avoiding the infinity-approaching time-varying parameters. Furthermore, the important property order is further enforced and obtained under the proposed approach, conforming to the unidirectional information flow characteristic of chains. Finally, the validity and superiority of the proposed chain-patterned approach are demonstrated by comparative examples.

Abstract:
This study addresses the bipartite output consensus problem of heterogeneous uncertain multiagent systems (MASs) under hybrid event-triggered control mechanism. Initially, a fully distributed adaptive bipartite compensator is composed, which consists of time-varying coupling weights and hybrid event-triggered mechanism to estimate the state of the leader. The hybrid event-triggered mechanism includes the event-triggered mechanism for the leader and the edge-event triggered mechanism for all edges to reduce the information transmission among agents. Then, a novel distributed output feedback controller is put forward for uncertain system dynamics. With the aid of the proposed controller, the bipartite output consensus problem of heterogeneous uncertain MASs can be resolved. Furthermore, the above results can be extended to the case of switching topology. Lastly, the validity of the theoretical findings is confirmed through four simulation examples.

Abstract:
Special tasks in complex and extreme environments require mobile robots to possess the good capabilities of navigation and securing map data. Mobile robots driven by the chaotic properties of memristive neural networks (MNN) can offer intriguing insights. However, the expandable MNN capable of providing multiple reliable options for diverse application scenarios has yet to be thoroughly explored. Hence, this article proposes a new universal method to enhance the dynamics in neural networks for generating numerous neural networks with rich dynamics, providing multiple options for the navigation and security of IoT-based robots. The enhanced dynamics in this method benefit from expanding the number of memristive electromagnetic radiation, the number of neurons, and their integration. Many different memristive central cyclic neural network (MCCNN) are successfully derived from the newly constructed central cyclic neural network as an example. Various dynamics of memristive central cyclic neural networks (MCCNN) are numerically investigated, including bifurcation, homogeneous and heterogeneous multistability, and large-scale amplitude control. The analog circuit and digital hardware platform are built to verify the physical existence and feasibility of MCCNN. Finally, MCCNN is applied to drive the IoT-based mobile robot. To evaluate the robot’s area coverage, obstacle avoidance performance, several experiments are carried out, which validate the robot’s superiority.

Abstract:
In this article, the constrained navigation problem for autonomous robots moving in unknown cluttered environments is considered. In particular, it is required to ensure the safety of the path planning and control units during the on-line operations. This statement gives rise to a networked control framework whose the key critical aspects are addressed by resorting to model predictive control technicalities developed within a set-theoretic approach. In particular, a novel control architecture is conceived whose the main features can be summarized as follows: anti-collision capabilities despite time-induced time-delay occurrences along the communication medium; mission accomplishment despite unpredictable obstacle occurrences along the nominal path. These properties are formally proven together with ultimate uniformly boundedness and constraints fulfillment of the regulated trajectory regardless of the vehicle uncertainties. In particular, skid-steered tracked mobile robot are considered for their flexibility and adaptability to operate in arduous scenarios for hazard missions. Final experiments are provided to show the effectiveness and to highlight the main advantages of the proposed control architecture.

Abstract:
This article deals with the challenge of a fair and efficient reallocation of resources in a multiagent system (MAS). A novel dynamic control framework is introduced in which the state of each agent evolves according to a distributed control law. This law ensures the allocation of resources according to predefined weights and promotes a fair distribution among the agents. The control strategy is thoroughly analyzed to show that resource allocation remains well-defined, avoids singularities, and ensures consistent performance. Moreover, it is proved that the total resource allocated remains constant, showing that the system can preserve a crucial invariant throughout its evolution. Theoretical results validate the approach and show its adaptability to changing agent states while maintaining the overall resource constraints. A key advantage of the proposed strategy is that the total amount of resources matching the initial distribution remains unknown to the agents. Instead, through emergent behavior resulting from interaction with other agents, each agent uses an appropriate amount of the resource based on its own requirements. This work contributes to an effective control strategy to achieve stable and fair resource allocation in multiagent networks.

Abstract:
This article studies the adaptive boundary control of a rotating body-beam system (RBBS) composed of a cantilevered beam with a tip payload connected to its upper end. The opposite end of the beam is fixed to the center of a rotational rigid disk. We assume that the dynamic process of the RBBS is affected by unknown disturbances and parameters. The external control actions, constituted by a control force exerted on the tip payload and a control torque acting on the disk, occur in dead zone nonlinearity and actuator failure. First, the mathematical expression of dead zone nonlinearity and actuator failure is combined and then divided into a desired control signal and a nonlinear input error. Second, by summing the input errors and external disturbances, adaptive boundary control and parameter compensation laws are designed for the RBBS to ensure vibration attenuation and regulate the rotating speed of the disk to a desired value. Third, the constructed control schemes ensure uniformity ultimately and boundedness regulation of the state variables, which is proved through the Lyapunov direct method. Finally, the effectiveness and robustness of the designed controllers are tested using numerical simulations.

Abstract:
This article focuses on the low-conservative stability criteria of delayed neural networks (DNNs). To achieve this goal, new techniques are developed to effectively utilize more system-related information. To use the time-varying delay information, some delay-product terms are introduced into the Lyapunov–Krasovskii functional (LKF), and an extended matrix-injection-based transformation method, which introduces delay-derivative-dependent slack matrices while obtaining the negative definite condition, is proposed. With respect to the use of activation function information, the terms related to the activation function are fully augmented in the LKF. In particular, by considering the sector-constraint information of the activation function, a new nonlinear-function-dependent functional term is established, and a sector-constraint-dependent matrix-separation-based inequality is developed. By applying the above techniques, several improved stability criteria are derived, and two typical examples are provided to illustrate the advantages of the proposed methods.

Abstract:
This article proposes a high-order robust dynamic surface control method for high-order strict-feedback systems (SFSs) with asymmetric output constraints and external disturbances, based on the fully actuated system approach. By introducing a class of nonlinear transformation functions, the original system’s output constraint problem is transformed into a bounded problem in a new system representation. The proposed method directly designs a controller for each higher order subsystem using the fully actuated system framework, avoiding transformation to a first-order system and thereby simplifying the control design process. Stability analysis demonstrates that all closed-loop signals are uniformly ultimately bounded, while the system output successfully tracks the reference signal without violating the prescribed constraints. Numerical simulations on a robotic manipulator and an electromechanical system validate the effectiveness of the proposed approach.

Affiliations: Department of Electrical Engineering, Key Laboratory of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao, China; Department of Electrical Engineering, Measurement Technology and Instrumentation Key Laboratory Hebei Province, Yanshan University, Qinhuangdao, China; Department of Engineering, King’s College London, London, U.K.; School of Engineering, Lancaster University, Lancaster, U.K.

Abstract:
The co-design problem of dual event-triggered (DET) mechanism and polynomial dynamic output-feedback (PDOF) controller is investigated for positive polynomial fuzzy systems (PPFSs) with uncertainty and disturbance constraints. Specifically, a 1-norm DET mechanism compatible with the positivity of PPFSs is proposed to asynchronously update measurement outputs and PDOF control signals. However, synthesizing this DET-PDOF controller proves challenging due to the coupling of multiple unknown PDOF controller gain matrices within the positivity and stability conditions, which results in complex nonconvex terms. By introducing auxiliary variables and constraints, sufficient conditions for DET-PDOF controller solution are given to ensure both the L_1 -gain performance and strict positivity of PPFSs with uncertainty and disturbance. Moreover, existing stability analysis results that ignore membership functions (MFs) tend to be conservative, implying that the obtained DET-PDOF controller is effective only within a limited triggered threshold range, leading to worse transmission performance. Therefore, a multivariate optimization method based on an improved genetic algorithm (IGA), which accounts for the system states and PDOF controller variables, is developed to substantially expand the admissible DET threshold range while effectively suppressing dual-triggering frequencies. Finally, a numerical example and a two-linked tank system with parameter uncertainty are provided to validate the feasibility of the proposed scheme.

Abstract:
This article presents a novel reinforcement learning (RL)-based control scheme for trajectory tracking of robot manipulators, incorporating an uncertainty estimator and an optimal tracking controller. A momentum observer (MO) is implemented in conjunction with an integral sliding mode control (ISMC) to facilitate uncertainty estimation for compensation. A proportional–derivative-like (PD-like) control plus an actor–critic neural network (NN)-based feedforward control is utilized for trajectory tracking. An NN parameter selection scheme is adopted to circumvent the time-consuming adjustments of its activation functions and initial weights, thereby ensuring the admissibility of the initial control policy and improving its efficiency. Lyapunov function analysis demonstrates stability of the closed-loop system, in which all error signals are shown to remain bounded and eventually settle into a small residual set. The proposed control scheme is compared with a conventional PD approach consisting of a feedforward controller and an NN controller with adaptive radial basis functions (RBFs). Comparison is also made with a recent approach featuring a feedforward super-twisting sliding mode control (FSTSMC). Simulation and experimental results show superior tracking performance of the presented control scheme against the comparative counterparts, validating the new approach and further supporting its effectiveness and feasibility.

Abstract:
This article deals with the stabilization of nonlinear cyber–physical systems (CPS) subject to actuator faults via the fault-tolerant control (FTC) algorithm. First, to tackle the time-varying delays taken into the system, we proposed a novel quadratic function negative determination lemma, which derives the sufficient conditions for the corresponding quadratic polynomials arising in the derivatives of Lyapunov–Krasovskii functional (LKF). For this purpose, we are parting the time-delay intervals into uniformly equal subintervals and the tangents intersection is carried out in the region of each partitioned intervals. Thereafter, from the cross-points of tangents in each subinterval and choosing a freely adjustable parameter within the delay bounds, we attained a novel quadratic function negative definiteness conditions which profits with high system performance. By means of Lyapunov stability theory (LST), the sufficient conditions are derived in the form of linear matrix inequalities that ensure the asymptotic stabilization of the addressed system. Finally, numerical simulations including the realm of autonomous ground vehicle (AGV) problem are performed, and the comparative analysis in the line of negative-definite (ND) lemmas is exhibited to showcase the efficacy of the proposed approach (PA).

Abstract:
A reliable benchmark library is essential for advancing research in global optimization by enabling fair comparisons and rigorous testing of optimization algorithms across diverse problem landscapes. In this article, we focus on instance selection methods, which aim to choose representative problems for evaluating algorithm performance. We present a comprehensive review of existing instance selection methods, highlighting their strengths and limitations, particularly in balancing the consideration of algorithm performance and the analysis of problem characteristics using exploratory landscape analysis. Building on these insights, we introduce two novel instance selection methods that leverage both algorithm performance data and landscape analysis information to construct diverse and informative benchmark sets. For evaluation, we benchmark our approaches against four existing instance selection methods on the recently expanded DIRECTGOLib v2.0 library. Our results demonstrate that the proposed methods effectively identify representative instances that capture a wide range of problem characteristics, enabling a more comprehensive evaluation of algorithm performance. These findings have significant implications for the development and assessment of new optimization algorithms, ultimately contributing to more reliable and robust solutions for real-world optimization problems.

Abstract:
This article treats the problems of the stability, boundedness, and stabilizing control of discrete-time semi-Markov jump systems (SMJSs) with fragmentary semi-Markov kernel (SMK) under persistent disturbances. Since the statistical characteristics of stochastic processes are difficult to describe precisely and comprehensively, the available SMK information may be fragmentary, and only a portion of the information is known. Regarding this problem, we propose new approaches that leverage all the known SMK information and derive new criteria for analysis and control. The feasibility therein can be enhanced compared to the existing approaches with inadequate utilization of the known SMK information. Additionally, a polytopic approach is proposed to approximate the unknown portion of the SMK information to enrich the information available for subsequent analysis and control design. This is achieved through constructing a polytopic quadratic Lyapunov-like function (LF), which further improves the feasibility. In this way, both the available information and the approximated unknown part about the SMK are incorporated. Meanwhile, the ultimate boundedness of the closed-loop semi-Markov jump linear system (SMJLS) is ensured in the mean-square sense without requiring the deviation between the state and its nominal one to converge at all times. We illustrate the validity and superiority of the proposed approach through a numerical example and a simulated chemical process example using a machine learning-based surrogate model.

Abstract:
Semantic change detection (SCD) endeavors to identify land-cover changes from multitemporal remote sensing images, providing essential information for various applications. Nevertheless, conventional supervised SCD methods necessitate extensive pixel-level annotations, limiting their applicability. The capability of self-supervised methods to learn feature representations with large amounts of unlabeled data and minimal annotation, and to achieve superior performance, has made them one of the hot topics in remote sensing. However, most self-supervised methods in remote sensing are primarily designed to learn general semantic representations of images, which limits their effectiveness for tasks like SCD that require the analysis of complex semantic transformations. To address this, we propose a multistage, multitask, and multilevel self-supervised network, named S3CD, that learns semantic changes from bi-temporal remote sensing images across scene, pixel, and prototype levels in two stages. In particular, in Stage 2, the network enhances the robustness of SCD by learning semantic consistency within the semantic stable categories across different temporal and capturing the temporal patterns of semantic change categories. We evaluate S3CD on two widely used remote sensing change detection (CD) datasets, where it outperformed state-of-the-art self-supervised and supervised SCD methods. Notably, in the binary CD (BCD) task (i.e., detecting the locations of changes), S3CD also outperforms most supervised learning methods. Therefore, this approach facilitates the application of self-supervised learning in the field of remote sensing CD.

Abstract:
This study proposes a novel and cohesive framework to address stochastic finite-time consensus (FTC) problems, with the following main contributions: (i) We first introduce the original stochastic delay systems and, based on this, analyze the effects of Lévy noise, actuator faults, and Markov switching. Both leaderless and leader–follower topologies are considered, and a new control algorithm is proposed to investigate the fault-tolerant control problem under the influence of communication delays and Markov switching dynamics. (ii) To ensure that the states converge to a bounded compact set, the convergence analysis uses strong mathematical techniques, such as stopping time theory and the evolution of finite-time stochastic theory, to achieve mean-square and almost certain consensus. (iii) An important aspect of this study is the consideration of Markov-switching actuator faults, where fault occurrence and recovery evolve randomly according to a Markov process, introducing additional stochastic uncertainties into the system dynamics. Additionally, two numerical examples are provided to validate the correctness of the theoretical results.

Abstract:
This article is concerned with the recursive state estimation issue for a class of nonlinear cyber-physical systems (CPSs) with token bucket protocols (TBPs) subject to sensor failures and false data injection (FDI) attacks. In the system under consideration, measurement signals are transmitted to the remote estimator only when there are sufficient tokens in the bucket to meet the token consumption. During network transmissions, the signals are exposed to FDI attacks, which occur randomly and follow a Bernoulli distribution. The primary objective is to develop a state estimation algorithm that can handle the TBP, sensor failures, and FDI attacks simultaneously. Initially, the upper bound of the estimation error covariance is derived using an intensive stochastic technique and the induction approach. Subsequently, the desired estimator gains are recursively computed to minimize this upper bound. Finally, an example is presented to demonstrate the effectiveness of the proposed estimation scheme.

Affiliations: School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China; Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi-Hiroshima, Japan; School of Automation, Chongqing University, Chongqing, China; School of Artificial Intelligence and Automation, and the Key Laboratory of Image Processing and Intelligence Control, Huazhong University of Science and Technology, Wuhan, China

Abstract:
In this article, we address the problem of prescribed-time distributed convex optimization (DCO) for a class of networked Euler–Lagrange systems (NELSs) operating over undirected connected graphs. By utilizing position-dependent measured gradient values of local objective functions and facilitating local information exchanges among neighboring agents, we construct a set of auxiliary systems that collaboratively seek the optimal solution. The prescribed-time DCO problem is then reformulated as a prescribed-time stabilization challenge of an interconnected error system. We propose a prescribed-time small-gain criterion to characterize the prescribed-time stabilization of the system, presenting a novel approach that enhances effectiveness beyond existing asymptotic or finite-time stabilization methods for interconnected systems. Based on this criterion and the auxiliary systems, we design innovative adaptive prescribed-time local tracking controllers for the subsystems. The prescribed-time convergence is achieved through the introduction of time-varying gains that increase to infinity as time approaches the prescribed deadline. The Lyapunov function, along with prescribed-time mapping, is employed to establish the prescribed-time stability of the closed-loop system and the boundedness of internal signals. Finally, the theoretical results are validated through a numerical example.

Abstract:
The primary objective of this study is to enable the end effector of robot manipulators driven by brushless DC motors (BLDC), subjected to model uncertainties, to track the desired trajectory. Direct control in task space, with the primary goal of minimizing the tracking error of the end effector, is favored. Besides, incorporating actuator dynamics (AD)actuator dynamics (AD) into control synthesis and stability analysis is intended to enhance the sensitivity in terms of positioning and the reliability of robot manipulators. Consideration is given to uncertainties in both the robot manipulator and AD to achieve enhanced tracking performance. In order to improve the efficiency of the closed-loop control system, uncertainties in the dynamic model and AD were estimated using a self-organized adaptive fuzzy logic (AFL)adaptive fuzzy logic (AFL) framework, and the obtained estimates were applied to the control torque input. In the employed AFL framework, the means and variances of the membership functions (MFs)membership functions (MFs) are updated online in each iteration, enabling a more accurate estimation of uncertainties. The use of the newly created Lyapunov function demonstrates that the closed-loop system is uniformly ultimately bound. Experimental comparisons were conducted on a two-degree-of-freedom planar robot manipulator driven by a BLDC motor to test the applicability of the presented controller.

Abstract:
Underactuated multirotor uncrewed aerial vehicle (UAV) equipped with a manipulator (UWM) face significant challenges when transporting loads, as large swings in the manipulator can resemble a double pendulum and risk dislodging the payload. With complex control requirements, nonlinear motion coupling, and variable load conditions, conventional linear controllers are often inadequate. To address these issues, we present anti-swing control method based on system dynamics characteristics and online parameter compensation (ASDOC). This novel anti-wing controller stabilizes swinging by leveraging the system’s nonlinear dynamics and performing online parameter estimation, thus avoiding the limitations of linearization. This design adapts robustly to varying load characteristics, ensuring stability and reliability across diverse scenarios. Lyapunov-based analysis confirms the control objectives, while simulations substantiate ASDOC’s enhanced anti-swing performance.

Abstract:
In this article, the stability and stabilization for T-S fuzzy systems with periodically varying delays (PVDs) are explored. First, according to the characteristics of PVDs, an augmented Lyapunov–Krasovskii functional (LKF) related to fuzzy rules is established. Second, enhanced stability criteria are developed based on fuzzy augmented LKF together with a generalized delay derivative-dependent reciprocally convex matrix inequality (RCMI). It successfully overcomes the limitations of estimation for only two reciprocally convex terms (RCTs), meanwhile providing a tighter bound by introducing more free variables. Under the parallel distributed compensation (PDC) scheme, a fuzzy memory controller ensuring system stabilization is investigated. Finally, the enhancement of stability criteria and the effectiveness for controller design are verified through numerical simulation.

Abstract:
Concurrent and complex aerial missions with multiple targets exceed the capabilities of a single cooperative formation of high-speed flight vehicles (HSFVs). To address this challenge, this article decomposes a fleet of HSFVs (subject to multiple compounding factors, including unknown aerodynamic disturbances, unmodeled or parametric uncertainties, actuator faults, and potential intervehicle collisions) into several subgroups and develops a recurrent neural network (RNN) online learning-based prescribed-time safe and robust cooperative group formation control protocol under dynamic event-triggered communication. A distributed prescribed-time event-triggered estimator (DP-TE-TE) is first developed to drive all HSFVs to acquire the convex hull information (i.e., input, velocity, and position) spanned by multiple virtual leader vehicles (VLVs) before grouping or the input, velocity, and position information of their respective single VLV within the group after grouping. Then, based on the constraint-following theory, the safety distance inequality between any potentially colliding pair of HSFVs, along with the first-order differential equation involving the formation position tracking error, is converted into collision motion constraints and prescribed-time trajectory tracking constraints, respectively. To enhance the flight control performance of the swarm, an RNN is constructed for each HSFV to learn the unknown nonlinear function induced by multiple compounding factors, thereby providing online compensation for the subsequent control design. Finally, by integrating the constraint-following errors derived from collision motion constraints and prescribed-time trajectory tracking constraints, the RNN compensation term, and the estimated information, the prescribed-time safe and robust cooperative group formation control scheme (P-TSRCGFCS) is proposed. In the simulation examples, the effectiveness of the proposed algorithms is verified by dividing 12 HSFVs and three VLVs into three subgroups to perform the desired cooperative group formation task.

Abstract:
For the first time, this article presents a dissipativity-based observer design for accurate state-of-charge (SOC) estimation, essential for improving the safety, performance, and lifespan of lithium-ion batteries (LIBs) in electric vehicle (EV) battery management systems (BMSs). However, model uncertainties and measurement noise significantly affect estimation accuracy. To address this, a novel observer design based on ( \mathcal Q, \mathcal S, \mathcal R )- \gamma -dissipativity theory is developed, formulated within a linear matrix inequality (LMI) framework, and integrated with the Lyapunov–Krasovskii functional (LKF) approach. The proposed observer ensures robustness and stability in SOC estimation under uncertain and noisy conditions. A one-resistor capacitor (1-RC) equivalent circuit model (ECM) is adopted for battery modeling, with experimental validation performed on a Panasonic 18650PF cell. The proposed method is compared against the adaptive unscented Kalman filter (AUKF) under four drive cycles: the urban dynamometer driving schedule (UDDS), the aggressive US06 supplemental federal test procedure, the Los Angeles 92 (LA92), and the highway fuel economy test (HWFET). Results show that the proposed observer achieves root-mean-square errors (RMSEs) of 0.77%, 0.50%, 0.65%, and 0.48% and mean absolute errors (MAEs) of 0.59%, 0.42%, 0.50%, and 0.40% under UDDS, US06, LA92, and HWFET, respectively. This corresponds to RMSE reductions of 28.38%, 88.93%, 67.25%, and 38.35% compared with AUKF. Notably, the proposed method achieves a maximum accuracy of 99.23%, surpassing the latest reported accuracy of 98.50%.

Affiliations: School of Information Engineering, Nanchang University, Nanchang, China; School of Automation Science and Engineering, South China University of Technology, Guangzhou, China; Department of Mechanics and Engineering Science, State Key Laboratory for Turbulence and Complex Systems, BIC-ESAT, College of Engineering, Peking University, Beijing, China; Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada

Abstract:
A novel collaborative position and orientation control scheme (CPOCS) for dual-arm robots is proposed, which is capable of controlling the end-effectors’ positions with high precision while preserving their orientations unchanged to some practical tasks (e.g., box handling). To solve the proposed CPOCS in real time while considering key factors such as unknown bounded noise and strict time response constraints in practical engineering environments, this article proposes a novel precisely predefined-time convergent barrier recurrent neural network (PCB-RNN) based on a newly developed piecewise barrier evolution formula. Unlike existing RNNs, the proposed PCB-RNN, owing to its piecewise barrier evolution formula, can achieve precisely predefined-time convergence (PPTC) when addressing the proposed CPOCS under unknown bounded noise conditions. Comprehensive theoretical analysis rigorously proves the PPTC ability of the PCB-RNN under both noise-free and unknown bounded noise conditions. Furthermore, extensive simulation and physical experiments on dual-arm robots validate the effectiveness of the proposed CPOCS and demonstrate the advanced PPTC capability of the proposed PCB-RNN under unknown bounded noises.

Abstract:
This article addresses the problem of resilient consensus control for nonlinear multiagent systems (MASs) operating over networks subject to denial-of-service (DoS) attacks. We propose an event-triggered, recurrent-neural-network-based model predictive consensus controller (RNN-MPCC) that integrates three components: 1) a data-driven recurrent neural network (RNN) predictor of agent dynamics with a certified uniform one-step error bound; 2) a DoS-aware communication model that constrains attack frequency and duration and is embedded in the resilient consensus and update logic; and 3) an aperiodic (event-triggered) execution that reduces transmissions and solver calls while preventing Zeno behavior via a minimum interevent time. The predictive controller optimizes a receding-horizon-based cost function that penalizes the disagreement vector, control effort, and hold-induced errors, enforces input and state constraints, and constructs effective Laplacians from successfully received packets and locally held neighbor copies. Finally, simulations on a six-agent leader–follower multi-UAV network demonstrate that the proposed event-triggered RNN-MPCC achieves resilient consensus under DoS attacks.