Pub Date : 2026-02-03DOI: 10.1109/tcyb.2026.3656420
Yao Li, Chengpu Yu, Renshuo Cheng, Fang Deng, Jie Chen
{"title":"Inverse Dynamic Games With Process Noise and Unknown Target States: A Linear Estimation Approach","authors":"Yao Li, Chengpu Yu, Renshuo Cheng, Fang Deng, Jie Chen","doi":"10.1109/tcyb.2026.3656420","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3656420","url":null,"abstract":"","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"100 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-02DOI: 10.1109/tcyb.2026.3656946
Bing Sun, Wei-Jie Yu, Xiao-Fang Liu, Jinghui Zhong, Jian-Yu Li, Zhi-Hui Zhan, Sam Kwong, Jun Zhang
{"title":"Tensor-Based Ant Colony Optimization for Set Meal Design in Online-to-Offline Restaurants","authors":"Bing Sun, Wei-Jie Yu, Xiao-Fang Liu, Jinghui Zhong, Jian-Yu Li, Zhi-Hui Zhan, Sam Kwong, Jun Zhang","doi":"10.1109/tcyb.2026.3656946","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3656946","url":null,"abstract":"","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"1 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146101330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
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.
{"title":"ADR-DMOEA: A Dynamic Multiobjective Optimization Evolutionary Algorithm Based on Adaptive Dynamic Response Strategy.","authors":"Yuying Wang,Ping Zhou,Shengxiang Yang,Tianyou Chai","doi":"10.1109/tcyb.2026.3652642","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3652642","url":null,"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.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146069935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-28DOI: 10.1109/tcyb.2026.3651627
Kunyu Wang,Lin Zhang,Zhen Chen,Hongbo Cheng,Han Lu,Wentong Cai,Qingsha S Cheng,M Jamal Deen
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.
{"title":"Self-Evolution of Hybrid Data-Physics Equipment Digital Twin Using Meta Learning and Continual Learning.","authors":"Kunyu Wang,Lin Zhang,Zhen Chen,Hongbo Cheng,Han Lu,Wentong Cai,Qingsha S Cheng,M Jamal Deen","doi":"10.1109/tcyb.2026.3651627","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3651627","url":null,"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.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"272 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146069937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-28DOI: 10.1109/tcyb.2026.3652011
Siyong Song,Yingchun Wang,Jiayue Sun,Yunfei Mu
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.
{"title":"Mode Cluster-Based Event-Triggered Control for Stochastic Markovian Jump Systems Under Denial-of-Service Attack.","authors":"Siyong Song,Yingchun Wang,Jiayue Sun,Yunfei Mu","doi":"10.1109/tcyb.2026.3652011","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3652011","url":null,"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.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"42 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146069949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-26DOI: 10.1109/TCYB.2025.3646492
Yi Yu, Guo-Ping Liu, Zhong-Hua Pang, Jian Sun, Rongni Yang
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.
{"title":"Blockchain-Assisted Intelligent Resilient Tracking Control of Networked Systems.","authors":"Yi Yu, Guo-Ping Liu, Zhong-Hua Pang, Jian Sun, Rongni Yang","doi":"10.1109/TCYB.2025.3646492","DOIUrl":"https://doi.org/10.1109/TCYB.2025.3646492","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"PP ","pages":""},"PeriodicalIF":10.5,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146051779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1109/tcyb.2026.3651519
Han Wu,Qinglei Hu,Jianying Zheng,Xiaodong Shao,Yueyang Liu,Dongyu Li
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.
{"title":"Output-Feedback Control of Linear Continuous-Time Systems Using Discounted Inverse Reinforcement Learning.","authors":"Han Wu,Qinglei Hu,Jianying Zheng,Xiaodong Shao,Yueyang Liu,Dongyu Li","doi":"10.1109/tcyb.2026.3651519","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3651519","url":null,"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.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"42 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146034075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1109/tcyb.2026.3650907
Zhi-Hui Fu,Ming-Feng Ge,Teng-Fei Ding,Zhi-Wei Liu
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.
{"title":"Task Optimization for Fixed-Time Control of Intermittent Human-Robot Interaction With Time-Varying Exponents and Coefficients.","authors":"Zhi-Hui Fu,Ming-Feng Ge,Teng-Fei Ding,Zhi-Wei Liu","doi":"10.1109/tcyb.2026.3650907","DOIUrl":"https://doi.org/10.1109/tcyb.2026.3650907","url":null,"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.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"7 1","pages":""},"PeriodicalIF":11.8,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146034077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：