A Dynamic Job-shop Scheduling Problem (DJSP) in 3C (i.e., Computer, Communication, and Consumer Electronics) manufacturing requires efficient resource allocation under dynamically changing production conditions where jobs arrive unpredictably. Traditional optimization methods struggle to provide scalable solutions due to the high computational cost of searching for the optimal schedules in large and complex environments. To address this challenge, this work proposes a Dual Graph convolutional networks-driven Dynamic Cooperative Hunting Optimizer (DG-DCHO). It integrates Graph Convolutional Networks (GCN) with metaheuristic optimization to generate high-quality schedules and significantly improve computational efficiency. A GCN generator processes graph representations of job-shop environment, captures complex dependencies among jobs and machines, and constructs high-quality initial schedules for the optimization process. A GCN evaluator estimates makespan values directly from schedule representations and replaces costly fitness evaluation, thereby minimizing computational overhead and improving optimization speed. A Dynamic Cooperative Hunting Optimizer serves as a base optimizer and generates scheduling solutions by balancing global exploration with local exploitation through an adaptive search strategy. Experimental results across various DJSP instances demonstrate that DG-DCHO consistently outperforms advanced scheduling algorithms by producing higher-quality solutions with reduced computational resources, establishing it as a scalable and effective framework for real-time dynamic scheduling of large-scale manufacturing systems. Note to Practitioners—This paper is motivated by the practical need to rapidly generate efficient production schedules for complex job shops. We propose a novel automated approach, DG-DCHO, which uses deep learning to learn the dependencies of the production environment and rapidly generate high-quality initial schedules. DG-DCHO also estimates schedule performance without relying on lengthy simulations, accelerating the optimization process with an adaptive algorithm. To apply this approach, practitioners would provide standard manufacturing data, including the sequence of operations required for each job, the constraints between operations, the list of available machines, the potential machine assignments for each operation, and the processing times. The system uses this information to automatically build the required graph model, where DG-DCHO optimizes and outputs the best scheduling sequence. This results in the faster generation of more efficient production schedules, improving responsiveness and productivity. Although the simulation results are strong, practical implementation requires integration with factory systems and initial training in artificial intelligence models. Our future plans to extend the proposed approach to addressing other dynamic optimization challenges in logistics, intelligent manufacturing,
{"title":"Dual-GNN-Driven Cooperative Optimization for Makespan-Minimized and Large-Scale 3C Dynamic Job-Shop Scheduling","authors":"Jing Bi;Chen Wang;Ziqi Wang;Junqi Zhang;Haitao Yuan;Jia Zhang;Rajkumar Buyya","doi":"10.1109/TASE.2026.3661178","DOIUrl":"10.1109/TASE.2026.3661178","url":null,"abstract":"A Dynamic Job-shop Scheduling Problem (DJSP) in 3C (i.e., Computer, Communication, and Consumer Electronics) manufacturing requires efficient resource allocation under dynamically changing production conditions where jobs arrive unpredictably. Traditional optimization methods struggle to provide scalable solutions due to the high computational cost of searching for the optimal schedules in large and complex environments. To address this challenge, this work proposes a Dual Graph convolutional networks-driven Dynamic Cooperative Hunting Optimizer (DG-DCHO). It integrates Graph Convolutional Networks (GCN) with metaheuristic optimization to generate high-quality schedules and significantly improve computational efficiency. A GCN generator processes graph representations of job-shop environment, captures complex dependencies among jobs and machines, and constructs high-quality initial schedules for the optimization process. A GCN evaluator estimates makespan values directly from schedule representations and replaces costly fitness evaluation, thereby minimizing computational overhead and improving optimization speed. A Dynamic Cooperative Hunting Optimizer serves as a base optimizer and generates scheduling solutions by balancing global exploration with local exploitation through an adaptive search strategy. Experimental results across various DJSP instances demonstrate that DG-DCHO consistently outperforms advanced scheduling algorithms by producing higher-quality solutions with reduced computational resources, establishing it as a scalable and effective framework for real-time dynamic scheduling of large-scale manufacturing systems. Note to Practitioners—This paper is motivated by the practical need to rapidly generate efficient production schedules for complex job shops. We propose a novel automated approach, DG-DCHO, which uses deep learning to learn the dependencies of the production environment and rapidly generate high-quality initial schedules. DG-DCHO also estimates schedule performance without relying on lengthy simulations, accelerating the optimization process with an adaptive algorithm. To apply this approach, practitioners would provide standard manufacturing data, including the sequence of operations required for each job, the constraints between operations, the list of available machines, the potential machine assignments for each operation, and the processing times. The system uses this information to automatically build the required graph model, where DG-DCHO optimizes and outputs the best scheduling sequence. This results in the faster generation of more efficient production schedules, improving responsiveness and productivity. Although the simulation results are strong, practical implementation requires integration with factory systems and initial training in artificial intelligence models. Our future plans to extend the proposed approach to addressing other dynamic optimization challenges in logistics, intelligent manufacturing,","PeriodicalId":51060,"journal":{"name":"IEEE Transactions on Automation Science and Engineering","volume":"23 ","pages":"4350-4364"},"PeriodicalIF":6.4,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146134383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Elevating Interpretability in Bearing Fault Diagnosis: A Knowledge Distillation Framework Integrating Dynamic and Causal A Priori","authors":"Xu Ding, Zihua Yan, Hao Wu, Qile Ren, Hua Zhai, Juan Xu","doi":"10.1109/tase.2026.3660370","DOIUrl":"https://doi.org/10.1109/tase.2026.3660370","url":null,"abstract":"","PeriodicalId":51060,"journal":{"name":"IEEE Transactions on Automation Science and Engineering","volume":"17 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Load frequency control is critical for maintaining grid stability, particularly in modern power systems with wind power penetration and increasing exposure to denial-of-service attacks. This paper presents a data-driven dynamic event-triggered reinforcement learning framework for constrained H${}_{infty } $ load frequency control in multi-area power systems. The control problem is formulated as a min–max optimization task, and a dynamic event-triggered strategy is designed to reduce computational and communication burdens. A neural network-based reinforcement learning framework is developed to approximate the near-optimal event-triggered control strategy without requiring explicit system dynamics. To further counteract the impact of frequency-based denial-of-service attacks, a dedicated attacks compensation mechanism is designed. Theoretical analysis proves input-to-state stability of the closed-loop system and guarantees convergence of the neural network parameters. Extensive simulation studies on multi-area power systems with wind power integration demonstrate that the proposed method ensures stable frequency regulation while effectively alleviating the transmission burdens and mitigating the adverse effects of cyberattacks. Note to Practitioners—The reliable operation of multi-area interconnected power systems is becoming increasingly difficult due to two practical challenges: the rapid frequency fluctuations introduced by renewable energy, and the growing risk of cyberattacks that disrupt communication links. To handle these practical challenges, this work develops a data-driven dynamic event-triggered reinforcement learning framework for constrained H${}_{infty } $ load frequency control in multi-area power systems. The approach avoids reliance on precise system models, making it suitable for complex and uncertain environments. The event-triggered mechanism effectively reduces communication and computation burdens, which only updates control signals when necessary, thus being suitable for large-scale interconnected grids. Moreover, an attacks compensation mechanism is designed to enhance resilience against denial-of-service attacks. Simulation results demonstrate that the method improves both reliability and efficiency compared with existing solutions. The practical limitation of this approach lies in its reliance on reinforcement learning, which means it requires a period of learning to achieve optimal control performance. These results provide practical insights for implementing robust and data-driven load frequency control strategies in multi-area interconnected power systems. Beyond application in power systems, the proposed ideas may also be extended to other automation systems, where communication security and resource efficiency are critical.
{"title":"Data-Driven Event-Triggered H∞ Load Frequency Control With Security Against DoS Attacks","authors":"Yuhao Chen;Huarong Zhao;Longquan Ma;Qiang Yang;Hongnian Yu;Li Peng","doi":"10.1109/TASE.2026.3660419","DOIUrl":"10.1109/TASE.2026.3660419","url":null,"abstract":"Load frequency control is critical for maintaining grid stability, particularly in modern power systems with wind power penetration and increasing exposure to denial-of-service attacks. This paper presents a data-driven dynamic event-triggered reinforcement learning framework for constrained H<inline-formula> <tex-math>${}_{infty } $ </tex-math></inline-formula> load frequency control in multi-area power systems. The control problem is formulated as a min–max optimization task, and a dynamic event-triggered strategy is designed to reduce computational and communication burdens. A neural network-based reinforcement learning framework is developed to approximate the near-optimal event-triggered control strategy without requiring explicit system dynamics. To further counteract the impact of frequency-based denial-of-service attacks, a dedicated attacks compensation mechanism is designed. Theoretical analysis proves input-to-state stability of the closed-loop system and guarantees convergence of the neural network parameters. Extensive simulation studies on multi-area power systems with wind power integration demonstrate that the proposed method ensures stable frequency regulation while effectively alleviating the transmission burdens and mitigating the adverse effects of cyberattacks. Note to Practitioners—The reliable operation of multi-area interconnected power systems is becoming increasingly difficult due to two practical challenges: the rapid frequency fluctuations introduced by renewable energy, and the growing risk of cyberattacks that disrupt communication links. To handle these practical challenges, this work develops a data-driven dynamic event-triggered reinforcement learning framework for constrained H<inline-formula> <tex-math>${}_{infty } $ </tex-math></inline-formula> load frequency control in multi-area power systems. The approach avoids reliance on precise system models, making it suitable for complex and uncertain environments. The event-triggered mechanism effectively reduces communication and computation burdens, which only updates control signals when necessary, thus being suitable for large-scale interconnected grids. Moreover, an attacks compensation mechanism is designed to enhance resilience against denial-of-service attacks. Simulation results demonstrate that the method improves both reliability and efficiency compared with existing solutions. The practical limitation of this approach lies in its reliance on reinforcement learning, which means it requires a period of learning to achieve optimal control performance. These results provide practical insights for implementing robust and data-driven load frequency control strategies in multi-area interconnected power systems. Beyond application in power systems, the proposed ideas may also be extended to other automation systems, where communication security and resource efficiency are critical.","PeriodicalId":51060,"journal":{"name":"IEEE Transactions on Automation Science and Engineering","volume":"23 ","pages":"4602-4614"},"PeriodicalIF":6.4,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-02-03DOI: 10.1109/TASE.2026.3659947
Yanmin Wu;Wei Qian;Zidong Wang
This paper is concerned with the adaptive dynamic event-triggered (DET) $H_{infty }$ control for a class of networked nonlinear systems with non-uniform sampling under the Takagi-Sugeno (T-S) fuzzy model. To address the problems of high energy consumption in sensors and the high occupancy rate of limited bandwidth, an improved adaptive DET communication mechanism with non-uniform sampling is proposed, in which the interval dynamic variable is constructed with an adaptive law. Unlike existing works, an online iterative asynchronous premise reconstruction (APR) technique is devised to tackle the challenges caused by the mismatch of premise variables. Based on the adaptive DET mechanism and the online iterative APR method, switched-like fuzzy controllers are designed, which can be switched at different triggering instances. Furthermore, to ensure stability and achieve the desired control performance, new triggering instants-dependent Lyapunov functions are constructed in accordance with the idea of event interval partitioning. Finally, the practicability of the proposed strategy is demonstrated using two practical examples. Note to Practitioners—The motivation of this study is to devise a DET $H_{infty }$ control strategy for networked T-S fuzzy systems, which can be extensively utilized in suspension systems, power systems, and permanent magnet synchronous motor systems. Considering the energy consumption of sensors and the limited bandwidth of practical communication networks, the adaptive DET communication mechanism with aperiodic sampling is proposed for the purpose of reducing the sampling frequency of sensors and unnecessary data transmission. The premise variable asynchronous challenge caused by the DET strategy, the online APR technique is designed. By using the online APR approach, the switched-like fuzzy controllers are devised, which can ensure the closed-loop systems satisfy asymptotic stability. In addition, the new triggering instants-dependent Lyapunov function is constructed to achieve desired control performance.
{"title":"Adaptive Dynamic Event-Triggered H∞ Control for Fuzzy Systems Through an Online Iterative Asynchronous Premise Reconstruction Strategy","authors":"Yanmin Wu;Wei Qian;Zidong Wang","doi":"10.1109/TASE.2026.3659947","DOIUrl":"10.1109/TASE.2026.3659947","url":null,"abstract":"This paper is concerned with the adaptive dynamic event-triggered (DET) <inline-formula> <tex-math>$H_{infty }$ </tex-math></inline-formula> control for a class of networked nonlinear systems with non-uniform sampling under the Takagi-Sugeno (T-S) fuzzy model. To address the problems of high energy consumption in sensors and the high occupancy rate of limited bandwidth, an improved adaptive DET communication mechanism with non-uniform sampling is proposed, in which the interval dynamic variable is constructed with an adaptive law. Unlike existing works, an online iterative asynchronous premise reconstruction (APR) technique is devised to tackle the challenges caused by the mismatch of premise variables. Based on the adaptive DET mechanism and the online iterative APR method, switched-like fuzzy controllers are designed, which can be switched at different triggering instances. Furthermore, to ensure stability and achieve the desired control performance, new triggering instants-dependent Lyapunov functions are constructed in accordance with the idea of event interval partitioning. Finally, the practicability of the proposed strategy is demonstrated using two practical examples. Note to Practitioners—The motivation of this study is to devise a DET <inline-formula> <tex-math>$H_{infty }$ </tex-math></inline-formula> control strategy for networked T-S fuzzy systems, which can be extensively utilized in suspension systems, power systems, and permanent magnet synchronous motor systems. Considering the energy consumption of sensors and the limited bandwidth of practical communication networks, the adaptive DET communication mechanism with aperiodic sampling is proposed for the purpose of reducing the sampling frequency of sensors and unnecessary data transmission. The premise variable asynchronous challenge caused by the DET strategy, the online APR technique is designed. By using the online APR approach, the switched-like fuzzy controllers are devised, which can ensure the closed-loop systems satisfy asymptotic stability. In addition, the new triggering instants-dependent Lyapunov function is constructed to achieve desired control performance.","PeriodicalId":51060,"journal":{"name":"IEEE Transactions on Automation Science and Engineering","volume":"23 ","pages":"4301-4313"},"PeriodicalIF":6.4,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-02-03DOI: 10.1109/TASE.2026.3660881
Yanpeng Shi;Jiangping Hu;Baogen Song;Peng Li;Lei Shi
This paper investigates the output containment tracking problem in general heterogeneous multi-agent systems facing prescribed performance and intermittent communication. In this case, a novel non-periodic intermittent control framework is introduced to facilitate the intricate nature of the complex network to achieve the containment objective. First, an intermittent communication network is built by introducing a novel intermittent interval condition combining average dwell-time and extreme value theories into the directed graph. Second, a distributed non-periodic intermittent containment control strategy is designed, utilizing an internal system and a modified containment control approach. Subsequently, a distributed prescribed performance hybrid controller is developed to achieve output containment tracking. Additionally, sufficient conditions for the exponential stability are obtained based on the non-periodic intermittent and prescribed performance control methods. This criterion adopts the characterization of the average time interval. The effectiveness of the designed hybrid control strategy is verified by the simulation example, showcasing its advantage to solve the challenges in intermittent communication and prescribed performance. Note to Practitioners—In a complicated heterogeneous network, large-scale agents involved with different dynamics need to employ distributed communication and collaborate with each other to achieve certain tracking tasks. In practical applications, the risk of both communication barriers and limited resources increases dramatically, then an effective non-periodic intermittent control scheme is proposed to guarantee the safe communication for the heterogeneous connected agents. Besides, in harsh environments, the considered agents have to work in a restricted space avoiding the hazardous area, which may limit the position or other performances. Then, it is crucial to address these issues. By introducing the modified containment control, this paper proposes a distributed prescribed performance containment control to ensure the desired transient and steady-state performances, which have important engineering significance.
{"title":"Prescribed Performance Output Containment of Heterogeneous Multi-Agent Systems With Non-Periodic Intermittent Communication","authors":"Yanpeng Shi;Jiangping Hu;Baogen Song;Peng Li;Lei Shi","doi":"10.1109/TASE.2026.3660881","DOIUrl":"10.1109/TASE.2026.3660881","url":null,"abstract":"This paper investigates the output containment tracking problem in general heterogeneous multi-agent systems facing prescribed performance and intermittent communication. In this case, a novel non-periodic intermittent control framework is introduced to facilitate the intricate nature of the complex network to achieve the containment objective. First, an intermittent communication network is built by introducing a novel intermittent interval condition combining average dwell-time and extreme value theories into the directed graph. Second, a distributed non-periodic intermittent containment control strategy is designed, utilizing an internal system and a modified containment control approach. Subsequently, a distributed prescribed performance hybrid controller is developed to achieve output containment tracking. Additionally, sufficient conditions for the exponential stability are obtained based on the non-periodic intermittent and prescribed performance control methods. This criterion adopts the characterization of the average time interval. The effectiveness of the designed hybrid control strategy is verified by the simulation example, showcasing its advantage to solve the challenges in intermittent communication and prescribed performance. Note to Practitioners—In a complicated heterogeneous network, large-scale agents involved with different dynamics need to employ distributed communication and collaborate with each other to achieve certain tracking tasks. In practical applications, the risk of both communication barriers and limited resources increases dramatically, then an effective non-periodic intermittent control scheme is proposed to guarantee the safe communication for the heterogeneous connected agents. Besides, in harsh environments, the considered agents have to work in a restricted space avoiding the hazardous area, which may limit the position or other performances. Then, it is crucial to address these issues. By introducing the modified containment control, this paper proposes a distributed prescribed performance containment control to ensure the desired transient and steady-state performances, which have important engineering significance.","PeriodicalId":51060,"journal":{"name":"IEEE Transactions on Automation Science and Engineering","volume":"23 ","pages":"4329-4340"},"PeriodicalIF":6.4,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-02-03DOI: 10.1109/TASE.2026.3660669
Xiaoyang Gao;Xin Hu;Jiarui Liu;Tieshan Li
Dynamic positioning (DP) stands as the keystone underpinning ships’ operations in the abyssal depths and remote oceans. This paper proposes an event-driven disturbance rejection approximate optimal dynamic positioning scheme for surface ships with prescribed performance via reinforcement learning (RL). Firstly, a disturbance observer is established to achieve the online estimations of marine environmental disturbances such that the undesirable disturbance effects on control performance can be reduced. Meanwhile, the positioning error transformations with the prescribed performance function is established to combine with the backstepping method and the virtual controller can be designed to constrain the positioning error. Then, for the velocity error surface, the RL method provides the actor-critic architecture to approximate the actual optimal commanded control law and minimized the specified performance index function. Subsequently, the optimal commanded control design incorporates the event-driven mechanism to avoid communication resource waste as well as actuator wear and tear. By applying the Lyapunov stability theory, it is proven that the designed RL control law forces the ship’s actual position and yaw angle to converge to desired target with prescribed performance while ensuring all signals in the closed-loop system are uniformly ultimately bounded. The feature of this paper is the reasonable integration of prescribed performance and RL, which ensures that the performance index function of the ship is minimized while keeping the DP error within the safety range. Finally, simulations with comparisons based on a sea launch ship show the effectiveness further validating the superiority of the RL control scheme. Note to Practitioners—In practical engineering, DP ships are often used to perform challenging special tasks such as drilling, cable laying, and satellite launching, and thus inevitably operate in harsh sea conditions for long periods. Issues concerning its safety and energy efficiency deserve in-depth consideration. These include safety constraints on ship position and heading during positioning, exposure to unknown ocean disturbances, as well as the crucial need to conserve energy consumption, communication resources, and thruster actuation frequency. Different from existing DP systems based on prescribed performance robust control, the RL-based event-driven prescribed performance disturbance rejection optimal control scheme developed in this paper can synergistically keep the positioning error within a specified range under disturbances. Taking an offshore launch and recovery ship as the simulation object, the comparison results show that the proposed algorithm enables the DP to effectively reduce resources. Our scheme provides a certain foundation for improving the energy-saving capability of DP ships in marine engineering operations and ensuring their safety. In addition, this scheme can be applied to other practical systems with
{"title":"Event-Driven Prescribed Optimal Disturbance Rejection for Dynamic Positioning of Ships via Reinforcement Learning","authors":"Xiaoyang Gao;Xin Hu;Jiarui Liu;Tieshan Li","doi":"10.1109/TASE.2026.3660669","DOIUrl":"10.1109/TASE.2026.3660669","url":null,"abstract":"Dynamic positioning (DP) stands as the keystone underpinning ships’ operations in the abyssal depths and remote oceans. This paper proposes an event-driven disturbance rejection approximate optimal dynamic positioning scheme for surface ships with prescribed performance via reinforcement learning (RL). Firstly, a disturbance observer is established to achieve the online estimations of marine environmental disturbances such that the undesirable disturbance effects on control performance can be reduced. Meanwhile, the positioning error transformations with the prescribed performance function is established to combine with the backstepping method and the virtual controller can be designed to constrain the positioning error. Then, for the velocity error surface, the RL method provides the actor-critic architecture to approximate the actual optimal commanded control law and minimized the specified performance index function. Subsequently, the optimal commanded control design incorporates the event-driven mechanism to avoid communication resource waste as well as actuator wear and tear. By applying the Lyapunov stability theory, it is proven that the designed RL control law forces the ship’s actual position and yaw angle to converge to desired target with prescribed performance while ensuring all signals in the closed-loop system are uniformly ultimately bounded. The feature of this paper is the reasonable integration of prescribed performance and RL, which ensures that the performance index function of the ship is minimized while keeping the DP error within the safety range. Finally, simulations with comparisons based on a sea launch ship show the effectiveness further validating the superiority of the RL control scheme. Note to Practitioners—In practical engineering, DP ships are often used to perform challenging special tasks such as drilling, cable laying, and satellite launching, and thus inevitably operate in harsh sea conditions for long periods. Issues concerning its safety and energy efficiency deserve in-depth consideration. These include safety constraints on ship position and heading during positioning, exposure to unknown ocean disturbances, as well as the crucial need to conserve energy consumption, communication resources, and thruster actuation frequency. Different from existing DP systems based on prescribed performance robust control, the RL-based event-driven prescribed performance disturbance rejection optimal control scheme developed in this paper can synergistically keep the positioning error within a specified range under disturbances. Taking an offshore launch and recovery ship as the simulation object, the comparison results show that the proposed algorithm enables the DP to effectively reduce resources. Our scheme provides a certain foundation for improving the energy-saving capability of DP ships in marine engineering operations and ensuring their safety. In addition, this scheme can be applied to other practical systems with","PeriodicalId":51060,"journal":{"name":"IEEE Transactions on Automation Science and Engineering","volume":"23 ","pages":"4615-4626"},"PeriodicalIF":6.4,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
State-of-the-art generalist manipulation policies have enabled the deployment of robotic manipulators in unstructured human environments. However, these frameworks struggle in cluttered environments primarily because they utilize auxiliary modules for low-level motion planning and control. Motion planning remains challenging due to the high dimensionality of the robot’s configuration space and the presence of workspace obstacles. Neural motion planners have enhanced motion planning efficiency by offering fast inference and effectively handling the inherent multi-modality of the motion planning problem. Despite such benefits, current neural motion planners often struggle to generalize to unseen, out-of-distribution planning settings. This paper reviews and analyzes the state-of-the-art neural motion planners, highlighting both their benefits and limitations. It also outlines a path toward establishing generalist neural motion planners capable of handling domain-specific challenges. For a list of the reviewed papers, please refer to https://davoodsz.github.io/planning-manip-survey.github.io/ Note to Practitioners—The paper reviews and summarizes rapidly evolving studies that leverage deep learning for motion planning of robotic manipulators. As robotic manipulators continue to transition from controlled laboratory environments to real-world settings, the demand for efficient, robust, and adaptable motion planning algorithms grows significantly. Thanks to characteristics such as fast inference time and inherent inductive bias, deep learning has been leveraged to facilitate this transition. This paper extensively reviews state-of-the-art deep learning methods used for motion planning of robotic manipulators, and outlines promising avenues and challenges for future research. It specifically evaluates and summarizes the performance of the most commonly used deep learning methods on various key components of motion planning, such as informed sampling, warm-starting trajectory optimization, and collision checking. This paper can serve as a resource for both experts and newcomers in high-DoF robotic motion planning using deep learning.
{"title":"Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities","authors":"Davood Soleymanzadeh;Ivan Lopez-Sanchez;Hao Su;Yunzhu Li;Xiao Liang;Minghui Zheng","doi":"10.1109/TASE.2026.3660830","DOIUrl":"10.1109/TASE.2026.3660830","url":null,"abstract":"State-of-the-art generalist manipulation policies have enabled the deployment of robotic manipulators in unstructured human environments. However, these frameworks struggle in cluttered environments primarily because they utilize auxiliary modules for low-level motion planning and control. Motion planning remains challenging due to the high dimensionality of the robot’s configuration space and the presence of workspace obstacles. Neural motion planners have enhanced motion planning efficiency by offering fast inference and effectively handling the inherent multi-modality of the motion planning problem. Despite such benefits, current neural motion planners often struggle to generalize to unseen, out-of-distribution planning settings. This paper reviews and analyzes the state-of-the-art neural motion planners, highlighting both their benefits and limitations. It also outlines a path toward establishing generalist neural motion planners capable of handling domain-specific challenges. For a list of the reviewed papers, please refer to <uri>https://davoodsz.github.io/planning-manip-survey.github.io/</uri> Note to Practitioners—The paper reviews and summarizes rapidly evolving studies that leverage deep learning for motion planning of robotic manipulators. As robotic manipulators continue to transition from controlled laboratory environments to real-world settings, the demand for efficient, robust, and adaptable motion planning algorithms grows significantly. Thanks to characteristics such as fast inference time and inherent inductive bias, deep learning has been leveraged to facilitate this transition. This paper extensively reviews state-of-the-art deep learning methods used for motion planning of robotic manipulators, and outlines promising avenues and challenges for future research. It specifically evaluates and summarizes the performance of the most commonly used deep learning methods on various key components of motion planning, such as informed sampling, warm-starting trajectory optimization, and collision checking. This paper can serve as a resource for both experts and newcomers in high-DoF robotic motion planning using deep learning.","PeriodicalId":51060,"journal":{"name":"IEEE Transactions on Automation Science and Engineering","volume":"23 ","pages":"4488-4531"},"PeriodicalIF":6.4,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-02-03DOI: 10.1109/tase.2026.3660357
Ya Liu, Yueer Wu, Fan Zhang, Panfeng Huang, Yingbo Lu, Haitao Chang
{"title":"Collision-free Trajectory Generation and Robust Nonlinear Distributed Model Predictive Control for Tethered Multi-rotor Unmanned Aerial Vehicles","authors":"Ya Liu, Yueer Wu, Fan Zhang, Panfeng Huang, Yingbo Lu, Haitao Chang","doi":"10.1109/tase.2026.3660357","DOIUrl":"https://doi.org/10.1109/tase.2026.3660357","url":null,"abstract":"","PeriodicalId":51060,"journal":{"name":"IEEE Transactions on Automation Science and Engineering","volume":"34 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-02-03DOI: 10.1109/tase.2026.3660614
Jun Zhang, Sheik M. Mohiuddin, Junjian Qi
{"title":"Distributed Optimal Control for Grid-Forming and Grid-Feeding Converters in DC Microgrid","authors":"Jun Zhang, Sheik M. Mohiuddin, Junjian Qi","doi":"10.1109/tase.2026.3660614","DOIUrl":"https://doi.org/10.1109/tase.2026.3660614","url":null,"abstract":"","PeriodicalId":51060,"journal":{"name":"IEEE Transactions on Automation Science and Engineering","volume":"117 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-02-03DOI: 10.1109/TASE.2026.3660685
Jinsen Zhang;Xiaobing Nie;Jinde Cao;Liang Hua
This paper studies the finite-time multistability of impulsive Hopfield neural networks with a general class of activation functions. First, the existence of $prod _{i=1}^{n}(2M_{i}+1)$ equilibrium points and $prod _{i=1}^{n}(M_{i}+1)$ invariant sets in such $n$ -neuron neural networks can be guaranteed by applying the Brouwer’s fixed-point theorem as well as upper and lower functions method. Furthermore, it is demonstrated that these equilibrium points and invariant sets remain valid for the same neural networks when subjected to an appropriate controller. Then, on the basis of Lyapunov function method and impulsive control theory, two finite-time multistability theorems are established for Hopfield neural networks under distinct impulse scenarios: stabilizing impulses and destabilizing impulses. The settling time estimations for determining the local finite-time stability of $prod _{i=1}^{n}(M_{i}+1)$ equilibrium points are developed by designing general impulsive sequences, which reveal that the settling time is dependent on initial state, impulsive effects and control parameters. From the perspective of impulsive effects, the introduced stabilizing impulses in neural networks not only accelerate the convergence rate but also yield tighter upper bound of settling time estimation relative to impulse-free systems. In stark contrast, destabilizing impulses significantly degrade the convergence performance while resulting in more conservative upper bound of settling time estimation. Finally, theoretical results are shown to be effective by two illustrative examples and two associative memory applications of grayscale image. Note to Practitioners—Multistability analysis, which investigates the coexistence and and local stability of multiple equilibrium points in dynamical systems, is directly applicable to some critical areas such as associative memory, pattern recognition, and combinatorial optimization, where each stable equilibrium point can represent a stored pattern or a feasible solution. However, prevailing multistability results primarily focus on asymptotic or exponential stability of these equilibria, which often fails to meet practical engineering requirements due to slow convergence speed and limited steady-state accuracy. To overcome these limitations, we design a novel controller coupled with a suitably constructed impulsive sequence that drives the system trajectory to multiple stable equilibrium points within the settling time. This approach guarantees significantly accelerated convergence and enhanced precision, offering a practical and effective solution for implementing high-speed and high-accuracy intelligent systems.
{"title":"Finite-Time Multistability of Impulsive Hopfield Neural Networks Under New Impulsive Sequence Designs","authors":"Jinsen Zhang;Xiaobing Nie;Jinde Cao;Liang Hua","doi":"10.1109/TASE.2026.3660685","DOIUrl":"10.1109/TASE.2026.3660685","url":null,"abstract":"This paper studies the finite-time multistability of impulsive Hopfield neural networks with a general class of activation functions. First, the existence of <inline-formula> <tex-math>$prod _{i=1}^{n}(2M_{i}+1)$ </tex-math></inline-formula> equilibrium points and <inline-formula> <tex-math>$prod _{i=1}^{n}(M_{i}+1)$ </tex-math></inline-formula> invariant sets in such <inline-formula> <tex-math>$n$ </tex-math></inline-formula>-neuron neural networks can be guaranteed by applying the Brouwer’s fixed-point theorem as well as upper and lower functions method. Furthermore, it is demonstrated that these equilibrium points and invariant sets remain valid for the same neural networks when subjected to an appropriate controller. Then, on the basis of Lyapunov function method and impulsive control theory, two finite-time multistability theorems are established for Hopfield neural networks under distinct impulse scenarios: stabilizing impulses and destabilizing impulses. The settling time estimations for determining the local finite-time stability of <inline-formula> <tex-math>$prod _{i=1}^{n}(M_{i}+1)$ </tex-math></inline-formula> equilibrium points are developed by designing general impulsive sequences, which reveal that the settling time is dependent on initial state, impulsive effects and control parameters. From the perspective of impulsive effects, the introduced stabilizing impulses in neural networks not only accelerate the convergence rate but also yield tighter upper bound of settling time estimation relative to impulse-free systems. In stark contrast, destabilizing impulses significantly degrade the convergence performance while resulting in more conservative upper bound of settling time estimation. Finally, theoretical results are shown to be effective by two illustrative examples and two associative memory applications of grayscale image. Note to Practitioners—Multistability analysis, which investigates the coexistence and and local stability of multiple equilibrium points in dynamical systems, is directly applicable to some critical areas such as associative memory, pattern recognition, and combinatorial optimization, where each stable equilibrium point can represent a stored pattern or a feasible solution. However, prevailing multistability results primarily focus on asymptotic or exponential stability of these equilibria, which often fails to meet practical engineering requirements due to slow convergence speed and limited steady-state accuracy. To overcome these limitations, we design a novel controller coupled with a suitably constructed impulsive sequence that drives the system trajectory to multiple stable equilibrium points within the settling time. This approach guarantees significantly accelerated convergence and enhanced precision, offering a practical and effective solution for implementing high-speed and high-accuracy intelligent systems.","PeriodicalId":51060,"journal":{"name":"IEEE Transactions on Automation Science and Engineering","volume":"23 ","pages":"4627-4638"},"PeriodicalIF":6.4,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146109882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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：