IEEE Transactions on Cybernetics最新文献_第10页

Cooperative Multiagent Learning and Exploration With Min–Max Intrinsic Motivation 最小-最大内在动机下的合作多智能体学习与探索

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/TCYB.2025.3557694

Yaqing Hou;Jie Kang;Haiyin Piao;Yifeng Zeng;Yew-Soon Ong;Yaochu Jin;Qiang Zhang

{"title":"Cooperative Multiagent Learning and Exploration With Min–Max Intrinsic Motivation","authors":"Yaqing Hou;Jie Kang;Haiyin Piao;Yifeng Zeng;Yew-Soon Ong;Yaochu Jin;Qiang Zhang","doi":"10.1109/TCYB.2025.3557694","DOIUrl":"10.1109/TCYB.2025.3557694","url":null,"abstract":"In the field of multiagent reinforcement learning (MARL), the ability to effectively explore unknown environments and collect information and experiences that are most beneficial for policy learning represents a critical research area. However, existing work often encounters difficulties in addressing the uncertainties caused by state changes and the inconsistencies between agents’ local observations and global information, which presents significant challenges to coordinated exploration among multiple agents. To address this issue, this article proposes a novel MARL exploration method with Min-Max intrinsic motivation (E2M) that promotes the learning of joint policies of agents by introducing surprise minimization and social influence maximization. Since the agent is subject to unstable state changes in the environment, we introduce surprise minimization by computing state entropy to encourage the agents to cope with more stable and familiar situations. This method enables surprise estimation based on the low-dimensional representation of states obtained from random encoders. Furthermore, to prevent surprise minimization from leading to conservative policies, we introduce mutual information between agents’ behaviors as social influence. By maximizing social influence, the agents are encouraged to interact to facilitate the emergence of cooperative behavior. The performance of our proposed E2M is testified across a range of popular StarCraft II and Multiagent MuJoCo tasks. Comprehensive results demonstrate its effectiveness in enhancing the cooperative capability of the multiple agents.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2852-2864"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849813","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}

引用次数: 0

Dynamic Locomotion Synchronization and Fuzzy Control of a Lower Limb Exoskeleton With Body Weight Support for Active Following Human Operator 负重支撑下肢外骨骼动态运动同步与模糊控制

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/TCYB.2025.3558616

Guoxin Li;Jiacheng Xu;Zhijun Li;Rong Song;Yu Kang

{"title":"Dynamic Locomotion Synchronization and Fuzzy Control of a Lower Limb Exoskeleton With Body Weight Support for Active Following Human Operator","authors":"Guoxin Li;Jiacheng Xu;Zhijun Li;Rong Song;Yu Kang","doi":"10.1109/TCYB.2025.3558616","DOIUrl":"10.1109/TCYB.2025.3558616","url":null,"abstract":"Despite remarkable progress in robotic exoskeletons, exoskeletons are still far from matching human-level guidance and locomotion performance in gait training or movement enhancement. A desirable exoskeleton would first provide a standard gait profile by learning from human operators while requiring body weight support with active human-following to govern dynamic locomotion synchronization. To address these issues, in this article, we propose a human operator-involved dynamic locomotion synchronization control framework for the lower limb exoskeleton actively following gait training with gravity-supporting. First, we designed a human motion capture system based on a five-link model for the locomotion of a human operator. To reproduce human-level motor skills, we use whole-body teleoperation to leverage human control intelligence to command the locomotion of a robotic exoskeleton system. Specifically, using the linear inverted pendulum (LIP) model, the human operator’s divergent component of motion (DCM) is obtained by the human motion capture system. The dynamic similarity is used to generate a reference DCM for the robotic exoskeleton to synchronize the human operator’s movement. Finally, a fuzzy-based adaptive controller is designed to track the synchronous trajectory for the exoskeleton in the presence of robotic dynamics uncertainties with input saturation. Experiments on the human subject are carried out to demonstrate the effectiveness of the proposed method.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2792-2805"},"PeriodicalIF":9.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143849783","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}

引用次数: 0

On Consensus Control of Uncertain Multiagent Systems Based on Two Types of Interval Observers 基于两类区间观测器的不确定多智能体系统的一致控制

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-18 DOI: 10.1109/TCYB.2025.3559110

Yuchen Qian;Zhonghua Miao;Jin Zhou;Xiaojin Zhu

引用次数: 0

Robust Reconstructed Neural Network With Spectral Reshaping Activation 采用频谱重塑激活的鲁棒重构神经网络

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-16 DOI: 10.1109/TCYB.2025.3557397

Honggui Han;Zecheng Tang;Xiaolong Wu;Hongyan Yang;Junfei Qiao

引用次数: 0

Intermittent Observer for Chaotic Lur’e Systems With Multi-Nondifferentiable Delay and Partially Limited Output Channels and Its Application to Secure Communication 具有多不可微延迟和部分受限输出信道的混沌Lur系统间歇观测器及其在保密通信中的应用

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-16 DOI: 10.1109/tcyb.2025.3557539

Kui Ding, Quanxin Zhu, Tingwen Huang

引用次数: 0

Observer-Based Periodic Event-Triggered Adaptive Fuzzy Control for Networked Nonlinear Systems 基于观测器的网络非线性系统周期性事件触发自适应模糊控制

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-16 DOI: 10.1109/tcyb.2025.3554702

Ning Zhao, Huiyan Zhang, Xuan Qiu, Ramesh K. Agarwal

引用次数: 0

Iterative Learning Control of Minimum Energy Path Following Tasks for Second-Order MIMO Systems: An Indirect Reference Update Framework 二阶MIMO系统最小能量路径跟踪任务的迭代学习控制：一个间接参考更新框架

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-15 DOI: 10.1109/TCYB.2025.3556703

Yiyang Chen;Yiming Wang;Christopher T. Freeman

{"title":"Iterative Learning Control of Minimum Energy Path Following Tasks for Second-Order MIMO Systems: An Indirect Reference Update Framework","authors":"Yiyang Chen;Yiming Wang;Christopher T. Freeman","doi":"10.1109/TCYB.2025.3556703","DOIUrl":"10.1109/TCYB.2025.3556703","url":null,"abstract":"In a large range of manufacturing tasks, the design objective is characterised as following a given path defined in space. In these applications, the tracking time of any particular position along the path is not specified, so an appropriate motion profile can be chosen among its admissible solutions to improve its tracking performance. This article develops an indirect reference update framework that maximizes accuracy while embedding practical constraints. An optimal path planning problem, incorporating system constraints, is formulated and can be solved using a discretized approach to derive a motion profile that minimizes control energy for a broad spectrum of industrial tasks. To satisfy robustness concerns, an iterative learning control (ILC) algorithm with an indirect reference update framework is designed to improve the accuracy and robustness of path following. It is evaluated on a gantry robot test platform, and the results illustrate superior levels of practical performance in terms of energy reduction and path following accuracy compared with existing approaches.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 7","pages":"3403-3416"},"PeriodicalIF":9.4,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143836825","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}

引用次数: 0

Tomography of Quantum States From Structured Measurements via Quantum-Aware Transformer 基于量子感知变压器的结构化测量的量子态断层扫描

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-14 DOI: 10.1109/TCYB.2025.3556466

Hailan Ma;Zhenhong Sun;Daoyi Dong;Chunlin Chen;Herschel Rabitz

{"title":"Tomography of Quantum States From Structured Measurements via Quantum-Aware Transformer","authors":"Hailan Ma;Zhenhong Sun;Daoyi Dong;Chunlin Chen;Herschel Rabitz","doi":"10.1109/TCYB.2025.3556466","DOIUrl":"10.1109/TCYB.2025.3556466","url":null,"abstract":"Quantum state tomography (QST) is the process of reconstructing the state of a quantum system (mathematically described as a density matrix) through a series of different measurements, which can be solved by learning a parameterized function to translate experimentally measured statistics into physical density matrices. However, the specific structure of quantum measurements for characterizing a quantum state has been neglected in previous work. In this article, we explore the similarity between highly structured sentences in natural language and intrinsically structured measurements in QST. To fully leverage the intrinsic quantum characteristics involved in QST, we design a quantum-aware transformer (QAT) model to capture the complex relationship between measured frequencies and density matrices. In particular, we query quantum operators in the architecture to facilitate informative representations of quantum data and integrate the Bures distance into the loss function to evaluate quantum state fidelity, thereby enabling the reconstruction of quantum states from measured data with high fidelity. Extensive simulations and experiments (on IBM quantum computers) demonstrate the superiority of the QAT in reconstructing quantum states with favorable robustness against experimental noise.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2571-2582"},"PeriodicalIF":9.4,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831556","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}

引用次数: 0

Impulsive Observer of Linear Systems: An Adaptive Impulsive Gain Approach 线性系统的脉冲观测器：一种自适应脉冲增益方法

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-11 DOI: 10.1109/TCYB.2025.3556721

Xuegang Tan;Jinde Cao;Jianquan Lu

引用次数: 0

Game-Based Event-Triggered Control for Unmanned Surface Vehicle: Algorithm Design and Harbor Experiment 基于博弈的无人水面车辆事件触发控制：算法设计与港口实验

IF 9.4 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2025-04-11 DOI: 10.1109/TCYB.2025.3556042

Guoqing Zhang;Shilin Yin;Jiqiang Li;Wenjun Zhang;Weidong Zhang

{"title":"Game-Based Event-Triggered Control for Unmanned Surface Vehicle: Algorithm Design and Harbor Experiment","authors":"Guoqing Zhang;Shilin Yin;Jiqiang Li;Wenjun Zhang;Weidong Zhang","doi":"10.1109/TCYB.2025.3556042","DOIUrl":"10.1109/TCYB.2025.3556042","url":null,"abstract":"To improve the trajectory tracking performance of unmanned surface vehicle (USV), this article investigates the USV optimal control problem with the consideration of actuator wear. In the proposed algorithm, the USV control system is divide into kinematic subsystem and kinetic subsystem. In particular, corresponding performance indexes that looking forward to be optimized are defined for each subsystem. The related value functions, Hamilton-Jacobi–Bellman equations and optimal control policies are approximated by actor-critic neural networks. To reduce the wear of propeller and rudder, the event-triggered problem is considered as a zero-sum game solving problem, where the best control inputs and worst thresholds are delivered via minmax strategy. Also, the nonlinear uncertainties of the USV are approximated and environment disturbances are compensated in the value functions for better control performance. The USV closed-loop control system is proved semi-globally uniformly ultimately bounded stability via Lyapunov theory. Finally, a simulation case and harbor experiment are illustrated to verify the superiorities and engineering application values of the proposed algorithm.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 6","pages":"2729-2741"},"PeriodicalIF":9.4,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143822848","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}

引用次数: 0