RL-Based Adaptive Fuzzy Optimized Tracking Control for Constrained Switched Stochastic Nonlinear Systems: A Modified AED-ADT Method

IF 10.5 1区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

IEEE Transactions on Cybernetics Pub Date : 2025-08-07 DOI:10.1109/TCYB.2025.3590340

Chengyuan Yan;Jing Zhang;Jianwei Xia;Ju H. Park

{"title":"RL-Based Adaptive Fuzzy Optimized Tracking Control for Constrained Switched Stochastic Nonlinear Systems: A Modified AED-ADT Method","authors":"Chengyuan Yan;Jing Zhang;Jianwei Xia;Ju H. Park","doi":"10.1109/TCYB.2025.3590340","DOIUrl":null,"url":null,"abstract":"This study presents a reinforcement learning (RL)-based adaptive fuzzy event-triggered optimized tracking control strategy for slowly switched nonlinear systems with stochastic disturbances in the prescribed set-time performance. The designed optimized event-triggered mechanism for the subsystems effectively solves the asynchronous switching problem with no limit on the maximum asynchronous time. Moreover, the tracking performance of system can be optimized significantly using an RL strategy. Using the lemma proposed in the study (<xref>Lemma 3</xref>) and the normalized function, it is shown that under the performance constraint approach, the selection of the performance function is consistent with the control protocols. By adopting the modified admissible edge-dependent average dwell time method and the optimal controller, the boundedness of closed-loop system signals is proved, and the Zeno phenomenon does not occur. Finally, the superiority of the optimized strategy is verified using numerical simulations and a practical single-link manipulator.","PeriodicalId":13112,"journal":{"name":"IEEE Transactions on Cybernetics","volume":"55 10","pages":"4596-4608"},"PeriodicalIF":10.5000,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Cybernetics","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/11119417/","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

This study presents a reinforcement learning (RL)-based adaptive fuzzy event-triggered optimized tracking control strategy for slowly switched nonlinear systems with stochastic disturbances in the prescribed set-time performance. The designed optimized event-triggered mechanism for the subsystems effectively solves the asynchronous switching problem with no limit on the maximum asynchronous time. Moreover, the tracking performance of system can be optimized significantly using an RL strategy. Using the lemma proposed in the study (Lemma 3) and the normalized function, it is shown that under the performance constraint approach, the selection of the performance function is consistent with the control protocols. By adopting the modified admissible edge-dependent average dwell time method and the optimal controller, the boundedness of closed-loop system signals is proved, and the Zeno phenomenon does not occur. Finally, the superiority of the optimized strategy is verified using numerical simulations and a practical single-link manipulator.

查看原文本刊更多论文

约束切换随机非线性系统基于rl的自适应模糊优化跟踪控制：一种改进的AED-ADT方法。

针对具有随机扰动的慢切换非线性系统，提出了一种基于强化学习的自适应模糊事件触发优化跟踪控制策略。所设计的优化的子系统事件触发机制有效地解决了异步切换问题，不限制最大异步时间。此外，使用强化学习策略可以显著优化系统的跟踪性能。利用本文提出的引理（引理3）和归一化函数，证明了在性能约束方法下，性能函数的选择与控制协议一致。采用改进的允许边相关ADT方法和最优控制器，证明了闭环系统信号的有界性，且不发生芝诺现象。最后，通过数值仿真和实际单连杆机械手验证了优化策略的优越性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Cybernetics COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-COMPUTER SCIENCE, CYBERNETICS

CiteScore

25.40

自引率

11.00%

发文量

1869

期刊介绍： The scope of the IEEE Transactions on Cybernetics includes computational approaches to the field of cybernetics. Specifically, the transactions welcomes papers on communication and control across machines or machine, human, and organizations. The scope includes such areas as computational intelligence, computer vision, neural networks, genetic algorithms, machine learning, fuzzy systems, cognitive systems, decision making, and robotics, to the extent that they contribute to the theme of cybernetics or demonstrate an application of cybernetics principles.