中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Synergetic learning for unknown nonlinear H. control using neural networks

文献类型：期刊论文

作者Zhu, Liao4,5; Guo, Ping4,5; Wei, Qinglai1,2,3
刊名NEURAL NETWORKS
出版日期2023-11-01
卷号168页码:287-299
关键词H. control Nonlinear systems Adaptive dynamic programming Temporal difference Neural network Data-driven
ISSN号0893-6080
DOI10.1016/j.neunet.2023.09.029
通讯作者Guo, Ping(pguo@bnu.edu.cn)
英文摘要The well-known H. control design gives robustness to a controller by rejecting perturbations from the external environment, which is difficult to do for completely unknown affine nonlinear systems. Accordingly, the immediate objective of this paper is to develop an on-line real-time synergetic learning algorithm, so that a data-driven H. controller can be received. By converting the H. control problem into a two-player zero-sum game, a model-free Hamilton-Jacobi-Isaacs equation (MF-HJIE) is first derived using off-policy reinforcement learning, followed by a proof of equivalence between the MF-HJIE and the conventional HJIE. Next, by applying the temporal difference to the MF-HJIE, a synergetic evolutionary rule with experience replay is designed to learn the optimal value function, the optimal control, and the worst perturbation, that can be performed on-line and in real-time along the system state trajectory. It is proven that the synergistic learning system constructed by the system plant and the evolutionary rule is uniformly ultimately bounded. Finally, simulation results on an F16 aircraft system and a nonlinear system back up the tractability of the proposed method.
WOS关键词STATE-FEEDBACK CONTROL ; ZERO-SUM GAMES ; POLICY UPDATE ALGORITHM ; SYSTEMS ; EQUATION
资助项目National Key Research and Development Program of China[2018AAA0100203] ; National Key Research and Development Program of China[2021YFE0206100] ; National Natural Science Foun-dation of China[62073321] ; Science and Technology Development Fund, Macau SAR[0060/2021/A]
WOS研究方向Computer Science ; Neurosciences & Neurology
语种英语
WOS记录号WOS:001086806900001
出版者PERGAMON-ELSEVIER SCIENCE LTD
资助机构National Key Research and Development Program of China ; National Natural Science Foun-dation of China ; Science and Technology Development Fund, Macau SAR
源URL[http://ir.ia.ac.cn/handle/173211/54334]  
专题多模态人工智能系统全国重点实验室
自动化研究所_复杂系统管理与控制国家重点实验室_智能化团队
通讯作者Guo, Ping
作者单位1.Macau Univ Sci & Technol, Inst Syst Engn, Taipa 999078, Macau, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
4.Beijing Normal Univ, Sch Syst Sci, Beijing 100875, Peoples R China
5.Beijing Normal Univ, Int Acad Ctr Complex Syst, Zhuhai 519087, Guangdong, Peoples R China
推荐引用方式
GB/T 7714		 Zhu, Liao,Guo, Ping,Wei, Qinglai. Synergetic learning for unknown nonlinear H. control using neural networks[J]. NEURAL NETWORKS,2023,168:287-299.
APA Zhu, Liao,Guo, Ping,&Wei, Qinglai.(2023).Synergetic learning for unknown nonlinear H. control using neural networks.NEURAL NETWORKS,168,287-299.
MLA Zhu, Liao,et al."Synergetic learning for unknown nonlinear H. control using neural networks".NEURAL NETWORKS 168(2023):287-299.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。