Design of Observer-Based Control With Residual Generator Using Actor-Critic Reinforcement Learning

被引：0

作者：

Qian L. ^{[1
]}

Zhao X. ^{[2
]}

Liu P. ^{[2
]}

Zhang Z. ^{[2
]}

Lv Y. ^{[1
]}

机构：

[1] Wuhan University of Technology, School of Transportation and Logistics Engineering, Wuhan

[2] Huazhong University of Science and Technology, State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Wuhan

来源：

IEEE Transactions on Artificial Intelligence | 2023年 / 4卷 / 04期

基金：

中国国家自然科学基金;

关键词：

Observer-based control; reinforcement learning (RL); residual generator; robot;

D O I：

10.1109/TAI.2022.3215671

中图分类号：

学科分类号：

摘要：

Observer-based control has been widely used in mechatronic systems. In this article, an observer-based control integrated with a residual generator is designed in the framework of actor-critic reinforcement learning, which has been applied to robot systems. In the learning process, a critic function is constructed by the state of the original system and its twin system. Thus, the system parameters and control gain can be obtained simultaneously through trial-and-error learning. To achieve system stability and reliability, the observer-based control with the residual generator is designed based on the learned results. The performance and effectiveness of the proposed scheme are demonstrated through a robot test rig. After a short period of learning, the robot is controlled only with the measured joint angle, and meanwhile, the residual generator can be used for fault detection to improve the system reliability. © 2020 IEEE.

引用

页码：734 / 743

页数：9

共 50 条

[1] Actor-Critic based Improper Reinforcement Learning
Zaki, Mohammadi
Mohan, Avinash
Gopalan, Aditya
Mannor, Shie
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
[2] Actor-Critic Reinforcement Learning for Tracking Control in Robotics
Pane, Yudha P.
Nageshrao, Subramanya P.
Babuska, Robert
[J]. 2016 IEEE 55TH CONFERENCE ON DECISION AND CONTROL (CDC), 2016, : 5819 - 5826
[3] Actor-Critic Reinforcement Learning for Control With Stability Guarantee
Han, Minghao
Zhang, Lixian
Wang, Jun
Pan, Wei
[J]. IEEE ROBOTICS AND AUTOMATION LETTERS, 2020, 5 (04) : 6217 - 6224
[4] USING ACTOR-CRITIC REINFORCEMENT LEARNING FOR CONTROL AND FLIGHT FORMATION OF QUADROTORS
Torres, Edgar
Xu, Lei
Sardarmehni, Tohid
[J]. PROCEEDINGS OF ASME 2022 INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION, IMECE2022, VOL 5, 2022,
[5] Simultaneous Vibration Control and Energy Harvesting Using Actor-Critic Based Reinforcement Learning
Loong, Cheng Ning
Chang, C. C.
Dimitrakoloulos, Elias G.
[J]. ACTIVE AND PASSIVE SMART STRUCTURES AND INTEGRATED SYSTEMS XII, 2018, 10595
[6] Actor-Critic reinforcement learning based on prior knowledge
[J]. Yang, Zhenyu, 1600, Transport and Telecommunication Institute, Lomonosova street 1, Riga, LV-1019, Latvia (18):
[7] Disturbance observer based actor-critic learning control for uncertain nonlinear systems
Liang, Xianglong
Yao, Zhikai
Ge, Yaowen
Yao, Jianyong
[J]. CHINESE JOURNAL OF AERONAUTICS, 2023, 36 (11) : 271 - 280
[8] Disturbance observer based actor-critic learning control for uncertain nonlinear systems
Xianglong LIANG
Zhikai YAO
Yaowen GE
Jianyong YAO
[J]. Chinese Journal of Aeronautics, 2023, (11) : 271 - 280
[9] Disturbance observer based actor-critic learning control for uncertain nonlinear systems
Xianglong LIANG
Zhikai YAO
Yaowen GE
Jianyong YAO
[J]. Chinese Journal of Aeronautics, 2023, 36 (11) : 271 - 280
[10] A deep residual reinforcement learning algorithm based on Soft Actor-Critic for autonomous navigation
Wen, Shuhuan
Shu, Yili
Rad, Ahmad
Wen, Zeteng
Guo, Zhengzheng
Gong, Simeng
[J]. EXPERT SYSTEMS WITH APPLICATIONS, 2025, 259

← 1 2 3 4 5 →