控制理论(社会学)
趋同(经济学)
弹道
计算机科学
理论(学习稳定性)
强化学习
跟踪(教育)
李雅普诺夫函数
迭代学习控制
自适应控制
跟踪误差
极限(数学)
标识符
Lyapunov稳定性
功能(生物学)
控制系统
控制工程
鲁棒控制
方案(数学)
机械臂
控制(管理)
机器人学
数学
机械手
最优控制
作者
Yuzhu Xiang,Weiwei Yi,Mohammed Chadli,Jian Chun Guo,Sheng Li,Zhengrong Xiang
出处
期刊:IEEE-ASME Transactions on Mechatronics
[Institute of Electrical and Electronics Engineers]
日期:2025-10-03
卷期号:31 (2): 1764-1774
被引量:28
标识
DOI:10.1109/tmech.2025.3612986
摘要
In this article, a reinforcement learning (RL)-based fixed-time trajectory tracking control scheme is proposed for robotic manipulators, where the unknown disturbances and model uncertainties are considered. A nonsingular fast terminal sliding surface is designed to guarantee the fixed-time convergence of the tracking error, with an estimation of the upper limit for the convergence time provided. A performance index function is formulated, incorporating both the tracking error and input cost. By employing an adaptive identifier and a critic, we develop an RL-based optimal tracking control scheme, where the convergence time is independent of initial conditions. The stability of the system and the fixed-time convergence of the closed-loop system are demonstrated via Lyapunov theory. Physical simulations and experiments are carried out to verify the feasibility of the proposed control strategy.
科研通智能强力驱动
Strongly Powered by AbleSci AI