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

Abstract

Observer-based control has been widely used in mechatronic systems. In this paper, an observer-based control integrated with 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 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.