Model-free Optimal Tracking Control for an Aircraft Skin Inspection Robot with Constrained-input and Input Time-delay via Integral Reinforcement Learning

• Published in: International journal of control, automation, and systems Vol. 18; no. 1; pp. 245 - 257
• Main Authors: Wu, Xuewei, Wang, Congqing
• Format: Journal Article
• Language: English
• Published: Bucheon / Seoul Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers 2020; Springer Nature B.V; 제어·로봇·시스템학회
• Subjects: Aircraft; Aircraft control; Algorithms; Computer simulation; Control; Control algorithms; Control theory; Coupling; Delay; Engineering; Inspection; Integrals; Machine learning; Mechatronics; Neural networks; Optimal control; Regular Papers; Robotics; Robots; Sampling; Tracking control; 제어계측공학; Constrained-input; model-free; input time-delay; reinforcement learning
• ISSN: 1598-6446; 2005-4092
• DOI: 10.1007/s12555-019-0351-7

This paper presents a model-free optimal tracking control algorithm for an aircraft skin inspection robot with constrained-input and input time-delay. To tackle the input time-delay problem, the original system is transformed into a delay-free system with constrained-input and unknown input coupling term. In order to overcome the optimal control problem subject to constrained-input, a discounted value function is employed. In general, it is known that the HJB equation does not admit a classical smooth solution. Moreover, since the input coupling term of the delay-free system is unknown, a model-free integral reinforcement learning(IRL) algorithm which only requires the system sampling data generated by arbitrary different control inputs and external disturbances is proposed. The model-free IRL method is implemented on an actor-critic neural network (NN) structure. A system sampling data set is utilized to learn the value function and control policy. Finally, the simulation verifies the effectiveness of the proposed algorithm.