Robust reinforcement learning-based tracking control for wheeled mobile robot

摘要

This paper proposes a method to design a robust reinforcement learning-based tracking control scheme for the wheeled mobile robot. A policy iteration algorithm and a neural network are used to design an adaptive critic robust controller. A H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">¿</sub> - tracking performance index optimal function is evaluated by this con troller. The stability of the closed-loop system while learning is proven by Lyapunov theory. The simulation results for wheeled mobile robot verify the effects of the proposed controller.