Optimal fuzzy output feedback tracking control for unmanned surface vehicles systems

Abstract

This study investigates an optimal fuzzy output feedback tracking control problem with a Q-learning algorithm on unmanned surface vehicles (USVs) with immeasurable velocities information. Firstly, the USVs are modeled by a Takagi–Sugeno (T–S) fuzzy system. Based on the fuzzy system, an ideal optimal fuzzy output feedback tracking controller is proposed by utilizing reconstruction states, measured output and input data. Theoretically, the analytical solution of the designed optimal controller is reduced to solving the algebraic Riccati equations (AREs). Due to the difficulty of solving AREs directly, a Q-learning value iteration algorithm is proposed to obtain its approximation solution. Furthermore, it is rigorously mathematically proved that the proposed Q-learning algorithm can approximate the ideal solution and guarantee the USVs output to track the desired reference signal. Ultimately, the simulation and comparison results with the existing control method verify the efficacy and advantage of the presented fuzzy optimal output feedback tracking control approach with a Q-learning algorithm.