Fuzzy optimal tracking control for nonlinear underactuated unmanned surface vehicles

In this paper, a reinforcement Q-learning fuzzy optimal tracking control method is investigated for nonlinear underactuated unmanned surface vehicles (USVs) with external disturbances. Firstly, the motion dynamics of USVs are described by the Takagi-Sugeno (T-S) fuzzy discrete-time systems. Secondly, by applying parallel distributed compensation (PDC) method and constructing cost function, the existence condition of optimal solutions is derived and reduced to the algebraic Riccati equations (AREs). To solve the solutions of the GAREs, a Q-learning value iteration (VI) algorithm is further developed, which can be implemented by eliminating the demand of initial allowable control policy and system information. The developed strategy has the advantage that the optimal control policy can ensure the USV to be stable and the desired reference signal can also be well tracked by the USV output. Finally, the proposed fuzzy optimal control algorithm is applied to control the USV, the simulation results verify the feasibility of the proposed optimal control algorithm.

Automated summary

This paper investigates a reinforcement Q-learning fuzzy optimal tracking control method for nonlinear underactuated unmanned surface vehicles (USVs) with external disturbances. The motion dynamics of USVs are described using the Takagi-Sugeno (T-S) fuzzy discrete-time systems. The existence condition of optimal solutions is derived by applying the parallel distributed compensation (PDC) method and constructing a cost function. A Q-learning value iteration (VI) algorithm is developed to solve the solutions of the algebraic Riccati equations (AREs).