Adaptive Sliding Mode Controller for Course Keeping of Unmanned Surface Vehicle

Abstract

A course keeping controller for unmanned surface vehicle (USV) is proposed in this paper. The USV is a very complicated, nonlinear and uncertain system. Considering that the parameters of the USV are time-varying. They vary with the condition of the ship and the varying navigation environment. An adaptive course keeping controller combines sliding mode technology and radial basis function neural network is developed. It has strong robustness. The radial basis function neural network is used for realizing the adaptive approximation of the nonlinear and uncertain part, and the sliding mode control is combined to realize the tracking of the desired heading angle. The adaptive laws of the neural network weights are derived by Lyapunov stability theorem, so as to guarantee the stability and convergence of the whole closed-loop system. The simulations are given to validate that the designed controller can make the course keeping accurately and quickly.