Adaptive RBF neural network control for unmanned surface vessel course tracking

Abstract

This paper presents an adaptive Radial Basis Function (RBF) neural network controller for the nonlinear course control of unmanned surface vessel (USV) with modeling errors and unknown bounded environment disturbances. An adaptive RBF neural network system is employed to approximate the uncertain term induced by modeling errors and unknown bounded environment disturbances. It is theoretically proved that the proposed adaptive RBF neural network controller can make the USV be tracked the designed heading angle and turning rate with arbitrary accuracy, while guaranteeing the asymptotic stability of the closed-loop course tracking control system of USV. Comparative studies are carried out between the proposed control scheme and the PD control under the same control parameters, and the results show that the proposed control scheme has a good performance.