Motion control of an AUV using a neural network adaptive controller

This paper presents a neural network adaptive controller for autonomous underwater vehicles (AUVs). A linearly parameterized neural network (LPNN) is used to approximate the nonlinear uncertainties of AUV dynamics, where the basis function vector of LPNN is constructed according to the physical properties of the AUV. A sliding mode control scheme is adopted to attenuate the effects of network reconstruction errors and disturbances in AUV dynamics. The asymptotic convergence of AUV tracking errors and the stability of the presented control system are guaranteed on the basis of Lyapunov theory. Numerical simulation studies for motion control of an AUV are performed to illustrate the effectiveness of the proposed controller.