Neural Net Based Nonlinear Adaptive Control for Autonomous Underwater Vehicles

Since the dynamics of autonomous underwater vehicles (AUVs) are highly nonlinear and their hydrodynamic coefficients vary with different operating conditions, a high performance control system of an AUV is needed to have the capacities of learning and adaptation to the variations of the AUV’s dynamics. In this paper, a linearly parameterized neural network (LPNN) is used to approximate the uncertainties of the vehicles’ dynamics, where the basis function vector of the network is constructed according to the vehicle’s physical properties. The proposed controller guarantees uniform boundedness of the vehicle’s trajectory tracking errors and network’s weights estimation errors based on Lyapunov stability theory, where the network’s reconstruction errors and the disturbances in the vehicle’s dynamics are bounded by unknown constant. Numerical simulation studies are performed to illustrate the effectiveness of the proposed control scheme.