A neural network based adaptive control scheme for underwater vehicles with an observer

Observer-based neural network adaptive control scheme (OBNC) for underwater vehicles is proposed in this paper. Three parts compose the scheme: output feedback control, neural network and sliding mode item. Where, the output feedback control is used to guarantee the stability of the system in initial phase, and the neural network is used to approximate the nonlinear dynamics of underwater vehicles and the sliding mode item is used to compensate and bate the internal and external disturbances. A linear observer is designed to estimate the corresponding rate and the control system is designed with only position measurement. The stability conditions and attraction region of the proposed scheme is provided by using Lyapunov-based approach. The effectiveness of the proposed control scheme is demonstrated by the pool experiment.