Neural Network Based Robust Adaptive Dynamic Surface Control for AUVs

Abstract

Abstract A neural network controller is presented for tracking control of underwater vehicles with uncertainties. By employing the neural network method to account for system uncertainties, the proposed scheme is developed by combining “dynamic surface control(DSC)”. Consequently, the problem of “explosion of complexity” inherent in the conventional backstepping method is avoided. Modeling errors and environmental disturbance are considered in the mathematical model. A two-layer neural network is introduced to compensate the modeling errors, while the effect of the environmental disturbance is addressed by using the property of hyperbolic tangent function. Under the developed tracking control approach, semi-global uniform boundedness of all closed-loop signals are guaranteed via Lyapunov analysis. Simulation studies are given to illustrate the effectiveness of the proposed tracking control.