Fully-tuned fuzzy neural network based robust adaptive tracking control of unmanned underwater vehicle with thruster dynamics

Abstract

In this paper, a fully-tuned fuzzy neural network based robust adaptive control (FFNNBARC) scheme for trajectory and attitude tracking of Unmanned Underwater Vehicle (UUV) subject to thruster dynamics and unknown disturbances, is proposed. The FFNNBRAC consists of a fully-tuned fuzzy neural network (FFNN) controller and a robust controller, where the FFNN estimation is introduced to approximate a backstepping control law, and the robust controller is proposed to provide the finite L2-gain property which can cope with reconstruction errors and can enhance the robustness of the overall control system. As a sequence, the FFNNBRAC scheme is able to render tracking errors asymptotically converge to zero and can guarantee all signals are bounded. Simulation studies and comparisons demonstrate the effectiveness and superiority of the FFNNBRAC scheme in terms of robustness and accuracy.