Design of robust adaptive neural course controller for unmanned surface vehicle based on trajectory linearization control

This paper proposes a novel course controller on unmanned surface vehicle (USV) by using the methods of robust adaptive neural network trajectory linearization control (TLC). TLC is an effective control method for solving nonlinear tracking and system decoupling. However, the performance of the current TLC control strategy will be significantly decreased when there is a large the uncertainty of model. To enhance performance of the systems, Radial Basis Function Neural Network (RBFNN) is introduced to approximate the uncertainty of model to achieve real-time online compensation. It is proven that all error signals in the system are uniformly ultimately bounded by Lyapunov function. Finally, simulation results are presented to illustrate the effectiveness of the control strategy.