Global sliding mode based adaptive neural network path following control for underactuated surface vessels with uncertain dynamics

Abstract

An adaptive neural network (NN) control scheme is proposed for path following control of underactuated surface vessels with only the surge and the yaw moment available, despite the presence of uncertain parameters and unstructured uncertainties including exogenous disturbances and measurement noise, etc. The control scheme is developed by integrating an NN approach and the adaptive implementation of the global sliding mode control. A global sliding mode control approach is developed to provide a framework for ensuring the existence of a sliding mode throughout the entire response, and can force the system state to be within the state region in which the NN is used when the system goes out of NNs control. Based on the Lyapunov stability theory, the uniform ultimate boundedness of the following error is proved. Numerical simulation results are provided to illustrate the effectiveness of the proposed controller and the accuracy of stability analysis.