Adaptive neural network and extended state observer-based non-singular terminal sliding modetracking control for an underactuated USV with unknown uncertainties

Abstract

In this paper, a non-singular terminal sliding mode control (NTSMC) scheme based on adaptive neural network (NN) and nonlinear extended state observer (ESO) is proposed for trajectory tracking control of the underactuated unmanned surface vehicle (USV) in the presence of model uncertainties and external disturbances. Firstly, a three-degree-of-freedom USV nonlinear mathematical model is established, then a nonlinear ESO is constructed to estimate the unmeasurable velocities and lumped disturbances. Besides, a neural shunt model is introduced to eliminate the repetitive derivative of the virtual control law and reduce the difficulty of the control law design. On the basis of these and considering the USV position and speed errors, a non-singular terminal sliding surface is constructed to achieve fast convergence. Meanwhile, the minimum learning parameter (MLP) neural network algorithm is designed to estimate the model uncertainties. Subsequently, an adaptive law is designed to compensate for the NN approximation errors and disturbances, which reduces the computational burden and enhances the robustness of the system. Finally, by using Lyapunov theory, it is proved that the designed control law can guarantee the uniform boundedness of all error signals in the closed-loop system. Comparative simulation results further confirm the effectiveness and superiority of the proposed method.

More information

Identifiers

ORCID for Tahsin Tezdogan: orcid.org/0000-0002-7032-3038

Catalogue record

Export record

Altmetrics