Adaptive Neural-Based Finite-Time Trajectory Tracking Control for Underactuated Marine Surface Vessels With Position Error Constraint

Abstract

This paper addresses the trajectory tracking control problem of an underactuated marine surface vessel with position error constraint, finite-time convergence requirement, model uncertainties, and external disturbances. A barrier Lyapunov function is incorporated with the backstepping control scheme to handle the position error constraint. The command filters and auxiliary systems are designed to avoid the tedious analytical computation of the virtual control laws. Furthermore, an adaptive radial basis function neural network is adopted to provide the estimation of the unknown hydrodynamic damping term, and a disturbance observer is designed to compensate for the lumped disturbances including the neural approximation errors and external ocean disturbances. We show that under the proposed control scheme, the tracking errors of the vessel can converge to a small neighborhood around 0 within finite time, while the constraint on the vessel position is never violated during the maneuver, and all closed-loop signals are proved to be bounded. Finally, a numerical simulation is provided to illustrate the effectiveness and superiority of the proposed control scheme.