NN-Based Predefined-Time 3D Trajectory Tracking Control of AUV with Prescribed Performance

This paper investigates predefined-time 3D trajectory tracking control problem of autonomous underwater vehicle (AUV) with prescribed-performance, external disturbances and unmodeled dynamics. By combining the radial basis function neural network (NN) and a prescribed-time sliding surface, a NN-based predefined-time control (N<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>BPTC) algorithm is designed to solve the above problem. It is proven that the 3D trajectory tracking errors can converge to the small set around the origin within the predefined time with prescribed steady-state performance. Some sufficient conditions of the closed-loop system are obtained by using Lyapunov stability. Finally, simulation examples are proposed to validate the theoretical analysis.