•  
  •  
 

Abstract

Over the past decades, numerous studies have explored the use of autonomous unmanned surface vehicles (USVs). Successful USV operation requires a robust tracking control system to perform a range of tasks. However, USV dynamics are uncertain, time-varying, and nonlinear. This paper presents a neural network-based sliding mode adaptive control (NNSMAC) system to enhance USV tracking performance. Trajectories were generated using spline and polynomial interpolation based on a set of N predefined waypoints. Simulation results show that the proposed method outperforms traditional sliding mode control in error reduction, enabling more effective tracking.

Download
COinS