Trajectory Tracking Control for Wheel Mobile Robots on Bank Road

Abstract

This paper investigates a trajectory tracking control strategy for an Ackerman-steering four-wheeled mobile robot (WMR) with front-wheel steering and rear-wheel drive. When the WMR is driving on a bank road, the overshoot significantly increases during the initial tracking phase, leading to reduced tracking performance. A nonlinear extended state observer based on a radial basis function neural network (RBFNN-NESO) has been proposed to estimate disturbances in the WMR and reduce initial overshoot, thereby improving estimation accuracy. Then an error feedback control method is employed to propose a finite-time nonlinear controller, which ensures the convergence of velocity and position errors. Finally, experimental results are provided to demonstrate the effectiveness of the proposed WMR controller.