A Neural Network Algorithm for the Error Optimization in the Path Tracking Control of a Mobile Robot

Abstract

In this paper a nonholonomic mobile robot with completely unknown dynamics is discussed. A mathematical model has been considered and an efficient neural network is developed, which is capable of compensating errors both in position and velocity ensuring guaranteed tracking performance. The neural network assumes a single layered structure, by taking advantage of the robot regressor that expresses the highly nonlinear robot dynamics in a linear form in terms of the known and unknown robot dynamic parameters. It does not require any offline training procedures. Lyapunov theory has been used to prove system stability. The practicality and effectiveness of the proposed tracking algorithm are demonstrated by simulation and comparison results.