A compensating scheme for robot tracking based on neural networks

Abstract

This paper considers tracking control of robots in joint space. A new control scheme is proposed based on the well-known computed torque method and a neural network based, compensating controller. This scheme takes advantages of the model based control approach and uses the neural network controller to compensate for the robot modelling uncertainties. The neural network is trained on line based on Lyapunov theory and thus its convergence is guaranteed. Simulation results are provided to demonstrate performance of the scheme.