Intelligent position/force control for uncertain robot using neural network compensation

The performance of robot force tracking control is affected by the uncertainties in both the robot dynamic model and environment stiffness. The purpose of this paper is to improve the controller robustness by applying the neural network (NN) technique to compensate for the uncertainties of the robot model at input trajectory level rather than at the joint torque level. In addition, a self-adaptive fuzzy controller is introduced for robot manipulator position/force control. Simulation results based on a two-DOF robot show that highly robust position/force tracking can be achieved in the presence of large uncertainties in the robot model.