Adaptive Neural Network Position/force Control of Robot Manipulators with Model Uncertainties*

In this paper, adaptive neural network position/force control of robot manipulators with model uncertainties is considered. The controller combines a neural network modeling technique with self-tuning fuzzy control which describes the relationship between force and position/velocity error. And robust control can be easily incorporated to suppress the neural network modeling errors and the bounded disturbances. Simulation results based on 2-DOF robot show the effectiveness of this approach