Adaptive Neural Network Impedance Control of Robots Based on Reference Model

Abstract

Adaptive neural impedance control based on reference impedance model is introduced. Both model parameter uncertainties and model uncertainties are considered in controller design. The designed controller based reference impedance model ensure similar dynamics between robot and reference model. In order to handle model parameter uncertainties, the adaptive controller is designed and model uncertainties is estimated with neural network based radial basis function. System closed-loop stability is proved by Lyapunov theorem and the performance of proposed control method is verified by simulation with two-DOFs robot.