Adaptive impedance control based on dynamic recurrent fuzzy neural network for upper-limb rehabilitation robot

Abstract

The controller design is one of the major difficulties in realizing robot-aided rehabilitation program. The purpose of our study is to develop an adaptive impedance force control strategy based on dynamic recurrent fuzzy neural network to maintain the stability of the rehabilitation robot system in the case when the patient's physical condition makes a change. An on-line identification method was used to estimate impaired limb's mechanical impedance parameters. By using dynamic recurrent fuzzy neural network, desired impedance control parameters between rehabilitation robotic end-effector and upper-limb were regulated through on-line learning according to the estimated impaired limb's mechanical impedance parameters. Analysis and simulation results indicate that the proposed algorithm is much more stable and smooth than other impedance control methods.