HUMAN-EMG PROSTHETIC HAND INTERFACE USING NEURAL NETWORK

S. Morita, K. Shibata, X.–Z. Zheng, K. Ito

Abstract

For the improvement of the amputee’s activity of daily living (ADL), several kinds of electromyogram (EMG) controlled prosthetic hands have been developed so far. But there is still significant difference between the movements of these hands and human ones. In this paper, we propose a direct torque control method for the prosthetic hand. In order to estimate the joint torque from EMG signals, an artificial neural network by the feedback error learning schema is used. 2- DOF motions, i.e. hand grasping/opening and arm flexion/extension, are picked up. Then it is verified that the neural network can learn the relation between the EMG signal and joint torque.

Keywords

prosthetic hand, neural network, EMG signal

Download

IMEKO-WC-2000-TC13-P338.pdf

DOI

-

IMEKO TC

TC13 - Measurements in Biology and Medicine

Back to the proceedings