Robot finger design for myoelectric prosthetic hand and recognition of finger motions via surface EMG

Abstract

In this paper, robot hand design aiming at application to a myoelectric prosthetic hand and recognition of finger operation via surface EMG are discussed. The robot hand with two fingers, thumb and index finger, was built to implement fundamental motions required in daily life, such as grasping and holding. The fingers are driven by the wire actuation system to imitate the human's tendon mechanism. In order to control each finger of the developed myoelectric prosthetic hand independently, using the neural network, identifier which classifies four finger operations, namely flexion and extension of the thumb in metacarpophalangeal (MP) joint and flexion and extension of the index finger in MP joint, was constructed. The recognition of each finger operation was performed using the four patterns of the neural network based identifiers in which the recognition method of finger operations differs each other, and the results were compared.