Eventos Anais de eventos
COBEM 2017
24th ABCM International Congress of Mechanical Engineering
Control of a Tendon-Driven Robotic Hand from Surface Electromyographic Signals
Submission Author:
Carlos Malqui , RJ
Co-Authors:
Marco Antonio Meggiolaro, Carlos Malqui
Presenter: Carlos Malqui
doi://10.26678/ABCM.COBEM2017.COB17-1881
Abstract
Initially, this research was presented as main study to develop a robotic prosthesis for people with hand amputation, such as the case of disjointed amputation handle. This paper covers the following topics: position of electrodes to capture the surface electromyography signals (sEMG), design of an electromyography as muscle interface, pre-processing method and the use of techniques of computational intelligence for the interpretation of the sEMG signals, design of the robotic hand and control method used to control the positions of the fingers and the control of hand grip strength. Was used the wavelet packet as feature extraction method in electromyographic signals, and multi-layer neural network as pattern classification method. The proposed model obtained satisfactory results, thereby capturing 90.5% for recognizing positions of 6 different hand positions 5 to 94.3% and 96.25% for 4 positions.
Keywords
Surface electromyography, Patterns Classification, neural networks, Wavelet Transform, Robotic hand
