Prediction of Grasping by Myoelectric Sensing and Image Sensing

Hideki AOYAMA  Kazuaki KONDO  Yuichi NAKAMURA  Junichi AKITA  Masashi TODA  Sigeru SAKURAZAWA 

Publication
D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)  Vol.J95-D  No.3  pp.527-538
Publication Date: 2012/03/01
Online ISSN: 1881-0225
Print ISSN: 1880-4535
Type of Manuscript: Special Section PAPER (Special Issue on Student Research)
Category: 
Keyword: 
EMG,  prediction of grasping,  preshaping,  user interface,  sensor fusion, 

Full Text(in Japanese): PDF(2MB)

Summary: 
This paper presents a novel method for predicting grasping time, position, mode and a target object before actual grasping by a hand. In this method, an integration of measuring hand traveling by image sensing and preshaping by myoelectric sensing is applied for predicting the grasp. For that purpose, we first investigated the relationship between preshaping and EMG in a variety of grasping conditions. Then, we conducted experiments of prediction, and the results show that the proposed method has an ability of predicting grasping around 200 miliseconds prior to actual grasping (aroud 70% of time from beginning to end of hand movements).