Literature DB >> 27322596

Towards an SEMG-based tele-operated robot for masticatory rehabilitation.

Hadi Kalani1, Sahar Moghimi2, Alireza Akbarzadeh1.   

Abstract

This paper proposes a real-time trajectory generation for a masticatory rehabilitation robot based on surface electromyography (SEMG) signals. We used two Gough-Stewart robots. The first robot was used as a rehabilitation robot while the second robot was developed to model the human jaw system. The legs of the rehabilitation robot were controlled by the SEMG signals of a tele-operator to reproduce the masticatory motion in the human jaw, supposedly mounted on the moving platform, through predicting the location of a reference point. Actual jaw motions and the SEMG signals from the masticatory muscles were recorded and used as output and input, respectively. Three different methods, namely time-delayed neural networks, time delayed fast orthogonal search, and time-delayed Laguerre expansion technique, were employed and compared to predict the kinematic parameters. The optimal model structures as well as the input delays were obtained for each model and each subject through a genetic algorithm. Equations of motion were obtained by the virtual work method. Fuzzy method was employed to develop a fuzzy impedance controller. Moreover, a jaw model was developed to demonstrate the time-varying behavior of the muscle lengths during the rehabilitation process. The three modeling methods were capable of providing reasonably accurate estimations of the kinematic parameters, although the accuracy and training/validation speed of time-delayed fast orthogonal search were higher than those of the other two aforementioned methods. Also, during a simulation study, the fuzzy impedance scheme proved successful in controlling the moving platform for the accurate navigation of the reference point in the desired trajectory. SEMG has been widely used as a control command for prostheses and exoskeleton robots. However, in the current study by employing the proposed rehabilitation robot the complete continuous profile of the clenching motion was reproduced in the sagittal plane.
Copyright © 2016. Published by Elsevier Ltd.

Entities:  

Keywords:  Artificial neural networks; Clenching movement; Fast orthogonal search; Fuzzy impedance control; Laguerre estimation technique; Rehabilitation robot; SEMG-based control

Mesh:

Year:  2016        PMID: 27322596     DOI: 10.1016/j.compbiomed.2016.05.014

Source DB:  PubMed          Journal:  Comput Biol Med        ISSN: 0010-4825            Impact factor:   4.589


  1 in total

1.  Feature Extraction of Surface Electromyography Using Wavelet Weighted Permutation Entropy for Hand Movement Recognition.

Authors:  Xiaoyun Liu; Xugang Xi; Xian Hua; Hujiao Wang; Wei Zhang
Journal:  J Healthc Eng       Date:  2020-11-24       Impact factor: 2.682

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.