A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints
The growing interest of the industry production in wearable robots for assistance and rehabilitation purposes opens the challenge for developing intuitive and natural control strategies. Myoelectric control, or myo-control, which consists in decoding the human motor intent from muscular activity and...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2018-11-01
|
Series: | Frontiers in Neurorobotics |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fnbot.2018.00074/full |
id |
doaj-05d8e00451d04362a9b0ac78da62e1b4 |
---|---|
record_format |
Article |
spelling |
doaj-05d8e00451d04362a9b0ac78da62e1b42020-11-24T21:46:27ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182018-11-011210.3389/fnbot.2018.00074377081A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow JointsDomenico Buongiorno0Michele Barsotti1Francesco Barone2Vitoantonio Bevilacqua3Antonio Frisoli4Department of Electrical and Information Engineering, Polytechnic University of Bari, Bari, ItalyPercro Laboratory, Tecip Institute, Scuola Superiore Sant'Anna, Pisa, ItalyPercro Laboratory, Tecip Institute, Scuola Superiore Sant'Anna, Pisa, ItalyDepartment of Electrical and Information Engineering, Polytechnic University of Bari, Bari, ItalyPercro Laboratory, Tecip Institute, Scuola Superiore Sant'Anna, Pisa, ItalyThe growing interest of the industry production in wearable robots for assistance and rehabilitation purposes opens the challenge for developing intuitive and natural control strategies. Myoelectric control, or myo-control, which consists in decoding the human motor intent from muscular activity and its mapping into control outputs, represents a natural way to establish an intimate human-machine connection. In this field, model based myo-control schemes (e.g., EMG-driven neuromusculoskeletal models, NMS) represent a valid solution for estimating the moments of the human joints. However, a model optimization is needed to adjust the model's parameters to a specific subject and most of the optimization approaches presented in literature consider complex NMS models that are unsuitable for being used in a control paradigm since they suffer from long-lasting setup and optimization phases. In this work we present a minimal NMS model for predicting the elbow and shoulder torques and we compare two optimization approaches: a linear optimization method (LO) and a non-linear method based on a genetic algorithm (GA). The LO optimizes only one parameter per muscle, whereas the GA-based approach performs a deep customization of the muscle model, adjusting 12 parameters per muscle. EMG and force data have been collected from 7 healthy subjects performing a set of exercises with an arm exoskeleton. Although both optimization methods substantially improved the performance of the raw model, the findings of the study suggest that the LO might be beneficial with respect to GA as the latter is much more computationally heavy and leads to minimal improvements with respect to the former. From the comparison between the two considered joints, it emerged also that the more accurate the NMS model is, the more effective a complex optimization procedure could be. Overall, the two optimized NMS models were able to predict the shoulder and elbow moments with a low error, thus demonstrating the potentiality for being used in an admittance-based myo-control scheme. Thanks to the low computational cost and to the short setup phase required for wearing and calibrating the system, obtained results are promising for being introduced in industrial or rehabilitation real time scenarios.https://www.frontiersin.org/article/10.3389/fnbot.2018.00074/fullneuromusculoskeletal modelEMGupper limboptimizationmyo-controlgenetic algorithm |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Domenico Buongiorno Michele Barsotti Francesco Barone Vitoantonio Bevilacqua Antonio Frisoli |
spellingShingle |
Domenico Buongiorno Michele Barsotti Francesco Barone Vitoantonio Bevilacqua Antonio Frisoli A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints Frontiers in Neurorobotics neuromusculoskeletal model EMG upper limb optimization myo-control genetic algorithm |
author_facet |
Domenico Buongiorno Michele Barsotti Francesco Barone Vitoantonio Bevilacqua Antonio Frisoli |
author_sort |
Domenico Buongiorno |
title |
A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints |
title_short |
A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints |
title_full |
A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints |
title_fullStr |
A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints |
title_full_unstemmed |
A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints |
title_sort |
linear approach to optimize an emg-driven neuromusculoskeletal model for movement intention detection in myo-control: a case study on shoulder and elbow joints |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Neurorobotics |
issn |
1662-5218 |
publishDate |
2018-11-01 |
description |
The growing interest of the industry production in wearable robots for assistance and rehabilitation purposes opens the challenge for developing intuitive and natural control strategies. Myoelectric control, or myo-control, which consists in decoding the human motor intent from muscular activity and its mapping into control outputs, represents a natural way to establish an intimate human-machine connection. In this field, model based myo-control schemes (e.g., EMG-driven neuromusculoskeletal models, NMS) represent a valid solution for estimating the moments of the human joints. However, a model optimization is needed to adjust the model's parameters to a specific subject and most of the optimization approaches presented in literature consider complex NMS models that are unsuitable for being used in a control paradigm since they suffer from long-lasting setup and optimization phases. In this work we present a minimal NMS model for predicting the elbow and shoulder torques and we compare two optimization approaches: a linear optimization method (LO) and a non-linear method based on a genetic algorithm (GA). The LO optimizes only one parameter per muscle, whereas the GA-based approach performs a deep customization of the muscle model, adjusting 12 parameters per muscle. EMG and force data have been collected from 7 healthy subjects performing a set of exercises with an arm exoskeleton. Although both optimization methods substantially improved the performance of the raw model, the findings of the study suggest that the LO might be beneficial with respect to GA as the latter is much more computationally heavy and leads to minimal improvements with respect to the former. From the comparison between the two considered joints, it emerged also that the more accurate the NMS model is, the more effective a complex optimization procedure could be. Overall, the two optimized NMS models were able to predict the shoulder and elbow moments with a low error, thus demonstrating the potentiality for being used in an admittance-based myo-control scheme. Thanks to the low computational cost and to the short setup phase required for wearing and calibrating the system, obtained results are promising for being introduced in industrial or rehabilitation real time scenarios. |
topic |
neuromusculoskeletal model EMG upper limb optimization myo-control genetic algorithm |
url |
https://www.frontiersin.org/article/10.3389/fnbot.2018.00074/full |
work_keys_str_mv |
AT domenicobuongiorno alinearapproachtooptimizeanemgdrivenneuromusculoskeletalmodelformovementintentiondetectioninmyocontrolacasestudyonshoulderandelbowjoints AT michelebarsotti alinearapproachtooptimizeanemgdrivenneuromusculoskeletalmodelformovementintentiondetectioninmyocontrolacasestudyonshoulderandelbowjoints AT francescobarone alinearapproachtooptimizeanemgdrivenneuromusculoskeletalmodelformovementintentiondetectioninmyocontrolacasestudyonshoulderandelbowjoints AT vitoantoniobevilacqua alinearapproachtooptimizeanemgdrivenneuromusculoskeletalmodelformovementintentiondetectioninmyocontrolacasestudyonshoulderandelbowjoints AT antoniofrisoli alinearapproachtooptimizeanemgdrivenneuromusculoskeletalmodelformovementintentiondetectioninmyocontrolacasestudyonshoulderandelbowjoints AT domenicobuongiorno linearapproachtooptimizeanemgdrivenneuromusculoskeletalmodelformovementintentiondetectioninmyocontrolacasestudyonshoulderandelbowjoints AT michelebarsotti linearapproachtooptimizeanemgdrivenneuromusculoskeletalmodelformovementintentiondetectioninmyocontrolacasestudyonshoulderandelbowjoints AT francescobarone linearapproachtooptimizeanemgdrivenneuromusculoskeletalmodelformovementintentiondetectioninmyocontrolacasestudyonshoulderandelbowjoints AT vitoantoniobevilacqua linearapproachtooptimizeanemgdrivenneuromusculoskeletalmodelformovementintentiondetectioninmyocontrolacasestudyonshoulderandelbowjoints AT antoniofrisoli linearapproachtooptimizeanemgdrivenneuromusculoskeletalmodelformovementintentiondetectioninmyocontrolacasestudyonshoulderandelbowjoints |
_version_ |
1725902092048007168 |