Cargando…

Robust Torque Predictions From Electromyography Across Multiple Levels of Active Exoskeleton Assistance Despite Non-linear Reorganization of Locomotor Output

Robotic exoskeletons can assist humans with walking by providing supplemental torque in proportion to the user's joint torque. Electromyographic (EMG) control algorithms can estimate a user's joint torque directly using real-time EMG recordings from the muscles that generate the torque. Ho...

Descripción completa

Detalles Bibliográficos
Autores principales: George, Jacob A., Gunnell, Andrew J., Archangeli, Dante, Hunt, Grace, Ishmael, Marshall, Foreman, K. Bo, Lenzi, Tommaso
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8595105/
https://www.ncbi.nlm.nih.gov/pubmed/34803646
http://dx.doi.org/10.3389/fnbot.2021.700823
_version_ 1784600123358052352
author George, Jacob A.
Gunnell, Andrew J.
Archangeli, Dante
Hunt, Grace
Ishmael, Marshall
Foreman, K. Bo
Lenzi, Tommaso
author_facet George, Jacob A.
Gunnell, Andrew J.
Archangeli, Dante
Hunt, Grace
Ishmael, Marshall
Foreman, K. Bo
Lenzi, Tommaso
author_sort George, Jacob A.
collection PubMed
description Robotic exoskeletons can assist humans with walking by providing supplemental torque in proportion to the user's joint torque. Electromyographic (EMG) control algorithms can estimate a user's joint torque directly using real-time EMG recordings from the muscles that generate the torque. However, EMG signals change as a result of supplemental torque from an exoskeleton, resulting in unreliable estimates of the user's joint torque during active exoskeleton assistance. Here, we present an EMG control framework for robotic exoskeletons that provides consistent joint torque predictions across varying levels of assistance. Experiments with three healthy human participants showed that using diverse training data (from different levels of assistance) enables robust torque predictions, and that a convolutional neural network (CNN), but not a Kalman filter (KF), can capture the non-linear transformations in EMG due to exoskeleton assistance. With diverse training, the CNN could reliably predict joint torque from EMG during zero, low, medium, and high levels of exoskeleton assistance [root mean squared error (RMSE) below 0.096 N-m/kg]. In contrast, without diverse training, RMSE of the CNN ranged from 0.106 to 0.144 N-m/kg. RMSE of the KF ranged from 0.137 to 0.182 N-m/kg without diverse training, and did not improve with diverse training. When participant time is limited, training data should emphasize the highest levels of assistance first and utilize at least 35 full gait cycles for the CNN. The results presented here constitute an important step toward adaptive and robust human augmentation via robotic exoskeletons. This work also highlights the non-linear reorganization of locomotor output when using assistive exoskeletons; significant reductions in EMG activity were observed for the soleus and gastrocnemius, and a significant increase in EMG activity was observed for the erector spinae. Control algorithms that can accommodate spatiotemporal changes in muscle activity have broad implications for exoskeleton-based assistance and rehabilitation following neuromuscular injury.
format Online
Article
Text
id pubmed-8595105
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-85951052021-11-18 Robust Torque Predictions From Electromyography Across Multiple Levels of Active Exoskeleton Assistance Despite Non-linear Reorganization of Locomotor Output George, Jacob A. Gunnell, Andrew J. Archangeli, Dante Hunt, Grace Ishmael, Marshall Foreman, K. Bo Lenzi, Tommaso Front Neurorobot Neuroscience Robotic exoskeletons can assist humans with walking by providing supplemental torque in proportion to the user's joint torque. Electromyographic (EMG) control algorithms can estimate a user's joint torque directly using real-time EMG recordings from the muscles that generate the torque. However, EMG signals change as a result of supplemental torque from an exoskeleton, resulting in unreliable estimates of the user's joint torque during active exoskeleton assistance. Here, we present an EMG control framework for robotic exoskeletons that provides consistent joint torque predictions across varying levels of assistance. Experiments with three healthy human participants showed that using diverse training data (from different levels of assistance) enables robust torque predictions, and that a convolutional neural network (CNN), but not a Kalman filter (KF), can capture the non-linear transformations in EMG due to exoskeleton assistance. With diverse training, the CNN could reliably predict joint torque from EMG during zero, low, medium, and high levels of exoskeleton assistance [root mean squared error (RMSE) below 0.096 N-m/kg]. In contrast, without diverse training, RMSE of the CNN ranged from 0.106 to 0.144 N-m/kg. RMSE of the KF ranged from 0.137 to 0.182 N-m/kg without diverse training, and did not improve with diverse training. When participant time is limited, training data should emphasize the highest levels of assistance first and utilize at least 35 full gait cycles for the CNN. The results presented here constitute an important step toward adaptive and robust human augmentation via robotic exoskeletons. This work also highlights the non-linear reorganization of locomotor output when using assistive exoskeletons; significant reductions in EMG activity were observed for the soleus and gastrocnemius, and a significant increase in EMG activity was observed for the erector spinae. Control algorithms that can accommodate spatiotemporal changes in muscle activity have broad implications for exoskeleton-based assistance and rehabilitation following neuromuscular injury. Frontiers Media S.A. 2021-11-03 /pmc/articles/PMC8595105/ /pubmed/34803646 http://dx.doi.org/10.3389/fnbot.2021.700823 Text en Copyright © 2021 George, Gunnell, Archangeli, Hunt, Ishmael, Foreman and Lenzi. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
George, Jacob A.
Gunnell, Andrew J.
Archangeli, Dante
Hunt, Grace
Ishmael, Marshall
Foreman, K. Bo
Lenzi, Tommaso
Robust Torque Predictions From Electromyography Across Multiple Levels of Active Exoskeleton Assistance Despite Non-linear Reorganization of Locomotor Output
title Robust Torque Predictions From Electromyography Across Multiple Levels of Active Exoskeleton Assistance Despite Non-linear Reorganization of Locomotor Output
title_full Robust Torque Predictions From Electromyography Across Multiple Levels of Active Exoskeleton Assistance Despite Non-linear Reorganization of Locomotor Output
title_fullStr Robust Torque Predictions From Electromyography Across Multiple Levels of Active Exoskeleton Assistance Despite Non-linear Reorganization of Locomotor Output
title_full_unstemmed Robust Torque Predictions From Electromyography Across Multiple Levels of Active Exoskeleton Assistance Despite Non-linear Reorganization of Locomotor Output
title_short Robust Torque Predictions From Electromyography Across Multiple Levels of Active Exoskeleton Assistance Despite Non-linear Reorganization of Locomotor Output
title_sort robust torque predictions from electromyography across multiple levels of active exoskeleton assistance despite non-linear reorganization of locomotor output
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8595105/
https://www.ncbi.nlm.nih.gov/pubmed/34803646
http://dx.doi.org/10.3389/fnbot.2021.700823
work_keys_str_mv AT georgejacoba robusttorquepredictionsfromelectromyographyacrossmultiplelevelsofactiveexoskeletonassistancedespitenonlinearreorganizationoflocomotoroutput
AT gunnellandrewj robusttorquepredictionsfromelectromyographyacrossmultiplelevelsofactiveexoskeletonassistancedespitenonlinearreorganizationoflocomotoroutput
AT archangelidante robusttorquepredictionsfromelectromyographyacrossmultiplelevelsofactiveexoskeletonassistancedespitenonlinearreorganizationoflocomotoroutput
AT huntgrace robusttorquepredictionsfromelectromyographyacrossmultiplelevelsofactiveexoskeletonassistancedespitenonlinearreorganizationoflocomotoroutput
AT ishmaelmarshall robusttorquepredictionsfromelectromyographyacrossmultiplelevelsofactiveexoskeletonassistancedespitenonlinearreorganizationoflocomotoroutput
AT foremankbo robusttorquepredictionsfromelectromyographyacrossmultiplelevelsofactiveexoskeletonassistancedespitenonlinearreorganizationoflocomotoroutput
AT lenzitommaso robusttorquepredictionsfromelectromyographyacrossmultiplelevelsofactiveexoskeletonassistancedespitenonlinearreorganizationoflocomotoroutput