Inertial measurement unit based human action recognition for soft-robotic exoskeletons

Absence from work caused by overloading the musculoskeletal system lowers the life quality of the worker and entails unnecessary costs for both the employer and the health system. Soft-robotic exoskeletons offer a possibility to overcome these problems by increasing the system flexibility, not limit...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Moritz Burgdorff, Hristo Filaretov, Jörg Krüger, Jan Kuschan
Formato:	article
Lenguaje:	EN
Publicado:	Estonian Academy Publishers 2021
Materias:	machine learning human action recognition wearables soft-robotic exoskeletons assembly inertial measurement unit. Science Q
Acceso en línea:	https://doaj.org/article/983f611ae5f24385abcee91cd73fd424
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:983f611ae5f24385abcee91cd73fd424
record_format	dspace
spelling	oai:doaj.org-article:983f611ae5f24385abcee91cd73fd4242021-11-17T17:48:20ZInertial measurement unit based human action recognition for soft-robotic exoskeletons1736-60461736-753010.3176/proc.2021.4.16https://doaj.org/article/983f611ae5f24385abcee91cd73fd4242021-11-01T00:00:00Zhttps://kirj.ee/wp-content/plugins/kirj/pub/proc-4-2021-484-492_20211117100506.pdfhttps://doaj.org/toc/1736-6046https://doaj.org/toc/1736-7530Absence from work caused by overloading the musculoskeletal system lowers the life quality of the worker and entails unnecessary costs for both the employer and the health system. Soft-robotic exoskeletons offer a possibility to overcome these problems by increasing the system flexibility, not limiting the supported Degrees of Freedom and being simultaneously an actuator and a joint. Since such exoskeletons can only be designed for using power when supporting the wearer, battery lifetime can be increased by covering only those actions for which support is needed. As regards controls, a major difficulty lies in finding a compromise between saving energy and supporting the wearer. However, an action-depending control can reduce the supported actions to only relevant ones and increase battery lifetime. The system conditions include detection of user actions in real time and distinguishing between actions requiring and not requiring support. We contributed an analysis and modification of human action recognition (HAR) benchmark algorithms from activities of daily living, transferred them onto industrial use cases and made the models compatible with embedded computers for real-time recognition on soft exoskeletons. We identified the most common challenges for inertial measurement unit based HAR and compared the best-performing algorithms using a newly recorded dataset of overhead car assembly for industrial relevance. By introducing orientation estimation, F1-scores could be increased by up to 0.04. With an overall F1-score without a Null class of up to 0.883, we were able to lay the foundation for using HAR for action dependent force support.Moritz BurgdorffHristo FilaretovJörg KrügerJan KuschanEstonian Academy Publishersarticlemachine learninghuman action recognitionwearablessoft-robotic exoskeletonsassemblyinertial measurement unit.ScienceQENProceedings of the Estonian Academy of Sciences, Vol 70, Iss 4, Pp 484-492 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	machine learning human action recognition wearables soft-robotic exoskeletons assembly inertial measurement unit. Science Q
spellingShingle	machine learning human action recognition wearables soft-robotic exoskeletons assembly inertial measurement unit. Science Q Moritz Burgdorff Hristo Filaretov Jörg Krüger Jan Kuschan Inertial measurement unit based human action recognition for soft-robotic exoskeletons
description	Absence from work caused by overloading the musculoskeletal system lowers the life quality of the worker and entails unnecessary costs for both the employer and the health system. Soft-robotic exoskeletons offer a possibility to overcome these problems by increasing the system flexibility, not limiting the supported Degrees of Freedom and being simultaneously an actuator and a joint. Since such exoskeletons can only be designed for using power when supporting the wearer, battery lifetime can be increased by covering only those actions for which support is needed. As regards controls, a major difficulty lies in finding a compromise between saving energy and supporting the wearer. However, an action-depending control can reduce the supported actions to only relevant ones and increase battery lifetime. The system conditions include detection of user actions in real time and distinguishing between actions requiring and not requiring support. We contributed an analysis and modification of human action recognition (HAR) benchmark algorithms from activities of daily living, transferred them onto industrial use cases and made the models compatible with embedded computers for real-time recognition on soft exoskeletons. We identified the most common challenges for inertial measurement unit based HAR and compared the best-performing algorithms using a newly recorded dataset of overhead car assembly for industrial relevance. By introducing orientation estimation, F1-scores could be increased by up to 0.04. With an overall F1-score without a Null class of up to 0.883, we were able to lay the foundation for using HAR for action dependent force support.
format	article
author	Moritz Burgdorff Hristo Filaretov Jörg Krüger Jan Kuschan
author_facet	Moritz Burgdorff Hristo Filaretov Jörg Krüger Jan Kuschan
author_sort	Moritz Burgdorff
title	Inertial measurement unit based human action recognition for soft-robotic exoskeletons
title_short	Inertial measurement unit based human action recognition for soft-robotic exoskeletons
title_full	Inertial measurement unit based human action recognition for soft-robotic exoskeletons
title_fullStr	Inertial measurement unit based human action recognition for soft-robotic exoskeletons
title_full_unstemmed	Inertial measurement unit based human action recognition for soft-robotic exoskeletons
title_sort	inertial measurement unit based human action recognition for soft-robotic exoskeletons
publisher	Estonian Academy Publishers
publishDate	2021
url	https://doaj.org/article/983f611ae5f24385abcee91cd73fd424
work_keys_str_mv	AT moritzburgdorff inertialmeasurementunitbasedhumanactionrecognitionforsoftroboticexoskeletons AT hristofilaretov inertialmeasurementunitbasedhumanactionrecognitionforsoftroboticexoskeletons AT jorgkruger inertialmeasurementunitbasedhumanactionrecognitionforsoftroboticexoskeletons AT jankuschan inertialmeasurementunitbasedhumanactionrecognitionforsoftroboticexoskeletons
_version_	1718425370543259648

Inertial measurement unit based human action recognition for soft-robotic exoskeletons

Ejemplares similares