Publicação

Human-Exoskeleton Interaction Simulation Framework via Deep Reinforcement Learning

Ver documento

Detalhes bibliográficos
Resumo:Designing and controlling lower-limb exoskeletons is a complex and costly process that requires extensive prototyping, human testing, and iterative refinement. A key challenge in active exoskeleton development is accurately perceiving human-robot interaction (HRI) and delivering practical assistance through advanced control strategies. Simulating HRI in controlled environments offers a powerful alternative, enabling efficient experiment design and assistive device development while reducing time, costs, and reliance on physical testing. This paper presents a simulation framework based on deep reinforcement learning (DRL) to investigate the interaction dynamics between human locomotion and powered lower-limb exoskeletons, utilizing the OpenSim physics-based simulator. A musculoskeletal model, integrated with an exoskeleton, functions as an agent that generates muscle forces derived from kinematics, ground reaction forces, and muscle data. The DRL architecture enables the agent to learn natural walking motion through training with experimental data in the simulator. Results demonstrate the model’s ability to simulate locomotion dynamics and provide insights into several factors, including muscle activity, muscle forces, human-exoskeleton interaction, and gait patterns.
Autores principais:SIlvino, Diogo Roseira
Outros Autores:Figueiredo, Joana; Santos, Cristina
Assunto:Human-Robot Interaction Deep Reinforcement Learning Exoskeleton
Ano:2025
País:Portugal
Tipo de documento:comunicação em conferência
Tipo de acesso:acesso aberto
Instituição associada:Universidade do Minho
Idioma:inglês
Origem:RepositóriUM - Universidade do Minho
_version_ 1866270340653514752
author SIlvino, Diogo Roseira
author2 Figueiredo, Joana
Santos, Cristina
author2_role author
author
author_facet SIlvino, Diogo Roseira
Figueiredo, Joana
Santos, Cristina
author_role author
contributor_name_str_mv Universidade do Minho
country_str PT
creators_json_txt [{\"Person.name\":\"SIlvino, Diogo Roseira\"},{\"Person.name\":\"Figueiredo, Joana\"},{\"Person.name\":\"Santos, Cristina\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Universidade do Minho
datacite.creators.creator.creatorName.fl_str_mv SIlvino, Diogo Roseira
Figueiredo, Joana
Santos, Cristina
datacite.date.Accepted.fl_str_mv 2025-01-01T00:00:00Z
datacite.date.available.fl_str_mv 2025-03-24T10:54:15Z
datacite.date.embargoed.fl_str_mv 2025-03-24T10:54:15Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Human-Robot Interaction
Deep Reinforcement Learning
Exoskeleton
datacite.titles.title.fl_str_mv Human-Exoskeleton Interaction Simulation Framework via Deep Reinforcement Learning
dc.contributor.none.fl_str_mv Universidade do Minho
dc.creator.none.fl_str_mv SIlvino, Diogo Roseira
Figueiredo, Joana
Santos, Cristina
dc.date.Accepted.fl_str_mv 2025-01-01T00:00:00Z
dc.date.available.fl_str_mv 2025-03-24T10:54:15Z
dc.date.embargoed.fl_str_mv 2025-03-24T10:54:15Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://hdl.handle.net/1822/95068
dc.language.none.fl_str_mv eng
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Human-Robot Interaction
Deep Reinforcement Learning
Exoskeleton
dc.title.fl_str_mv Human-Exoskeleton Interaction Simulation Framework via Deep Reinforcement Learning
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_5794
description Designing and controlling lower-limb exoskeletons is a complex and costly process that requires extensive prototyping, human testing, and iterative refinement. A key challenge in active exoskeleton development is accurately perceiving human-robot interaction (HRI) and delivering practical assistance through advanced control strategies. Simulating HRI in controlled environments offers a powerful alternative, enabling efficient experiment design and assistive device development while reducing time, costs, and reliance on physical testing. This paper presents a simulation framework based on deep reinforcement learning (DRL) to investigate the interaction dynamics between human locomotion and powered lower-limb exoskeletons, utilizing the OpenSim physics-based simulator. A musculoskeletal model, integrated with an exoskeleton, functions as an agent that generates muscle forces derived from kinematics, ground reaction forces, and muscle data. The DRL architecture enables the agent to learn natural walking motion through training with experimental data in the simulator. Results demonstrate the model’s ability to simulate locomotion dynamics and provide insights into several factors, including muscle activity, muscle forces, human-exoskeleton interaction, and gait patterns.
dirty 0
eu_rights_str_mv openAccess
format conferencePaper
fulltext.url.fl_str_mv https://prod-dspace.uminho.pt/bitstreams/e6f3c50f-880a-4604-b4ee-16ef6cc13933/download
id rum_b2caf8881df69e01ec6669c4e81df8ea
identifier.url.fl_str_mv https://hdl.handle.net/1822/95068
instacron_str repositorium
institution Universidade do Minho
instname_str Universidade do Minho
language eng
network_acronym_str rum
network_name_str RepositóriUM - Universidade do Minho
oai_identifier_str oai:repositorium.uminho.pt:1822/95068
organization_str_mv urn:organizationAcronym:repositorium
person_str_mv SIlvino, Diogo Roseira
Figueiredo, Joana
Santos, Cristina
publishDate 2025
reponame_str RepositóriUM - Universidade do Minho
repository_id_str urn:repositoryAcronym:rum
service_str_mv urn:repositoryAcronym:rum
spelling engporDesigning and controlling lower-limb exoskeletons is a complex and costly process that requires extensive prototyping, human testing, and iterative refinement. A key challenge in active exoskeleton development is accurately perceiving human-robot interaction (HRI) and delivering practical assistance through advanced control strategies. Simulating HRI in controlled environments offers a powerful alternative, enabling efficient experiment design and assistive device development while reducing time, costs, and reliance on physical testing. This paper presents a simulation framework based on deep reinforcement learning (DRL) to investigate the interaction dynamics between human locomotion and powered lower-limb exoskeletons, utilizing the OpenSim physics-based simulator. A musculoskeletal model, integrated with an exoskeleton, functions as an agent that generates muscle forces derived from kinematics, ground reaction forces, and muscle data. The DRL architecture enables the agent to learn natural walking motion through training with experimental data in the simulator. Results demonstrate the model’s ability to simulate locomotion dynamics and provide insights into several factors, including muscle activity, muscle forces, human-exoskeleton interaction, and gait patterns.application/pdfporHuman-Exoskeleton Interaction Simulation Framework via Deep Reinforcement LearningSIlvino, Diogo RoseiraFigueiredo, JoanaSantos, CristinaHostingInstitutionOrganizationalUniversidade do Minhoe-mailmailto:repositorium@usdb.uminho.ptrepositorium@usdb.uminho.pt2025-03-24T10:54:15Z20252025-01-01T00:00:00ZHandlehttps://hdl.handle.net/1822/95068http://purl.org/coar/access_right/c_abf2open accessHuman-Robot InteractionDeep Reinforcement LearningExoskeleton1875832 bytesother research producthttp://purl.org/coar/resource_type/c_5794conference paperhttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://prod-dspace.uminho.pt/bitstreams/e6f3c50f-880a-4604-b4ee-16ef6cc13933/download
spellingShingle Human-Exoskeleton Interaction Simulation Framework via Deep Reinforcement Learning
SIlvino, Diogo Roseira
Human-Robot Interaction
Deep Reinforcement Learning
Exoskeleton
status SINGLETON
subject.fl_str_mv Human-Robot Interaction
Deep Reinforcement Learning
Exoskeleton
title Human-Exoskeleton Interaction Simulation Framework via Deep Reinforcement Learning
title_full Human-Exoskeleton Interaction Simulation Framework via Deep Reinforcement Learning
title_fullStr Human-Exoskeleton Interaction Simulation Framework via Deep Reinforcement Learning
title_full_unstemmed Human-Exoskeleton Interaction Simulation Framework via Deep Reinforcement Learning
title_short Human-Exoskeleton Interaction Simulation Framework via Deep Reinforcement Learning
title_sort Human-Exoskeleton Interaction Simulation Framework via Deep Reinforcement Learning
topic Human-Robot Interaction
Deep Reinforcement Learning
Exoskeleton
topic_facet Human-Robot Interaction
Deep Reinforcement Learning
Exoskeleton
url https://hdl.handle.net/1822/95068
visible 1