Development of a multibody simulator to study the CHARMIE robot

Bibliographic Details
Main Author: Gonçalves, Fernando
Publication Date: 2024
Other Authors: Ribeiro, Tiago, Ribeiro, A. Fernando, Lopes, Gil, Flores, Paulo
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: https://hdl.handle.net/1822/91489
Summary: [Excerpt] 1. INTRODUCTION The Laboratory of Automation and Robotics of the University of Minho has developed CHARMIE, a human-inspired robot designed to assist humans in domestic tasks [1] (See Figure 1). One of the challenges in developing a complex mobile manipulator robot is testing and optimizing its control. Damages to the physical prototype, or possible hazardous situations, can be avoided by testing control solutions in a virtual environment. This is even more relevant when using Reinforcement Learning as a control strategy, where the neural network requires testing a set of inaccurate and inadequate solutions before the reward function allows the system to converge into more optimal strategies. This work deals with the development of a multibody simulator that represents the key kinematics and dynamics of CHARMIE’s bodies and joints.[...]
id RCAP_4e6d902df3e858ffd40605912df41a1d
oai_identifier_str oai:repositorium.sdum.uminho.pt:1822/91489
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Development of a multibody simulator to study the CHARMIE robotEngenharia e Tecnologia::Engenharia MecânicaSaúde de qualidade[Excerpt] 1. INTRODUCTION The Laboratory of Automation and Robotics of the University of Minho has developed CHARMIE, a human-inspired robot designed to assist humans in domestic tasks [1] (See Figure 1). One of the challenges in developing a complex mobile manipulator robot is testing and optimizing its control. Damages to the physical prototype, or possible hazardous situations, can be avoided by testing control solutions in a virtual environment. This is even more relevant when using Reinforcement Learning as a control strategy, where the neural network requires testing a set of inaccurate and inadequate solutions before the reward function allows the system to converge into more optimal strategies. This work deals with the development of a multibody simulator that represents the key kinematics and dynamics of CHARMIE’s bodies and joints.[...]This work has been supported by the Laboratory of Automation and Robotics (LAR) of University of Minho, and the ALGORITMI and CMEMS research centers. The first and second authors received funding through a doctoral scholarship from the Portuguese Foundation for Science and Technology [grant numbers SFRH/BD/145993/2019 and SFRH/BD/06944/2020], with funds from the Portuguese Ministry of Science, Technology and Higher Education and the European Social Fund through the Programa Operacional do Capital Humano (POCH). This work has been supported by FCT—Fundação para a Ciência e a Tecnologia within the R&D Units Project Scope: UIDB/00319/2020. This work has also been supported by the Portuguese Foundation for Science and Technology under the national support to R&D units grant, with the reference projects UIDB/04436/2020 and UIDP/04436/2020.Universidade do Minho. Departamento de Engenharia Mecânica (DEM)Universidade do MinhoGonçalves, FernandoRibeiro, TiagoRibeiro, A. FernandoLopes, GilFlores, Paulo2024-052024-05-01T00:00:00Zconference objectinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://hdl.handle.net/1822/91489enginfo:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-07-13T02:14:02Zoai:repositorium.sdum.uminho.pt:1822/91489Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:52:19.181358Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Development of a multibody simulator to study the CHARMIE robot
title Development of a multibody simulator to study the CHARMIE robot
spellingShingle Development of a multibody simulator to study the CHARMIE robot
Gonçalves, Fernando
Engenharia e Tecnologia::Engenharia Mecânica
Saúde de qualidade
title_short Development of a multibody simulator to study the CHARMIE robot
title_full Development of a multibody simulator to study the CHARMIE robot
title_fullStr Development of a multibody simulator to study the CHARMIE robot
title_full_unstemmed Development of a multibody simulator to study the CHARMIE robot
title_sort Development of a multibody simulator to study the CHARMIE robot
author Gonçalves, Fernando
author_facet Gonçalves, Fernando
Ribeiro, Tiago
Ribeiro, A. Fernando
Lopes, Gil
Flores, Paulo
author_role author
author2 Ribeiro, Tiago
Ribeiro, A. Fernando
Lopes, Gil
Flores, Paulo
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Universidade do Minho
dc.contributor.author.fl_str_mv Gonçalves, Fernando
Ribeiro, Tiago
Ribeiro, A. Fernando
Lopes, Gil
Flores, Paulo
dc.subject.por.fl_str_mv Engenharia e Tecnologia::Engenharia Mecânica
Saúde de qualidade
topic Engenharia e Tecnologia::Engenharia Mecânica
Saúde de qualidade
description [Excerpt] 1. INTRODUCTION The Laboratory of Automation and Robotics of the University of Minho has developed CHARMIE, a human-inspired robot designed to assist humans in domestic tasks [1] (See Figure 1). One of the challenges in developing a complex mobile manipulator robot is testing and optimizing its control. Damages to the physical prototype, or possible hazardous situations, can be avoided by testing control solutions in a virtual environment. This is even more relevant when using Reinforcement Learning as a control strategy, where the neural network requires testing a set of inaccurate and inadequate solutions before the reward function allows the system to converge into more optimal strategies. This work deals with the development of a multibody simulator that represents the key kinematics and dynamics of CHARMIE’s bodies and joints.[...]
publishDate 2024
dc.date.none.fl_str_mv 2024-05
2024-05-01T00:00:00Z
dc.type.driver.fl_str_mv conference object
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/1822/91489
url https://hdl.handle.net/1822/91489
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidade do Minho. Departamento de Engenharia Mecânica (DEM)
publisher.none.fl_str_mv Universidade do Minho. Departamento de Engenharia Mecânica (DEM)
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833597026481209344