Publicação

A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competition

Ver documento

Detalhes bibliográficos
Resumo:Localization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.
Autores principais:Klein, Luan C.
Outros Autores:Braun, João; Mendes, João; Pinto, Vítor H.; Martins, Felipe N.; Oliveira, Andre Schneider; Oliveira, Andre Schneider; Wörtche, Heinrich; Costa, Paulo Gomes da; Lima, José
Assunto:Indoor localization Machine learning Fiducial markers Industry 4.0 Robotics competitions
Ano:2023
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso aberto
Instituição associada:Instituto Politécnico de Bragança
Idioma:inglês
Origem:Biblioteca Digital do IPB
_version_ 1863850657596833792
author Klein, Luan C.
author2 Braun, João
Mendes, João
Pinto, Vítor H.
Martins, Felipe N.
Oliveira, Andre Schneider
Oliveira, Andre Schneider
Wörtche, Heinrich
Costa, Paulo Gomes da
Lima, José
author2_role author
author
author
author
author
author
author
author
author
author_facet Klein, Luan C.
Braun, João
Mendes, João
Pinto, Vítor H.
Martins, Felipe N.
Oliveira, Andre Schneider
Oliveira, Andre Schneider
Wörtche, Heinrich
Costa, Paulo Gomes da
Lima, José
author_role author
contributor_name_str_mv Biblioteca Digital do IPB
country_str PT
creators_json_str [{\"Person.name\":\"Klein, Luan C.\"},{\"Person.name\":\"Braun, João\",\"Person.identifier.orcid\":\"0000-0003-0276-4314\"},{\"Person.name\":\"Mendes, João\",\"Person.identifier.orcid\":\"0000-0003-0979-8314\"},{\"Person.name\":\"Pinto, Vítor H.\"},{\"Person.name\":\"Martins, Felipe N.\"},{\"Person.name\":\"Oliveira, Andre Schneider\"},{\"Person.name\":\"Oliveira, Andre Schneider\"},{\"Person.name\":\"Wörtche, Heinrich\"},{\"Person.name\":\"Costa, Paulo Gomes da\"},{\"Person.name\":\"Lima, José\",\"Person.identifier.orcid\":\"0000-0001-7902-1207\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Biblioteca Digital do IPB
datacite.creators.creator.creatorName.fl_str_mv Klein, Luan C.
Braun, João
Mendes, João
Pinto, Vítor H.
Martins, Felipe N.
Oliveira, Andre Schneider
Oliveira, Andre Schneider
Wörtche, Heinrich
Costa, Paulo Gomes da
Lima, José
datacite.date.Accepted.fl_str_mv 2023-01-01T00:00:00Z
datacite.date.available.fl_str_mv 2018-06-15T15:18:21Z
datacite.date.embargoed.fl_str_mv 2018-06-15T15:18:21Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Indoor localization
Machine learning
Fiducial markers
Industry 4.0
Robotics competitions
datacite.titles.title.fl_str_mv A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competition
dc.contributor.none.fl_str_mv Biblioteca Digital do IPB
dc.creator.none.fl_str_mv Klein, Luan C.
Braun, João
Mendes, João
Pinto, Vítor H.
Martins, Felipe N.
Oliveira, Andre Schneider
Oliveira, Andre Schneider
Wörtche, Heinrich
Costa, Paulo Gomes da
Lima, José
dc.date.Accepted.fl_str_mv 2023-01-01T00:00:00Z
dc.date.available.fl_str_mv 2018-06-15T15:18:21Z
dc.date.embargoed.fl_str_mv 2018-06-15T15:18:21Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10198/17690
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv MDPI
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Indoor localization
Machine learning
Fiducial markers
Industry 4.0
Robotics competitions
dc.title.fl_str_mv A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competition
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description Localization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.
dirty 0
eu_rights_str_mv openAccess
format article
fulltext.url.fl_str_mv https://bibliotecadigital.ipb.pt/bitstreams/c3030bed-ad68-45aa-a649-81c1145f4fec/download
id ipb_7233bc0da0ec96a8cdeee61dc22eff93
identifier.url.fl_str_mv http://hdl.handle.net/10198/17690
instacron_str ipb
institution Instituto Politécnico de Bragança
instname_str Instituto Politécnico de Bragança
language eng
network_acronym_str ipb
network_name_str Biblioteca Digital do IPB
oai_identifier_str oai:bibliotecadigital.ipb.pt:10198/17690
organization_str_mv urn:organizationAcronym:ipb
person_str_mv Klein, Luan C.
Braun, João
Braun, João
https://www.ciencia-id.pt/BF13-D66B-7D08
BF13-D66B-7D08
http://orcid.org/0000-0003-0276-4314
0000-0003-0276-4314
Mendes, João
Mendes, João
https://www.ciencia-id.pt/EA1F-844D-6BA9
EA1F-844D-6BA9
http://orcid.org/0000-0003-0979-8314
0000-0003-0979-8314
Pinto, Vítor H.
Martins, Felipe N.
Oliveira, Andre Schneider
Oliveira, Andre Schneider
Wörtche, Heinrich
Costa, Paulo Gomes da
Lima, José
Lima, José
https://www.ciencia-id.pt/6016-C902-86A9
6016-C902-86A9
http://orcid.org/0000-0001-7902-1207
0000-0001-7902-1207
publishDate 2023
publisher.none.fl_str_mv MDPI
reponame_str Biblioteca Digital do IPB
repository_id_str urn:repositoryAcronym:ipb
service_str_mv urn:repositoryAcronym:ipb
spelling engMDPIpt_PTLocalization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.application/pdfpt_PTA machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competitionKlein, Luan C.PersonalBraun, JoãoDSpacehttp://dspace.org/items/b8dfcbd7-1b89-48f3-afee-3e7d3f3c90d4DSpacehttp://dspace.org/items/b8dfcbd7-1b89-48f3-afee-3e7d3f3c90d4BraunJoão A.Ciência IDhttps://www.ciencia-id.ptBF13-D66B-7D08ORCIDhttp://orcid.org0000-0003-0276-4314Scopus Author IDhttps://www.scopus.com57211244317PersonalMendes, JoãoDSpacehttp://dspace.org/items/b5c9de22-cf9e-47b8-b7a4-26e08fb12b28DSpacehttp://dspace.org/items/b5c9de22-cf9e-47b8-b7a4-26e08fb12b28MendesJoãoCiência IDhttps://www.ciencia-id.ptEA1F-844D-6BA9ORCIDhttp://orcid.org0000-0003-0979-8314Scopus Author IDhttps://www.scopus.com57225794972Pinto, Vítor H.Martins, Felipe N.Oliveira, Andre SchneiderOliveira, Andre SchneiderWörtche, HeinrichCosta, Paulo Gomes daPersonalLima, JoséDSpacehttp://dspace.org/items/d88c2b2a-efc2-48ef-b1fd-1145475e0055DSpacehttp://dspace.org/items/d88c2b2a-efc2-48ef-b1fd-1145475e0055LimaJoséCiência IDhttps://www.ciencia-id.pt6016-C902-86A9ORCIDhttp://orcid.org0000-0001-7902-1207Researcher IDhttps://www.researcherid.comL-3370-2014Scopus Author IDhttps://www.scopus.com55851941311HostingInstitutionOrganizationalBiblioteca Digital do IPBe-mailmailto:dspace@ipb.ptdspace@ipb.ptDOIIsPartOf10.3390/s230631282018-06-15T15:18:21Z20232023-01-01T00:00:00ZHandlehttp://hdl.handle.net/10198/17690http://purl.org/coar/access_right/c_abf2open accessIndoor localizationMachine learningFiducial markersIndustry 4.0Robotics competitions2510349 bytesliteraturehttp://purl.org/coar/resource_type/c_6501journal article2023http://creativecommons.org/licenses/by/4.0/http://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://bibliotecadigital.ipb.pt/bitstreams/c3030bed-ad68-45aa-a649-81c1145f4fec/downloadSensors
spellingShingle A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competition
Klein, Luan C.
Indoor localization
Machine learning
Fiducial markers
Industry 4.0
Robotics competitions
subject.fl_str_mv Indoor localization
Machine learning
Fiducial markers
Industry 4.0
Robotics competitions
title A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competition
title_full A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competition
title_fullStr A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competition
title_full_unstemmed A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competition
title_short A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competition
title_sort A machine learning approach to robot localization using fiducial markers in robotatfactory 4.0 competition
topic Indoor localization
Machine learning
Fiducial markers
Industry 4.0
Robotics competitions
topic_facet Indoor localization
Machine learning
Fiducial markers
Industry 4.0
Robotics competitions
url http://hdl.handle.net/10198/17690
visible 1