Independent learners in abstract traffic scenarios

Detalhes bibliográficos
Autor(a) principal: Tavares, Anderson Rocha
Data de Publicação: 2012
Outros Autores: Bazzan, Ana Lucia Cetertich
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFRGS
Texto Completo: http://hdl.handle.net/10183/229327
Resumo: In transportation systems, drivers usually choose their routes in an uncoordinated way. In general, this leads to poor global and individual performance regarding travel times and road network load balance. This work presents a reinforcement learning based approach for route choice which relies solely on drivers’ experience to guide their decisions. There is no coordinated learning mechanism, thus driver agents are independent learners. Our approach is tested in two abstract traffic scenarios and it is compared to other route choice methods. Experimental results show that drivers learn routes in complex scenarios. Moreover, the approach outperforms the compared route choice methods regarding drivers’ travel time. Also, satisfactory performance is achieved regarding road network load balance. The simplicity, realistic assumptions and performance of the proposed approach suggest that it is a feasible candidate for implementation in navigation systems for guiding drivers decisions regarding route choice.
id UFRGS-2_0015cd45951be70a5072b81bf8539cd1
oai_identifier_str oai:www.lume.ufrgs.br:10183/229327
network_acronym_str UFRGS-2
network_name_str Repositório Institucional da UFRGS
repository_id_str
spelling Tavares, Anderson RochaBazzan, Ana Lucia Cetertich2021-09-01T04:26:11Z20120103-4308http://hdl.handle.net/10183/229327000892255In transportation systems, drivers usually choose their routes in an uncoordinated way. In general, this leads to poor global and individual performance regarding travel times and road network load balance. This work presents a reinforcement learning based approach for route choice which relies solely on drivers’ experience to guide their decisions. There is no coordinated learning mechanism, thus driver agents are independent learners. Our approach is tested in two abstract traffic scenarios and it is compared to other route choice methods. Experimental results show that drivers learn routes in complex scenarios. Moreover, the approach outperforms the compared route choice methods regarding drivers’ travel time. Also, satisfactory performance is achieved regarding road network load balance. The simplicity, realistic assumptions and performance of the proposed approach suggest that it is a feasible candidate for implementation in navigation systems for guiding drivers decisions regarding route choice.application/pdfengRevista de informática teórica e aplicada. Porto Alegre. Vol. 19, n. 2 (2012), p. 13-33Inteligência artificialSistemas multiagentesInformatica : TransportesIndependent learners in abstract traffic scenariosinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/otherinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT000892255.pdf.txt000892255.pdf.txtExtracted Texttext/plain42717http://www.lume.ufrgs.br/bitstream/10183/229327/2/000892255.pdf.txt0ca643db5b159610182f0f448ebc3a2bMD52ORIGINAL000892255.pdfTexto completo (inglês)application/pdf393422http://www.lume.ufrgs.br/bitstream/10183/229327/1/000892255.pdf3a947b6b56795d5a81c76822b0d198b4MD5110183/2293272021-09-19 04:32:39.018607oai:www.lume.ufrgs.br:10183/229327Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2021-09-19T07:32:39Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false
dc.title.pt_BR.fl_str_mv Independent learners in abstract traffic scenarios
title Independent learners in abstract traffic scenarios
spellingShingle Independent learners in abstract traffic scenarios
Tavares, Anderson Rocha
Inteligência artificial
Sistemas multiagentes
Informatica : Transportes
title_short Independent learners in abstract traffic scenarios
title_full Independent learners in abstract traffic scenarios
title_fullStr Independent learners in abstract traffic scenarios
title_full_unstemmed Independent learners in abstract traffic scenarios
title_sort Independent learners in abstract traffic scenarios
author Tavares, Anderson Rocha
author_facet Tavares, Anderson Rocha
Bazzan, Ana Lucia Cetertich
author_role author
author2 Bazzan, Ana Lucia Cetertich
author2_role author
dc.contributor.author.fl_str_mv Tavares, Anderson Rocha
Bazzan, Ana Lucia Cetertich
dc.subject.por.fl_str_mv Inteligência artificial
Sistemas multiagentes
Informatica : Transportes
topic Inteligência artificial
Sistemas multiagentes
Informatica : Transportes
description In transportation systems, drivers usually choose their routes in an uncoordinated way. In general, this leads to poor global and individual performance regarding travel times and road network load balance. This work presents a reinforcement learning based approach for route choice which relies solely on drivers’ experience to guide their decisions. There is no coordinated learning mechanism, thus driver agents are independent learners. Our approach is tested in two abstract traffic scenarios and it is compared to other route choice methods. Experimental results show that drivers learn routes in complex scenarios. Moreover, the approach outperforms the compared route choice methods regarding drivers’ travel time. Also, satisfactory performance is achieved regarding road network load balance. The simplicity, realistic assumptions and performance of the proposed approach suggest that it is a feasible candidate for implementation in navigation systems for guiding drivers decisions regarding route choice.
publishDate 2012
dc.date.issued.fl_str_mv 2012
dc.date.accessioned.fl_str_mv 2021-09-01T04:26:11Z
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/other
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10183/229327
dc.identifier.issn.pt_BR.fl_str_mv 0103-4308
dc.identifier.nrb.pt_BR.fl_str_mv 000892255
identifier_str_mv 0103-4308
000892255
url http://hdl.handle.net/10183/229327
dc.language.iso.fl_str_mv eng
language eng
dc.relation.ispartof.pt_BR.fl_str_mv Revista de informática teórica e aplicada. Porto Alegre. Vol. 19, n. 2 (2012), p. 13-33
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.source.none.fl_str_mv reponame:Repositório Institucional da UFRGS
instname:Universidade Federal do Rio Grande do Sul (UFRGS)
instacron:UFRGS
instname_str Universidade Federal do Rio Grande do Sul (UFRGS)
instacron_str UFRGS
institution UFRGS
reponame_str Repositório Institucional da UFRGS
collection Repositório Institucional da UFRGS
bitstream.url.fl_str_mv http://www.lume.ufrgs.br/bitstream/10183/229327/2/000892255.pdf.txt
http://www.lume.ufrgs.br/bitstream/10183/229327/1/000892255.pdf
bitstream.checksum.fl_str_mv 0ca643db5b159610182f0f448ebc3a2b
3a947b6b56795d5a81c76822b0d198b4
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)
repository.mail.fl_str_mv
_version_ 1815447765385216000

Registros relacionados