Onboard perception and localization for resource-constrained dynamic environments : a RoboCup small size League Case Study
Ano de defesa: | 2023 |
---|---|
Autor(a) principal: | |
Orientador(a): | |
Banca de defesa: | |
Tipo de documento: | Dissertação |
Tipo de acesso: | Acesso aberto |
Idioma: | eng |
Instituição de defesa: |
Universidade Federal de Pernambuco
|
Programa de Pós-Graduação: |
Programa de Pos Graduacao em Ciencia da Computacao
|
Departamento: |
Não Informado pela instituição
|
País: |
Brasil
|
Palavras-chave em Português: | |
Link de acesso: | https://repositorio.ufpe.br/handle/123456789/52045 |
Resumo: | Self-localization consists of estimating a robot’s position and orientation (pose) regarding its operating environment and is a fundamental skill in autonomous mobile robot navigation. Monte Carlo Localization (MCL) is a particle filter-based algorithm that addresses the local- ization problem by maintaining a set of particles that represent multiple hypothesis of the current robot’s state. At each step, the particles’ are moved according to the robot’s motion and their likelihoods, also called importance weights, are estimated based on the similarities between measurements acquired by the robot and their expected values, given the particle state. Then, a resampling algorithm is applied to the distribution, generating a new set based on the current weights. MCL finds successful utilization in RoboCup robot soccer leagues for solving the self- localization problem in humanoid and standard platform competitions. At 2022, this problem was also introduced in the RoboCup Small Size League (SSL) within the Vision Blackout Technical Challenge, which restricts teams to use onboard sensing and processing only for executing basic soccer tasks, instead of the typical SSL approach that uses an external camera for sensing the environment, but no solutions were proposed for self-localization so far. There- fore, this work presents an integrated pipeline for solving the SSL self-localization problem while also detecting the environment’s dynamic objects, using onboard monocular vision and inertial odometry data. We enhance the MCL using insights from implementations of other RoboCup leagues, im- proving the algorithm’s robustness regarding imprecise measurements and motion estimations. Also, we increase the algorithm’s processing speed by adapting the number of particles in the set according to the confidence of the current distribution, also called Adaptive MCL (AMCL). For that, we propose a novel approach for measuring the quality of the current distribution, based on applying the observation model to the resulting particle of the algorithm. The ap- proach was able to drastically increase the system’s computation speed, while also maintaining the capability to track the robot’s pose, and the confidence measure may be useful for making decisions and performing movements based on the current localization confidence. |
id |
UFPE_e7384a641ceb01775d346cd89df1ff3a |
---|---|
oai_identifier_str |
oai:repositorio.ufpe.br:123456789/52045 |
network_acronym_str |
UFPE |
network_name_str |
Repositório Institucional da UFPE |
repository_id_str |
|
spelling |
MELO, João Guilherme Oliveira Carvalho dehttp://lattes.cnpq.br/6345884604216720http://lattes.cnpq.br/6291354144339437BARROS, Edna Natividade da Silva2023-08-23T17:49:22Z2023-08-23T17:49:22Z2023-08-07MELO, João Guilherme Oliveira Carvalho de. Onboard perception and localization for resource-constrained dynamic environments: a RoboCup small size League Case Study. 2023. Dissertação (Mestrado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2023.https://repositorio.ufpe.br/handle/123456789/52045Self-localization consists of estimating a robot’s position and orientation (pose) regarding its operating environment and is a fundamental skill in autonomous mobile robot navigation. Monte Carlo Localization (MCL) is a particle filter-based algorithm that addresses the local- ization problem by maintaining a set of particles that represent multiple hypothesis of the current robot’s state. At each step, the particles’ are moved according to the robot’s motion and their likelihoods, also called importance weights, are estimated based on the similarities between measurements acquired by the robot and their expected values, given the particle state. Then, a resampling algorithm is applied to the distribution, generating a new set based on the current weights. MCL finds successful utilization in RoboCup robot soccer leagues for solving the self- localization problem in humanoid and standard platform competitions. At 2022, this problem was also introduced in the RoboCup Small Size League (SSL) within the Vision Blackout Technical Challenge, which restricts teams to use onboard sensing and processing only for executing basic soccer tasks, instead of the typical SSL approach that uses an external camera for sensing the environment, but no solutions were proposed for self-localization so far. There- fore, this work presents an integrated pipeline for solving the SSL self-localization problem while also detecting the environment’s dynamic objects, using onboard monocular vision and inertial odometry data. We enhance the MCL using insights from implementations of other RoboCup leagues, im- proving the algorithm’s robustness regarding imprecise measurements and motion estimations. Also, we increase the algorithm’s processing speed by adapting the number of particles in the set according to the confidence of the current distribution, also called Adaptive MCL (AMCL). For that, we propose a novel approach for measuring the quality of the current distribution, based on applying the observation model to the resulting particle of the algorithm. The ap- proach was able to drastically increase the system’s computation speed, while also maintaining the capability to track the robot’s pose, and the confidence measure may be useful for making decisions and performing movements based on the current localization confidence.Auto-localização é uma habilidade fundamental no campo de robôs móveis autônomos e consiste em estimar a posição e orientação de um robô em relação ao seu ambiente de oper- ação. Localização de Monte Carlo (em inglês Monte Carlo Localization - MCL) é um algoritmo baseado em filtros de partículas, abordando o problema de localização através de um conjunto de partículas que representam múltiplas hipóteses do estado atual do robô. Em cada iteração, as partículas são movimentadas de acordo com os deslocamentos realizados pelo robô e suas verossimilhanças são estimadas com base nas similaridades entre medidas adquiridas pelo robô e seus valores esperados, dados os estados das partículas. Em seguida, um novo conjunto de partículas é gerado com base nos pesos atuais através de algoritmos de reamostragem e o processo é reiniciado. MCL é utilizado com sucesso em diversas ligas de futebol de robôs da RoboCup para resolver o problema de localização, especialmente em competições de robôs hu- manóides e de plataformas padronizadas. Em 2022, este problema foi introduzido na categoria Small Size League (SSL) através do desafio técnico chamado Vision Blackout, que restringe os times a utilizarem apenas técnicas de sensoriamento e processamento embarcados para ex- ecutar tarefas do futebol de robôs. Assim, este trabalho apresenta uma solução integrada para resolver o problema de auto-localização no contexto de SSL enquanto, conjuntamente, detecta objetos dinâmicos do ambiente, utilizando informações adquiridas por uma câmera monocu- lar e odometria inercial embarcados. Nós aprimoramos o algoritmo de MCL utilizando idéias de implementações propostas por outras pesquisas realizadas em outras ligas da RoboCup, garantindo mais robustez à imprecisões em medidas e estimativas de odometria. Ademais, nós aceleramos a velocidade de processamento do algoritmo adaptando o número de partículas utilizadas de acordo com a confiança atual da distribuição, método também chamado de MCL adaptativo. Para isto, propomos uma nova abordagem para medir a qualidade da distribuição atual, baseada em aplicar o modelo de observação ao estado resultante do algoritmo de lo- calização. A abordagem foi capaz de aumentar drasticamente a velocidade de processamento do sistema, sem perder sua capacidade de rastrear a localização do robô, e a nova métrica de confiança também pode ser aproveitada para tomar decisões e realizar movimentos que favoreçam a convergência do algoritmo de localização.engUniversidade Federal de PernambucoPrograma de Pos Graduacao em Ciencia da ComputacaoUFPEBrasilhttp://creativecommons.org/licenses/by-nc-nd/3.0/br/info:eu-repo/semantics/openAccessEngenharia da computaçãoRobôs móveis autônomosAuto-localizaçãoMonte Carlo LocalizationRoboCupOnboard perception and localization for resource-constrained dynamic environments : a RoboCup small size League Case Studyinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesismestradoreponame:Repositório Institucional da UFPEinstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPEORIGINALDISSERTAÇÃO João Guilherme Oliveira Carvalho de Melo.pdfDISSERTAÇÃO João Guilherme Oliveira Carvalho de Melo.pdfapplication/pdf1181107https://repositorio.ufpe.br/bitstream/123456789/52045/1/DISSERTA%c3%87%c3%83O%20Jo%c3%a3o%20Guilherme%20Oliveira%20Carvalho%20de%20Melo.pdf11d69d6546033eaf504c926dc6e41848MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8811https://repositorio.ufpe.br/bitstream/123456789/52045/2/license_rdfe39d27027a6cc9cb039ad269a5db8e34MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82362https://repositorio.ufpe.br/bitstream/123456789/52045/3/license.txt5e89a1613ddc8510c6576f4b23a78973MD53TEXTDISSERTAÇÃO João Guilherme Oliveira Carvalho de Melo.pdf.txtDISSERTAÇÃO João Guilherme Oliveira Carvalho de Melo.pdf.txtExtracted texttext/plain198617https://repositorio.ufpe.br/bitstream/123456789/52045/4/DISSERTA%c3%87%c3%83O%20Jo%c3%a3o%20Guilherme%20Oliveira%20Carvalho%20de%20Melo.pdf.txt9620eb75ab633ff9882d22336ea229aaMD54THUMBNAILDISSERTAÇÃO João Guilherme Oliveira Carvalho de Melo.pdf.jpgDISSERTAÇÃO João Guilherme Oliveira Carvalho de Melo.pdf.jpgGenerated Thumbnailimage/jpeg1190https://repositorio.ufpe.br/bitstream/123456789/52045/5/DISSERTA%c3%87%c3%83O%20Jo%c3%a3o%20Guilherme%20Oliveira%20Carvalho%20de%20Melo.pdf.jpgd7bdf5ecfc89959a9f033d644abfdbb4MD55123456789/520452023-08-24 02:14:07.978oai:repositorio.ufpe.br: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Repositório InstitucionalPUBhttps://repositorio.ufpe.br/oai/requestattena@ufpe.bropendoar:22212023-08-24T05:14:07Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE)false |
dc.title.pt_BR.fl_str_mv |
Onboard perception and localization for resource-constrained dynamic environments : a RoboCup small size League Case Study |
title |
Onboard perception and localization for resource-constrained dynamic environments : a RoboCup small size League Case Study |
spellingShingle |
Onboard perception and localization for resource-constrained dynamic environments : a RoboCup small size League Case Study MELO, João Guilherme Oliveira Carvalho de Engenharia da computação Robôs móveis autônomos Auto-localização Monte Carlo Localization RoboCup |
title_short |
Onboard perception and localization for resource-constrained dynamic environments : a RoboCup small size League Case Study |
title_full |
Onboard perception and localization for resource-constrained dynamic environments : a RoboCup small size League Case Study |
title_fullStr |
Onboard perception and localization for resource-constrained dynamic environments : a RoboCup small size League Case Study |
title_full_unstemmed |
Onboard perception and localization for resource-constrained dynamic environments : a RoboCup small size League Case Study |
title_sort |
Onboard perception and localization for resource-constrained dynamic environments : a RoboCup small size League Case Study |
author |
MELO, João Guilherme Oliveira Carvalho de |
author_facet |
MELO, João Guilherme Oliveira Carvalho de |
author_role |
author |
dc.contributor.authorLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/6345884604216720 |
dc.contributor.advisorLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/6291354144339437 |
dc.contributor.author.fl_str_mv |
MELO, João Guilherme Oliveira Carvalho de |
dc.contributor.advisor1.fl_str_mv |
BARROS, Edna Natividade da Silva |
contributor_str_mv |
BARROS, Edna Natividade da Silva |
dc.subject.por.fl_str_mv |
Engenharia da computação Robôs móveis autônomos Auto-localização Monte Carlo Localization RoboCup |
topic |
Engenharia da computação Robôs móveis autônomos Auto-localização Monte Carlo Localization RoboCup |
description |
Self-localization consists of estimating a robot’s position and orientation (pose) regarding its operating environment and is a fundamental skill in autonomous mobile robot navigation. Monte Carlo Localization (MCL) is a particle filter-based algorithm that addresses the local- ization problem by maintaining a set of particles that represent multiple hypothesis of the current robot’s state. At each step, the particles’ are moved according to the robot’s motion and their likelihoods, also called importance weights, are estimated based on the similarities between measurements acquired by the robot and their expected values, given the particle state. Then, a resampling algorithm is applied to the distribution, generating a new set based on the current weights. MCL finds successful utilization in RoboCup robot soccer leagues for solving the self- localization problem in humanoid and standard platform competitions. At 2022, this problem was also introduced in the RoboCup Small Size League (SSL) within the Vision Blackout Technical Challenge, which restricts teams to use onboard sensing and processing only for executing basic soccer tasks, instead of the typical SSL approach that uses an external camera for sensing the environment, but no solutions were proposed for self-localization so far. There- fore, this work presents an integrated pipeline for solving the SSL self-localization problem while also detecting the environment’s dynamic objects, using onboard monocular vision and inertial odometry data. We enhance the MCL using insights from implementations of other RoboCup leagues, im- proving the algorithm’s robustness regarding imprecise measurements and motion estimations. Also, we increase the algorithm’s processing speed by adapting the number of particles in the set according to the confidence of the current distribution, also called Adaptive MCL (AMCL). For that, we propose a novel approach for measuring the quality of the current distribution, based on applying the observation model to the resulting particle of the algorithm. The ap- proach was able to drastically increase the system’s computation speed, while also maintaining the capability to track the robot’s pose, and the confidence measure may be useful for making decisions and performing movements based on the current localization confidence. |
publishDate |
2023 |
dc.date.accessioned.fl_str_mv |
2023-08-23T17:49:22Z |
dc.date.available.fl_str_mv |
2023-08-23T17:49:22Z |
dc.date.issued.fl_str_mv |
2023-08-07 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
MELO, João Guilherme Oliveira Carvalho de. Onboard perception and localization for resource-constrained dynamic environments: a RoboCup small size League Case Study. 2023. Dissertação (Mestrado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2023. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufpe.br/handle/123456789/52045 |
identifier_str_mv |
MELO, João Guilherme Oliveira Carvalho de. Onboard perception and localization for resource-constrained dynamic environments: a RoboCup small size League Case Study. 2023. Dissertação (Mestrado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2023. |
url |
https://repositorio.ufpe.br/handle/123456789/52045 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/3.0/br/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/3.0/br/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Pernambuco |
dc.publisher.program.fl_str_mv |
Programa de Pos Graduacao em Ciencia da Computacao |
dc.publisher.initials.fl_str_mv |
UFPE |
dc.publisher.country.fl_str_mv |
Brasil |
publisher.none.fl_str_mv |
Universidade Federal de Pernambuco |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFPE instname:Universidade Federal de Pernambuco (UFPE) instacron:UFPE |
instname_str |
Universidade Federal de Pernambuco (UFPE) |
instacron_str |
UFPE |
institution |
UFPE |
reponame_str |
Repositório Institucional da UFPE |
collection |
Repositório Institucional da UFPE |
bitstream.url.fl_str_mv |
https://repositorio.ufpe.br/bitstream/123456789/52045/1/DISSERTA%c3%87%c3%83O%20Jo%c3%a3o%20Guilherme%20Oliveira%20Carvalho%20de%20Melo.pdf https://repositorio.ufpe.br/bitstream/123456789/52045/2/license_rdf https://repositorio.ufpe.br/bitstream/123456789/52045/3/license.txt https://repositorio.ufpe.br/bitstream/123456789/52045/4/DISSERTA%c3%87%c3%83O%20Jo%c3%a3o%20Guilherme%20Oliveira%20Carvalho%20de%20Melo.pdf.txt https://repositorio.ufpe.br/bitstream/123456789/52045/5/DISSERTA%c3%87%c3%83O%20Jo%c3%a3o%20Guilherme%20Oliveira%20Carvalho%20de%20Melo.pdf.jpg |
bitstream.checksum.fl_str_mv |
11d69d6546033eaf504c926dc6e41848 e39d27027a6cc9cb039ad269a5db8e34 5e89a1613ddc8510c6576f4b23a78973 9620eb75ab633ff9882d22336ea229aa d7bdf5ecfc89959a9f033d644abfdbb4 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE) |
repository.mail.fl_str_mv |
attena@ufpe.br |
_version_ |
1802311273348595712 |