Terrain-aware autonomous exploration of unstructured confined spaces
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Tese |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFMG |
Texto Completo: | http://hdl.handle.net/1843/44581 |
Resumo: | This dissertation addresses the problem of exploring confined environments autonomously using terrestrial mobile robots. Here we propose a methodology for path planning in rough three-dimensional terrains and two exploration techniques that use the map's navigable areas, the related navigation cost, and the information expected from a frontier to select the next exploration sector. The presented pipelines are built over a representation of the environment based on three-dimensional meshes and raw point clouds. The reconstructed meshes are converted into traversable graphs, and the dangerous or untraversable regions are filtered considering the expected pose of the robot at the time of planning. The generation of the most promising paths uses a linear combination of weights applied to multiple traversability metrics of the terrain, such as distance, roughness, and energy consumption of the robot. The proposed exploration method uses the expected volumetric information of frontiers after visitation; this way, the exploration areas are selected according to their expected utility and visit cost, considering the terrain's topography. We also propose an online planning phase using the raw point cloud to avoid obstacles in dynamic environments. The online phase is faster to compute and uses an RRT algorithm biased towards the most informative frontier, which is capable of planning and selecting a target frontier without specifying a hardcoded utility metric. The algorithms were validated in representative simulated and real environments, proving the viability of the proposed methodologies. |
id |
UFMG_90d0cb654e444c191223608fe1139190 |
---|---|
oai_identifier_str |
oai:repositorio.ufmg.br:1843/44581 |
network_acronym_str |
UFMG |
network_name_str |
Repositório Institucional da UFMG |
repository_id_str |
|
spelling |
Douglas G. Macharethttp://lattes.cnpq.br/7640548709008824Mário Fernando Montenegro CamposLuiz ChaimowiczGustavo Medeiros FreitasGustavo PessinDenis Fernando Wolfhttp://lattes.cnpq.br/8363001713282037Héctor Ignácio Azpúrua Perez-Imaz2022-08-25T15:51:23Z2022-08-25T15:51:23Z2022-07-08http://hdl.handle.net/1843/44581This dissertation addresses the problem of exploring confined environments autonomously using terrestrial mobile robots. Here we propose a methodology for path planning in rough three-dimensional terrains and two exploration techniques that use the map's navigable areas, the related navigation cost, and the information expected from a frontier to select the next exploration sector. The presented pipelines are built over a representation of the environment based on three-dimensional meshes and raw point clouds. The reconstructed meshes are converted into traversable graphs, and the dangerous or untraversable regions are filtered considering the expected pose of the robot at the time of planning. The generation of the most promising paths uses a linear combination of weights applied to multiple traversability metrics of the terrain, such as distance, roughness, and energy consumption of the robot. The proposed exploration method uses the expected volumetric information of frontiers after visitation; this way, the exploration areas are selected according to their expected utility and visit cost, considering the terrain's topography. We also propose an online planning phase using the raw point cloud to avoid obstacles in dynamic environments. The online phase is faster to compute and uses an RRT algorithm biased towards the most informative frontier, which is capable of planning and selecting a target frontier without specifying a hardcoded utility metric. The algorithms were validated in representative simulated and real environments, proving the viability of the proposed methodologies.Esta tese aborda o problema de explorar ambientes confinados de forma autônoma usando robôs móveis terrestres. Aqui propomos um método de planejamento de caminhos em terrenos tridimensionais acidentados e duas técnicas de exploração que utilizam as áreas navegáveis do mapa, o custo de navegação relacionado e as informações esperadas de uma fronteira para selecionar o próximo setor de exploração. Os pipelines apresentados são construídos sobre uma representação do ambiente baseada em meshes tridimensionais e nuvens de pontos. Os meshes reconstruídos são convertidos em grafos de traversabilidade, e as regiões perigosas ou não transitáveis são filtradas considerando a pose esperada do robô no momento do planejamento. A geração dos caminhos mais promissores utiliza uma combinação linear de pesos aplicados a múltiplas métricas de atravessabilidade do terreno, como distância, rugosidade e consumo de energia do robô. O método de exploração proposto utiliza as informações volumétricas esperadas das fronteiras após simular a sua visitação; desta forma, as áreas de exploração são selecionadas de acordo com sua utilidade esperada (ganho de informação) e custo de visita, considerando a topografia do terreno. Também propomos um método de planejamento online usando diretamente a nuvem de pontos capaz de desviar de obstáculos em ambientes dinâmicos. A fase online é mais rápida para calcular e usa um algoritmo RRT com viés para as fronteiras mais informativas, sendo capaz de planejar e selecionar uma fronteira de destino sem especificar uma métrica de utilidade determinística. Os algoritmos foram validados em ambientes representativos simulados e reais, comprovando a viabilidade das metodologias propostas.engUniversidade Federal de Minas GeraisPrograma de Pós-Graduação em Ciência da ComputaçãoUFMGBrasilICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃOComputação – TesesRobótica móvel – TesesPlanejamento em ambientes 3D – TesesExploração em espaços confinados – TesesMobile RoboticsExplorationPath planning in 3D environmentsConfined SpacesIndustrial RoboticsRobótica MovelPlanejamento em ambientes 3DExploração em espaços confinadosRobótica industrialTerrain-aware autonomous exploration of unstructured confined spacesExploração autônoma de espaços confinados não estruturados com terrenos irregularesExploración autónoma de espacios confinados no estructurados con terreno irregularinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGORIGINALRC9_bibloteca_fix_summario.pdfRC9_bibloteca_fix_summario.pdfTese PhD Héctor Azpúruaapplication/pdf31900385https://repositorio.ufmg.br/bitstream/1843/44581/3/RC9_bibloteca_fix_summario.pdf068c064f0dfba4aa56e3f0aa8b3ebe05MD53LICENSElicense.txtlicense.txttext/plain; charset=utf-82118https://repositorio.ufmg.br/bitstream/1843/44581/4/license.txtcda590c95a0b51b4d15f60c9642ca272MD541843/445812022-08-25 12:51:24.229oai:repositorio.ufmg.br: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ório de PublicaçõesPUBhttps://repositorio.ufmg.br/oaiopendoar:2022-08-25T15:51:24Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false |
dc.title.pt_BR.fl_str_mv |
Terrain-aware autonomous exploration of unstructured confined spaces |
dc.title.alternative.pt_BR.fl_str_mv |
Exploração autônoma de espaços confinados não estruturados com terrenos irregulares Exploración autónoma de espacios confinados no estructurados con terreno irregular |
title |
Terrain-aware autonomous exploration of unstructured confined spaces |
spellingShingle |
Terrain-aware autonomous exploration of unstructured confined spaces Héctor Ignácio Azpúrua Perez-Imaz Mobile Robotics Exploration Path planning in 3D environments Confined Spaces Industrial Robotics Robótica Movel Planejamento em ambientes 3D Exploração em espaços confinados Robótica industrial Computação – Teses Robótica móvel – Teses Planejamento em ambientes 3D – Teses Exploração em espaços confinados – Teses |
title_short |
Terrain-aware autonomous exploration of unstructured confined spaces |
title_full |
Terrain-aware autonomous exploration of unstructured confined spaces |
title_fullStr |
Terrain-aware autonomous exploration of unstructured confined spaces |
title_full_unstemmed |
Terrain-aware autonomous exploration of unstructured confined spaces |
title_sort |
Terrain-aware autonomous exploration of unstructured confined spaces |
author |
Héctor Ignácio Azpúrua Perez-Imaz |
author_facet |
Héctor Ignácio Azpúrua Perez-Imaz |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Douglas G. Macharet |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/7640548709008824 |
dc.contributor.advisor-co1.fl_str_mv |
Mário Fernando Montenegro Campos |
dc.contributor.referee1.fl_str_mv |
Luiz Chaimowicz |
dc.contributor.referee2.fl_str_mv |
Gustavo Medeiros Freitas |
dc.contributor.referee3.fl_str_mv |
Gustavo Pessin |
dc.contributor.referee4.fl_str_mv |
Denis Fernando Wolf |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/8363001713282037 |
dc.contributor.author.fl_str_mv |
Héctor Ignácio Azpúrua Perez-Imaz |
contributor_str_mv |
Douglas G. Macharet Mário Fernando Montenegro Campos Luiz Chaimowicz Gustavo Medeiros Freitas Gustavo Pessin Denis Fernando Wolf |
dc.subject.por.fl_str_mv |
Mobile Robotics Exploration Path planning in 3D environments Confined Spaces Industrial Robotics Robótica Movel Planejamento em ambientes 3D Exploração em espaços confinados Robótica industrial |
topic |
Mobile Robotics Exploration Path planning in 3D environments Confined Spaces Industrial Robotics Robótica Movel Planejamento em ambientes 3D Exploração em espaços confinados Robótica industrial Computação – Teses Robótica móvel – Teses Planejamento em ambientes 3D – Teses Exploração em espaços confinados – Teses |
dc.subject.other.pt_BR.fl_str_mv |
Computação – Teses Robótica móvel – Teses Planejamento em ambientes 3D – Teses Exploração em espaços confinados – Teses |
description |
This dissertation addresses the problem of exploring confined environments autonomously using terrestrial mobile robots. Here we propose a methodology for path planning in rough three-dimensional terrains and two exploration techniques that use the map's navigable areas, the related navigation cost, and the information expected from a frontier to select the next exploration sector. The presented pipelines are built over a representation of the environment based on three-dimensional meshes and raw point clouds. The reconstructed meshes are converted into traversable graphs, and the dangerous or untraversable regions are filtered considering the expected pose of the robot at the time of planning. The generation of the most promising paths uses a linear combination of weights applied to multiple traversability metrics of the terrain, such as distance, roughness, and energy consumption of the robot. The proposed exploration method uses the expected volumetric information of frontiers after visitation; this way, the exploration areas are selected according to their expected utility and visit cost, considering the terrain's topography. We also propose an online planning phase using the raw point cloud to avoid obstacles in dynamic environments. The online phase is faster to compute and uses an RRT algorithm biased towards the most informative frontier, which is capable of planning and selecting a target frontier without specifying a hardcoded utility metric. The algorithms were validated in representative simulated and real environments, proving the viability of the proposed methodologies. |
publishDate |
2022 |
dc.date.accessioned.fl_str_mv |
2022-08-25T15:51:23Z |
dc.date.available.fl_str_mv |
2022-08-25T15:51:23Z |
dc.date.issued.fl_str_mv |
2022-07-08 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/1843/44581 |
url |
http://hdl.handle.net/1843/44581 |
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.publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Ciência da Computação |
dc.publisher.initials.fl_str_mv |
UFMG |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
ICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO |
publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFMG instname:Universidade Federal de Minas Gerais (UFMG) instacron:UFMG |
instname_str |
Universidade Federal de Minas Gerais (UFMG) |
instacron_str |
UFMG |
institution |
UFMG |
reponame_str |
Repositório Institucional da UFMG |
collection |
Repositório Institucional da UFMG |
bitstream.url.fl_str_mv |
https://repositorio.ufmg.br/bitstream/1843/44581/3/RC9_bibloteca_fix_summario.pdf https://repositorio.ufmg.br/bitstream/1843/44581/4/license.txt |
bitstream.checksum.fl_str_mv |
068c064f0dfba4aa56e3f0aa8b3ebe05 cda590c95a0b51b4d15f60c9642ca272 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG) |
repository.mail.fl_str_mv |
|
_version_ |
1803589309104652288 |