A visual questioning answering approach to enhance robot localization in indoor environments

The usage of a visual large language model to localize a robot in an indoor environment

Detalles Bibliográficos
Autores: Peña-Narvaez, Juan Diego, Martín, Francisco, Guerrero Hernández, José Miguel, Pérez-Rodríguez, Rodrigo
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universidad Rey Juan Carlos
Repositorio:BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
OAI Identifier:oai:burjcdigital.urjc.es:10115/27453
Acceso en línea:https://hdl.handle.net/10115/27453
Access Level:acceso abierto
Palabra clave:visual question answering
robot localization
robot navigation
semantic map
robot mapping
id ES_cf03f2d74cdcd1de91d26415fb87c3ff
oai_identifier_str oai:burjcdigital.urjc.es:10115/27453
network_acronym_str ES
network_name_str España
repository_id_str
spelling A visual questioning answering approach to enhance robot localization in indoor environmentsPeña-Narvaez, Juan DiegoMartín, FranciscoGuerrero Hernández, José MiguelPérez-Rodríguez, Rodrigovisual question answeringrobot localizationrobot navigationsemantic maprobot mappingThe usage of a visual large language model to localize a robot in an indoor environmentNavigating robots with precision in complex environments remains a significant challenge. In this article, we present an innovative approach to enhance robot localization in dynamic and intricate spaces like homes and offices. We leverage Visual Question Answering (VQA) techniques to integrate semantic insights into traditional mapping methods, formulating a novel position hypothesis generation to assist localization methods, while also addressing challenges related to mapping accuracy and localization reliability. Our methodology combines a probabilistic approach with the latest advances in Monte Carlo Localization methods and Visual Language models. The integration of our hypothesis generation mechanism results in more robust robot localization compared to existing approaches. Experimental validation demonstrates the effectiveness of our approach, surpassing state-of-the-art multi-hypothesis algorithms in both position estimation and particle quality. This highlights the potential for accurate self-localization, even in symmetric environments with large corridor spaces. Furthermore, our approach exhibits a high recovery rate from deliberate position alterations, showcasing its robustness. By merging visual sensing, semantic mapping, and advanced localization techniques, we open new horizons for robot navigation. Our work bridges the gap between visual perception, semantic understanding, and traditional mapping, enabling robots to interact with their environment through questions and enrich their map with valuable insights. The code for this project is available on GitHub "https://github.com/juandpenan/topology_nav_ros2"Frontiers in Neurorobotics202320232023info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/10115/27453reponame:BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlosinstname:Universidad Rey Juan CarlosInglésAtribución 4.0 Internacionalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:burjcdigital.urjc.es:10115/274532026-06-24T12:48:17Z
dc.title.none.fl_str_mv A visual questioning answering approach to enhance robot localization in indoor environments
title A visual questioning answering approach to enhance robot localization in indoor environments
spellingShingle A visual questioning answering approach to enhance robot localization in indoor environments
Peña-Narvaez, Juan Diego
visual question answering
robot localization
robot navigation
semantic map
robot mapping
title_short A visual questioning answering approach to enhance robot localization in indoor environments
title_full A visual questioning answering approach to enhance robot localization in indoor environments
title_fullStr A visual questioning answering approach to enhance robot localization in indoor environments
title_full_unstemmed A visual questioning answering approach to enhance robot localization in indoor environments
title_sort A visual questioning answering approach to enhance robot localization in indoor environments
dc.creator.none.fl_str_mv Peña-Narvaez, Juan Diego
Martín, Francisco
Guerrero Hernández, José Miguel
Pérez-Rodríguez, Rodrigo
author Peña-Narvaez, Juan Diego
author_facet Peña-Narvaez, Juan Diego
Martín, Francisco
Guerrero Hernández, José Miguel
Pérez-Rodríguez, Rodrigo
author_role author
author2 Martín, Francisco
Guerrero Hernández, José Miguel
Pérez-Rodríguez, Rodrigo
author2_role author
author
author
dc.subject.none.fl_str_mv visual question answering
robot localization
robot navigation
semantic map
robot mapping
topic visual question answering
robot localization
robot navigation
semantic map
robot mapping
description The usage of a visual large language model to localize a robot in an indoor environment
publishDate 2023
dc.date.none.fl_str_mv 2023
2023
2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10115/27453
url https://hdl.handle.net/10115/27453
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv Atribución 4.0 Internacional
http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Atribución 4.0 Internacional
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Frontiers in Neurorobotics
publisher.none.fl_str_mv Frontiers in Neurorobotics
dc.source.none.fl_str_mv reponame:BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
instname:Universidad Rey Juan Carlos
instname_str Universidad Rey Juan Carlos
reponame_str BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
collection BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869420043907891200
score 15,81155

Similares en LA Referencia