RFID tag aided navigation system for lawnmowers

Detalhes bibliográficos
Autor(a) principal: Costa, Dany dos Santos
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10773/33941
Resumo: Bosch Indego is an autonomous lawnmower that uses a perimeter wire to define the mowing area as well as a basic location/navigation mechanism. Apart from this absolute reference, the robot’s only sources of data are their inertial sensors and the integration of the motor’s movement (odometry). This implies that in larger gardens, there may be significant deviations, resulting in miscuts in certain regions. The main objective of this dissertation is to demonstrate that by integrating RFID tags placed on the grass as new reference points, it is possible to optimize the navigation/location process and reduce the robot’s localization deviation without having to return to the only source of absolute location (dock), which may be too far away from the cutting zone. Firstly, a research was conducted to determine the sort of RFID system that would be most suited for this application. Following that, it was implemented a system capable of proving the capacity to georeference RFID tags validating the relative error between the tag and the robot’s location with an emulator designed for this purpose. Subsequently, several tests were carried out on two synthetic fields, where tags were placed on the grass either randomly or in the perimeter wire. In the end, it was demonstrated that an RFID system can be implemented with the potential of aiding the mower by providing more reference points to the area. However, tests showed that the best solution is based on the implementation of tags exclusively on the perimeter wire, since the robot’s movement is very unpredictable, making it not always possible to correctly detect the tags. This does not happen when the mower is following the perimeter wire. Even so, it was possible to exemplify the great versatility that an RFID system can offer, namely being able to identify the dock without user intervention. Future work on this system should focus on improving tag detection accuracy as well as tag positioning relative to robot movement.
id RCAP_c233b8b64888b35f31fe9cc0692a3a9a
oai_identifier_str oai:ria.ua.pt:10773/33941
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling RFID tag aided navigation system for lawnmowersAutonomous lawnmowerLocalizationMappingTagsRFIDNavigationEmulatorOdometryRecalibrationBosch Indego is an autonomous lawnmower that uses a perimeter wire to define the mowing area as well as a basic location/navigation mechanism. Apart from this absolute reference, the robot’s only sources of data are their inertial sensors and the integration of the motor’s movement (odometry). This implies that in larger gardens, there may be significant deviations, resulting in miscuts in certain regions. The main objective of this dissertation is to demonstrate that by integrating RFID tags placed on the grass as new reference points, it is possible to optimize the navigation/location process and reduce the robot’s localization deviation without having to return to the only source of absolute location (dock), which may be too far away from the cutting zone. Firstly, a research was conducted to determine the sort of RFID system that would be most suited for this application. Following that, it was implemented a system capable of proving the capacity to georeference RFID tags validating the relative error between the tag and the robot’s location with an emulator designed for this purpose. Subsequently, several tests were carried out on two synthetic fields, where tags were placed on the grass either randomly or in the perimeter wire. In the end, it was demonstrated that an RFID system can be implemented with the potential of aiding the mower by providing more reference points to the area. However, tests showed that the best solution is based on the implementation of tags exclusively on the perimeter wire, since the robot’s movement is very unpredictable, making it not always possible to correctly detect the tags. This does not happen when the mower is following the perimeter wire. Even so, it was possible to exemplify the great versatility that an RFID system can offer, namely being able to identify the dock without user intervention. Future work on this system should focus on improving tag detection accuracy as well as tag positioning relative to robot movement.Bosch Indego é um corta-relvas autónomo que utiliza um fio de perímetro que demarca a zona de corte e serve de mecanismo base de localização/navegação. Tirando esta referência absoluta, o robot apenas conta com informação de sensores inerciais e integração da deslocação da parte motora (odometeria). Isto faz com que, em jardins de grandes dimensões possa ter desvios consideráveis, podendo falhar o corte em algumas zonas. O principal foco desta dissertação é demonstrar que é possível optimizar o processo de navegação/localização com a integração de tags RFID colocadas no relvado, que servirão como novos pontos de referência, de forma a corrigir o desvio de localização do robot sem que este tenha de voltar para a única fonte de localização absoluta que é a doca, que poderá estar muito distante da zona de corte. Primeiro foi feito um estudo sobre qual o tipo de sistema RFID por forma a saber qual a tecnologia mais apropriada para esta aplicação. Após isto, foi feita uma implementação capaz de demonstrar através de um emulador feito para o efeito a capacidade de georreferenciar tags RFID validando o erro entre a tag e a posição do robot. Posteriormente, foram feitos vários testes em dois relvados sintéticos, onde as tags foram colocadas no relvado quer de forma aleatória, quer organizada em cima do fio de perímetro. No fim demonstrou-se que é possível implementar um sistema RFID com a possibilidade de ajudar o robot através da adição de mais pontos de referência no mapa. Contudo, os testes constataram que a melhor solução baseia-se na implementação de tags exclusivamente no fio de perímetro, uma vez que o movimento do robot é muito incerto fazendo com que nem sempre seja possível detetar corretamente as tags. Isto não acontece quando este está a seguir o fio de perímetro. Ainda assim, foi possível exemplificar a grande versatilidade que um sistema RFID pode oferecer, nomeadamente podendo identificar a doca sem que seja necessária intervenção do utilizador. O trabalho futuro deste sistema deve-se de focar em melhorar a precisão da deteção das tags tal como o posicionamento das mesmas relativamente ao movimento do robot.2023-12-28T00:00:00Z2021-12-15T00:00:00Z2021-12-15info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/33941engCosta, Dany dos Santosinfo:eu-repo/semantics/embargoedAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-22T12:05:18Zoai:ria.ua.pt:10773/33941Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:05:17.337680Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv RFID tag aided navigation system for lawnmowers
title RFID tag aided navigation system for lawnmowers
spellingShingle RFID tag aided navigation system for lawnmowers
Costa, Dany dos Santos
Autonomous lawnmower
Localization
Mapping
Tags
RFID
Navigation
Emulator
Odometry
Recalibration
title_short RFID tag aided navigation system for lawnmowers
title_full RFID tag aided navigation system for lawnmowers
title_fullStr RFID tag aided navigation system for lawnmowers
title_full_unstemmed RFID tag aided navigation system for lawnmowers
title_sort RFID tag aided navigation system for lawnmowers
author Costa, Dany dos Santos
author_facet Costa, Dany dos Santos
author_role author
dc.contributor.author.fl_str_mv Costa, Dany dos Santos
dc.subject.por.fl_str_mv Autonomous lawnmower
Localization
Mapping
Tags
RFID
Navigation
Emulator
Odometry
Recalibration
topic Autonomous lawnmower
Localization
Mapping
Tags
RFID
Navigation
Emulator
Odometry
Recalibration
description Bosch Indego is an autonomous lawnmower that uses a perimeter wire to define the mowing area as well as a basic location/navigation mechanism. Apart from this absolute reference, the robot’s only sources of data are their inertial sensors and the integration of the motor’s movement (odometry). This implies that in larger gardens, there may be significant deviations, resulting in miscuts in certain regions. The main objective of this dissertation is to demonstrate that by integrating RFID tags placed on the grass as new reference points, it is possible to optimize the navigation/location process and reduce the robot’s localization deviation without having to return to the only source of absolute location (dock), which may be too far away from the cutting zone. Firstly, a research was conducted to determine the sort of RFID system that would be most suited for this application. Following that, it was implemented a system capable of proving the capacity to georeference RFID tags validating the relative error between the tag and the robot’s location with an emulator designed for this purpose. Subsequently, several tests were carried out on two synthetic fields, where tags were placed on the grass either randomly or in the perimeter wire. In the end, it was demonstrated that an RFID system can be implemented with the potential of aiding the mower by providing more reference points to the area. However, tests showed that the best solution is based on the implementation of tags exclusively on the perimeter wire, since the robot’s movement is very unpredictable, making it not always possible to correctly detect the tags. This does not happen when the mower is following the perimeter wire. Even so, it was possible to exemplify the great versatility that an RFID system can offer, namely being able to identify the dock without user intervention. Future work on this system should focus on improving tag detection accuracy as well as tag positioning relative to robot movement.
publishDate 2021
dc.date.none.fl_str_mv 2021-12-15T00:00:00Z
2021-12-15
2023-12-28T00:00:00Z
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.uri.fl_str_mv http://hdl.handle.net/10773/33941
url http://hdl.handle.net/10773/33941
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/embargoedAccess
eu_rights_str_mv embargoedAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799137707834736640