End-to-end approach for autonomous driving: a supervised learning method using computer vision algorithms for dataset creation

Detalhes bibliográficos
Autor(a) principal: Ribeiro, Inês A.
Data de Publicação: 2023
Outros Autores: Ribeiro, Tiago, Lopes, Gil, Ribeiro, A. Fernando
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: https://hdl.handle.net/1822/87267
Resumo: This paper presents a solution for an autonomously driven vehicle (a robotic car) based on artificial intelligence using a supervised learning method. A scaled-down robotic car containing only one camera as a sensor was developed to participate in the RoboCup Portuguese Open Autonomous Driving League competition. This study is based solely on the development of this robotic car, and the results presented are only from this competition. Teams usually solve the competition problem by relying on computer vision algorithms, and no research could be found on neural network model-based assistance for vehicle control. This technique is commonly used in general autonomous driving, and the amount of research is increasing. To train a neural network, a large number of labelled images is necessary; however, these are difficult to obtain. In order to address this problem, a graphical simulator was used with an environment containing the track and the robot/car to extract images for the dataset. A classical computer vision algorithm developed by the authors processes the image data to extract relevant information about the environment and uses it to determine the optimal direction for the vehicle to follow on the track, which is then associated with the respective image-grab. Several trainings were carried out with the created dataset to reach the final neural network model; tests were performed within a simulator, and the effectiveness of the proposed approach was additionally demonstrated through experimental results in two real robotics cars, which performed better than expected. This system proved to be very successful in steering the robotic car on a road-like track, and the agent’s performance increased with the use of supervised learning methods. With computer vision algorithms, the system performed an average of 23 complete laps around the track before going off-track, whereas with assistance from the neural network model the system never went off the track.
id RCAP_70629b19bb187b59cfbfce5216ce1f98
oai_identifier_str oai:repositorium.sdum.uminho.pt:1822/87267
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling End-to-end approach for autonomous driving: a supervised learning method using computer vision algorithms for dataset creationArtificial intelligenceAI in engineeringAutonomous drivingRoboticsSimulationComputer visionNeural networkSupervised learningThis paper presents a solution for an autonomously driven vehicle (a robotic car) based on artificial intelligence using a supervised learning method. A scaled-down robotic car containing only one camera as a sensor was developed to participate in the RoboCup Portuguese Open Autonomous Driving League competition. This study is based solely on the development of this robotic car, and the results presented are only from this competition. Teams usually solve the competition problem by relying on computer vision algorithms, and no research could be found on neural network model-based assistance for vehicle control. This technique is commonly used in general autonomous driving, and the amount of research is increasing. To train a neural network, a large number of labelled images is necessary; however, these are difficult to obtain. In order to address this problem, a graphical simulator was used with an environment containing the track and the robot/car to extract images for the dataset. A classical computer vision algorithm developed by the authors processes the image data to extract relevant information about the environment and uses it to determine the optimal direction for the vehicle to follow on the track, which is then associated with the respective image-grab. Several trainings were carried out with the created dataset to reach the final neural network model; tests were performed within a simulator, and the effectiveness of the proposed approach was additionally demonstrated through experimental results in two real robotics cars, which performed better than expected. This system proved to be very successful in steering the robotic car on a road-like track, and the agent’s performance increased with the use of supervised learning methods. With computer vision algorithms, the system performed an average of 23 complete laps around the track before going off-track, whereas with assistance from the neural network model the system never went off the track.This work has been supported by COMPETE: POCI01-0145-FEDER-007043 and FCT—Fundação para a Ciência e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020. In addition, this work has been funded through a doctoral scholarship from the Portuguese Foundation for Science and Technology (Fundação para a Ciência e a Tecnologia), grant number SFRH/BD/06944/2020, with funds from the Portuguese Ministry of Science, Technology, and Higher Education and the European Social Fund through the Programa Operacional do Capital Humano (POCH).Multidisciplinary Digital Publishing Institute (MDPI)Universidade do MinhoRibeiro, Inês A.Ribeiro, TiagoLopes, GilRibeiro, A. Fernando2023-08-282023-08-28T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/1822/87267engRibeiro, I.A.; Ribeiro, T.; Lopes, G.; Ribeiro, A.F. End-to-End Approach for Autonomous Driving: A Supervised Learning Method Using Computer Vision Algorithms for Dataset Creation. Algorithms 2023, 16, 411. https://doi.org/10.3390/a160904111999-489310.3390/a16090411411https://www.mdpi.com/1999-4893/16/9/411info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-12-23T01:39:15Zoai:repositorium.sdum.uminho.pt:1822/87267Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:53:56.591528Repositório 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 End-to-end approach for autonomous driving: a supervised learning method using computer vision algorithms for dataset creation
title End-to-end approach for autonomous driving: a supervised learning method using computer vision algorithms for dataset creation
spellingShingle End-to-end approach for autonomous driving: a supervised learning method using computer vision algorithms for dataset creation
Ribeiro, Inês A.
Artificial intelligence
AI in engineering
Autonomous driving
Robotics
Simulation
Computer vision
Neural network
Supervised learning
title_short End-to-end approach for autonomous driving: a supervised learning method using computer vision algorithms for dataset creation
title_full End-to-end approach for autonomous driving: a supervised learning method using computer vision algorithms for dataset creation
title_fullStr End-to-end approach for autonomous driving: a supervised learning method using computer vision algorithms for dataset creation
title_full_unstemmed End-to-end approach for autonomous driving: a supervised learning method using computer vision algorithms for dataset creation
title_sort End-to-end approach for autonomous driving: a supervised learning method using computer vision algorithms for dataset creation
author Ribeiro, Inês A.
author_facet Ribeiro, Inês A.
Ribeiro, Tiago
Lopes, Gil
Ribeiro, A. Fernando
author_role author
author2 Ribeiro, Tiago
Lopes, Gil
Ribeiro, A. Fernando
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidade do Minho
dc.contributor.author.fl_str_mv Ribeiro, Inês A.
Ribeiro, Tiago
Lopes, Gil
Ribeiro, A. Fernando
dc.subject.por.fl_str_mv Artificial intelligence
AI in engineering
Autonomous driving
Robotics
Simulation
Computer vision
Neural network
Supervised learning
topic Artificial intelligence
AI in engineering
Autonomous driving
Robotics
Simulation
Computer vision
Neural network
Supervised learning
description This paper presents a solution for an autonomously driven vehicle (a robotic car) based on artificial intelligence using a supervised learning method. A scaled-down robotic car containing only one camera as a sensor was developed to participate in the RoboCup Portuguese Open Autonomous Driving League competition. This study is based solely on the development of this robotic car, and the results presented are only from this competition. Teams usually solve the competition problem by relying on computer vision algorithms, and no research could be found on neural network model-based assistance for vehicle control. This technique is commonly used in general autonomous driving, and the amount of research is increasing. To train a neural network, a large number of labelled images is necessary; however, these are difficult to obtain. In order to address this problem, a graphical simulator was used with an environment containing the track and the robot/car to extract images for the dataset. A classical computer vision algorithm developed by the authors processes the image data to extract relevant information about the environment and uses it to determine the optimal direction for the vehicle to follow on the track, which is then associated with the respective image-grab. Several trainings were carried out with the created dataset to reach the final neural network model; tests were performed within a simulator, and the effectiveness of the proposed approach was additionally demonstrated through experimental results in two real robotics cars, which performed better than expected. This system proved to be very successful in steering the robotic car on a road-like track, and the agent’s performance increased with the use of supervised learning methods. With computer vision algorithms, the system performed an average of 23 complete laps around the track before going off-track, whereas with assistance from the neural network model the system never went off the track.
publishDate 2023
dc.date.none.fl_str_mv 2023-08-28
2023-08-28T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/1822/87267
url https://hdl.handle.net/1822/87267
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Ribeiro, I.A.; Ribeiro, T.; Lopes, G.; Ribeiro, A.F. End-to-End Approach for Autonomous Driving: A Supervised Learning Method Using Computer Vision Algorithms for Dataset Creation. Algorithms 2023, 16, 411. https://doi.org/10.3390/a16090411
1999-4893
10.3390/a16090411
411
https://www.mdpi.com/1999-4893/16/9/411
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.publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute (MDPI)
publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute (MDPI)
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_ 1799135137151057920