Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/90170
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Andrade, Nuno | por |
dc.contributor.author | Ribeiro, Tiago | por |
dc.contributor.author | Coelho, Joana | por |
dc.contributor.author | Lopes, Gil | por |
dc.contributor.author | Ribeiro, A. Fernando | por |
dc.date.accessioned | 2024-03-27T14:59:09Z | - |
dc.date.available | 2024-03-27T14:59:09Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Andrade, N.; Ribeiro, T.; Coelho, J.; Lopes, G. and Ribeiro, A. (2022). Combining YOLO and Deep Reinforcement Learning for Autonomous Driving in Public Roadworks Scenarios. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-547-0; ISSN 2184-433X, SciTePress, pages 793-800. DOI: 10.5220/0010913600003116 | por |
dc.identifier.issn | 2184-433X | - |
dc.identifier.uri | https://hdl.handle.net/1822/90170 | - |
dc.description.abstract | Autonomous driving is emerging as a useful practical application of Artificial Intelligence (AI) algorithms regarding both supervised learning and reinforcement learning methods. AI is a well-known solution for some autonomous driving problems but it is not yet established and fully researched for facing real world problems regarding specific situations human drivers face every day, such as temporary roadworks and temporary signs. This is the core motivation for the proposed framework in this project. YOLOv3-tiny is used for detecting roadworks signs in the path traveled by the vehicle. Deep Deterministic Policy Gradient (DDPG) is used for controlling the behavior of the vehicle when overtaking the working zones. Security and safety of the passengers and the surrounding environment are the main concern taken into account. YOLOv3-tiny achieved an 94.8% mAP and proved to be reliable in real-world applications. DDPG made the vehicle behave with success more than 50% of the episodes when testing, although still needs some improvements to be transported to the real-world for secure and safe driving. | por |
dc.description.sponsorship | This work has been supported by FCT-Fundacao para a Ciencia e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020. In addition, this work has also been funded through a doctoral scholarship from the Portuguese Foundation for Science and Technology (Fundacao para a Ciencia 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). | por |
dc.language.iso | eng | por |
dc.publisher | SCITEPRESS | por |
dc.relation | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F00319%2F2020/PT | por |
dc.relation | SFRH/BD/06944/2020 | por |
dc.rights | openAccess | por |
dc.subject | Deep Learning | por |
dc.subject | YOLO | por |
dc.subject | Reinforcement Learning | por |
dc.subject | Deep Deterministic Policy Gradient | por |
dc.subject | Autonomous Driving | por |
dc.subject | Public Roadworks | por |
dc.title | Combining YOLO and deep reinforcement learning for autonomous driving in public roadworks scenarios | por |
dc.type | conferencePaper | por |
dc.peerreviewed | yes | por |
dc.relation.publisherversion | https://www.scitepress.org/Link.aspx?doi=10.5220/0010913600003116 | por |
oaire.citationStartPage | 793 | por |
oaire.citationEndPage | 800 | por |
oaire.citationVolume | 3 | por |
dc.date.updated | 2024-03-27T12:02:41Z | - |
dc.identifier.doi | 10.5220/0010913600003116 | por |
dc.subject.fos | Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática | por |
dc.subject.wos | Science & Technology | - |
sdum.export.identifier | 14852 | - |
sdum.journal | ICAART | por |
sdum.conferencePublication | ICAART: PROCEEDINGS OF THE 14TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 3 | por |
sdum.bookTitle | ICAART: PROCEEDINGS OF THE 14TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 3 | por |
Aparece nas coleções: |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
ICAART_2022_246_CR.pdf | 1,12 MB | Adobe PDF | Ver/Abrir |