Logo do repositório
 
Publicação

Decentralized multi-agent reinforcement learning with visible light communication for robust urban traffic signal control

2025-11-11Artigo científico Acesso aberto
Ver registo simples
authorProfile.emailbiblioteca@isel.pt
datacite.subject.fosEngenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática
dc.contributor.authorAugusto Vieira, Manuel
dc.contributor.authorGonçalo Galvão
dc.contributor.authorVieira, Manuela
dc.contributor.authorVéstias, Mário
dc.contributor.authorLouro, Paula
dc.contributor.authorVieira, Pedro
dc.date.accessioned2026-01-07T09:27:31Z
dc.date.available2026-01-07T09:27:31Z
dc.date.issued2025-11-11
dc.description.abstractThe rapid growth of urban vehicle and pedestrian flows has intensified congestion, delays, and safety concerns, underscoring the need for sustainable and intelligent traffic management in modern cities. Traditional centralized traffic signal control systems often face challenges of scalability, heterogeneity of traffic patterns, and limited real-time adaptability. To address these limitations, this study proposes a decentralized Multi-Agent Reinforcement Learning (MARL) framework for adaptive traffic signal control, where Deep Reinforcement Learning (DRL) agents are deployed at each intersection and trained on local conditions to enable real-time decision-making for both vehicles and pedestrians. A key innovation lies in the integration of Visible Light Communication (VLC), which leverages existing LED-based infrastructure in traffic lights, streetlights, and vehicles to provide high-capacity, low-latency, and energy-efficient data exchange, thereby enhancing each agent’s situational awareness while promoting infrastructure sustainability. The framework introduces a queue–request–response mechanism that dynamically adjusts signal phases, resolves conflicts between flows, and prioritizes urgent or emergency movements, ensuring equitable and safer mobility for all users. Validation through microscopic simulations in SUMO and preliminary real-world experiments demonstrates reductions in average waiting time, travel time, and queue lengths, along with improvements in pedestrian safety and energy efficiency. These results highlight the potential of MARL–VLC integration as a sustainable, resilient, and human-centered solution for next-generation urban traffic management.eng
dc.identifier.citationVieira, M. A., Galvão, G., Vieira, M., Véstias, M., Louro, P., & Vieira, P. (2025). Decentralized multi-agent reinforcement learning with visible light communication for robust urban traffic signal control. Sustainability, 17(22), 10056. https://doi.org/10.3390/su172210056
dc.identifier.doi10.3390/su172210056
dc.identifier.eissn2071-1050
dc.identifier.urihttp://hdl.handle.net/10400.21/22447
dc.language.isoeng
dc.peerreviewedyes
dc.publisherMDPI AG
dc.relation.hasversionhttps://www.mdpi.com/2071-1050/17/22/10056
dc.relation.ispartofSustainability
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectSustainable urban mobility
dc.subjectIntellingent traffic management
dc.subjectMulti-agent reinforcement learning (MARL)
dc.subjectDeep reinforcement learning (DRL)
dc.subjectVisible light communication (VLC)
dc.subjectEnergy efficiency
dc.subjectPedestrian safety
dc.subjectSmart cities
dc.titleDecentralized multi-agent reinforcement learning with visible light communication for robust urban traffic signal controleng
dc.typejournal article
dspace.entity.typePublication
oaire.citation.endPage32
oaire.citation.issue22
oaire.citation.startPage1
oaire.citation.titleSustainability
oaire.citation.volume17
oaire.versionhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43
person.familyNameAugusto Vieira
person.familyNameVieira
person.familyNameVéstias
person.familyNameLouro
person.familyNameVieira
person.givenNameManuel
person.givenNameManuela
person.givenNameMário
person.givenNamePaula
person.givenNamePedro
person.identifierI-8527-2018
person.identifier10792
person.identifier499161
person.identifier.ciencia-idA511-1330-549F
person.identifier.ciencia-id9516-E25E-BB8E
person.identifier.ciencia-id4717-C2C7-3F2C
person.identifier.ciencia-idE511-8C08-E606
person.identifier.ciencia-id071B-9A70-15B8
person.identifier.orcid0000-0003-1385-3646
person.identifier.orcid0000-0002-1150-9895
person.identifier.orcid0000-0001-8556-4507
person.identifier.orcid0000-0002-4167-2052
person.identifier.orcid0000-0003-0279-8741
person.identifier.ridV-7860-2017
person.identifier.ridH-9953-2012
person.identifier.ridU-8346-2017
person.identifier.scopus-author-id5719 1567905
person.identifier.scopus-author-id7202140173
person.identifier.scopus-author-id14525867300
person.identifier.scopus-author-id8845716400
person.identifier.scopus-author-id7004567421
relation.isAuthorOfPublicationd8ffd958-0f70-4ec1-a9e9-d18e5c6d308e
relation.isAuthorOfPublicationb77c6785-9cfb-4cd4-90b5-c2b816bd7d11
relation.isAuthorOfPublicationa7d22b29-c961-45ac-bc09-cd5e1002f1e8
relation.isAuthorOfPublication730dc3dd-73eb-428d-b3a6-430085e33585
relation.isAuthorOfPublication51ae3527-d4ea-46f4-b6c9-62c7b77ac728
relation.isAuthorOfPublication.latestForDiscoveryb77c6785-9cfb-4cd4-90b5-c2b816bd7d11

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Descentralized_MAVieira.pdf
Tamanho:
11.56 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
4.03 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ISEL - Eng. Elect. Tel. Comp. - Artigos