{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T05:24:36Z","timestamp":1763011476817,"version":"3.45.0"},"reference-count":38,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sustainability"],"abstract":"<jats:p>The 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\u2019s situational awareness while promoting infrastructure sustainability. The framework introduces a queue\u2013request\u2013response 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\u2013VLC integration as a sustainable, resilient, and human-centered solution for next-generation urban traffic management.<\/jats:p>","DOI":"10.3390\/su172210056","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T10:56:27Z","timestamp":1762858587000},"page":"10056","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Decentralized Multi-Agent Reinforcement Learning with Visible Light Communication for Robust Urban Traffic Signal Control"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1385-3646","authenticated-orcid":false,"given":"Manuel Augusto","family":"Vieira","sequence":"first","affiliation":[{"name":"DEETC-ISEL\/IPL, R. Conselheiro Em\u00eddio Navarro, 1949-014 Lisboa, Portugal"},{"name":"UNINOVA-CTS and LASI, Quinta da Torre, Monte da Caparica, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4267-0389","authenticated-orcid":false,"given":"Gon\u00e7alo","family":"Galv\u00e3o","sequence":"additional","affiliation":[{"name":"DEETC-ISEL\/IPL, R. Conselheiro Em\u00eddio Navarro, 1949-014 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1150-9895","authenticated-orcid":false,"given":"Manuela","family":"Vieira","sequence":"additional","affiliation":[{"name":"DEETC-ISEL\/IPL, R. Conselheiro Em\u00eddio Navarro, 1949-014 Lisboa, Portugal"},{"name":"UNINOVA-CTS and LASI, Quinta da Torre, Monte da Caparica, 2829-516 Caparica, Portugal"},{"name":"NOVA School of Science and Technology, Quinta da Torre, Monte da Caparica, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8556-4507","authenticated-orcid":false,"given":"M\u00e1rio","family":"V\u00e9stias","sequence":"additional","affiliation":[{"name":"DEETC-ISEL\/IPL, R. Conselheiro Em\u00eddio Navarro, 1949-014 Lisboa, Portugal"},{"name":"INESC INOV, R. Alves Redol, 9, 1000-029 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4167-2052","authenticated-orcid":false,"given":"Paula","family":"Louro","sequence":"additional","affiliation":[{"name":"DEETC-ISEL\/IPL, R. Conselheiro Em\u00eddio Navarro, 1949-014 Lisboa, Portugal"},{"name":"UNINOVA-CTS and LASI, Quinta da Torre, Monte da Caparica, 2829-516 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0279-8741","authenticated-orcid":false,"given":"Pedro","family":"Vieira","sequence":"additional","affiliation":[{"name":"DEETC-ISEL\/IPL, R. Conselheiro Em\u00eddio Navarro, 1949-014 Lisboa, Portugal"},{"name":"Instituto de Telecomunica\u00e7\u00f5es, Instituto Superior T\u00e9cnico, 1049-001 Lisboa, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1080\/09540091.2014.885282","article-title":"Distributed learning and multi-objectivity in traffic light control","volume":"26","author":"Brys","year":"2014","journal-title":"Connect. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhong, W., and Liu, T. (2025, January 7\u20139). Reinforcement learning for dynamic traffic management: A scalable approach to congestion reduction. Proceedings of the 2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), New York City, NY, USA.","DOI":"10.1109\/ACDSA65407.2025.11166092"},{"key":"ref_3","unstructured":"Richter, S., Aberdeen, D., and Yu, J. (2006, January 4\u20139). Natural actor-critic for road traffic optimisation. Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_4","unstructured":"Cunningham, R., Garg, A., and Cahill, V. (2008, January 9\u201312). A collaborative reinforcement learning approach to urban traffic control optimization. Proceedings of the 2008 IEEE\/WIC\/ACM International Conference on Web Intelligence and Intelligent Agent Technology, Sydney, Australia."},{"key":"ref_5","unstructured":"Aziz, H.M.A., Feng, Z., and Ukkusuri, S. (2013, January 13\u201317). Reinforcement learning-based signal control using R-Markov average reward technique (RMART) accounting for neighborhood congestion information sharing. Proceedings of the Transportation Research Board 92nd Annual Meeting, Washington, DC, USA."},{"key":"ref_6","unstructured":"Chu, T., Wang, J., Codec\u00e0, L., and Li, Z. (2019). Multi-agent deep reinforcement learning for large-scale traffic signal control. arXiv."},{"key":"ref_7","first-page":"1","article-title":"A survey on traffic signal control problems with MARL","volume":"56","author":"Shi","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Vieira, M.A., Silva, R., and Santos, P. (2024). Visible light communication and learning-based control for urban intersections. Symmetry, 16.","DOI":"10.3390\/sym16020240"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Sikder, P., Rahman, M.T., and Bakibillah, A.S.M. (2025). Advancements and challenges of visible light communication in intelligent transportation systems: A comprehensive review. Photonics, 12.","DOI":"10.3390\/photonics12030225"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Nawaz, T., Seminara, M., Caputo, S., Mucchi, L., Cataliotti, F., and Catani, J. (2019). IEEE 802.15.7-compliant ultra-low latency relaying VLC system for safety-critical ITS. arXiv.","DOI":"10.1109\/TVT.2019.2948041"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"19532","DOI":"10.1109\/ACCESS.2024.3361399","article-title":"Traffic improvement in Manhattan road networks with the use of parallel hybrid biobjective genetic algorithm","volume":"12","author":"Akopov","year":"2024","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3143","DOI":"10.1007\/s00521-022-07880-4","article-title":"Mix-attention approximation for homogeneous large-scale multi-agent reinforcement learning","volume":"35","author":"Yang","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/s10458-023-09633-6","article-title":"A survey of multi-agent deep reinforcement learning with communication","volume":"38","author":"Zhu","year":"2024","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"47646","DOI":"10.1109\/ACCESS.2023.3275883","article-title":"Multi-agent reinforcement learning based on representational communication for large-scale traffic signal control","volume":"11","author":"Bokade","year":"2023","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2727","DOI":"10.1109\/TITS.2021.3128209","article-title":"Efficient resource allocation for multi-beam satellite-terrestrial vehicular networks: A multi-agent actor critic method with attention mechanism","volume":"23","author":"He","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_16","unstructured":"Thorpe, T.L., and Anderson, C.W. (1996). Traffic Light Control Using SARSA with Three State Representations, IBM Corporation."},{"key":"ref_17","unstructured":"Wiering, M. (July, January 29). Multi-agent reinforcement learning for traffic light control. Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000), Stanford, CA, USA."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jin, J., and Ma, X. (2015, January 1\u201315). Adaptive group-based signal control using reinforcement learning with eligibility traces. Proceedings of the 2015 IEEE 18th International Conference on Intelligent Transportation Systems, Gran Canaria, Spain.","DOI":"10.1109\/ITSC.2015.389"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Aleko, D.R., and Djahel, S. (2020). An efficient adaptive traffic light control system for urban road traffic congestion reduction in smart cities. Information, 11.","DOI":"10.3390\/info11020119"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1016\/j.trc.2014.12.009","article-title":"A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework","volume":"58","author":"Zhu","year":"2015","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_21","unstructured":"Medina, J.C., and Benekohal, R. (2014, January 12\u201316). Corridor-based coordination of learning agents for traffic signal control by enhancing Max-Plus algorithm. Proceedings of the Transportation Research Board 93rd Annual Meeting, Washington, DC, USA."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1109\/TETCI.2023.3309738","article-title":"Hierarchical coordination multi-agent reinforcement learning with spatio-temporal abstraction","volume":"8","author":"Ma","year":"2024","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"17382","DOI":"10.1109\/TITS.2022.3151080","article-title":"A general framework for decentralized safe optimal control of connected and automated vehicles in multi-lane signal-free intersections","volume":"23","author":"Xu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"457","DOI":"10.3390\/signals4020024","article-title":"Vehicular visible light communication for intersection management","volume":"4","author":"Vieira","year":"2023","journal-title":"Signals"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/j.sysarc.2019.02.009","article-title":"All one needs to know about fog computing and related edge computing paradigms: A complete survey","volume":"98","author":"Yousefpour","year":"2019","journal-title":"J. Syst. Archit."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Bilal, J.M., and Jacob, D. (2007, January 24\u201327). Intelligent traffic control system. Proceedings of the 2007 IEEE International Conference on Signal Processing and Communications, Dubai, United Arab Emirates.","DOI":"10.1109\/ICSPC.2007.4728364"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3341","DOI":"10.1109\/TVT.2008.2002957","article-title":"Analytical model for connectivity in vehicular ad hoc networks","volume":"57","author":"Yousefi","year":"2008","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Shen, W.-H., and Tsai, H.-M. (2017, January 27\u201329). Testing vehicle-to-vehicle visible light communications in real-world driving scenarios. Proceedings of the 2017 IEEE Vehicular Networking Conference (VNC), Torino, Italy.","DOI":"10.1109\/VNC.2017.8275596"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1109\/TVT.2018.2890726","article-title":"A deep reinforcement learning network for traffic light cycle control","volume":"68","author":"Liang","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Alvarez Lopez, J., Behrisch, M., Bieker-Walz, L., Erdmann, J., Fl\u00f6tter\u00f6d, Y.P., and Hilbrich, R. (2018, January 4\u20137). Microscopic traffic simulation using SUMO. Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, USA.","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref_31","first-page":"100305","article-title":"Measurement-based VLC channel characterization for I2V communications in a real urban scenario","volume":"28","author":"Caputo","year":"2021","journal-title":"Veh. Commun."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Miranda, R.F., Barriquello, C.H., Reguera, V.A., Denardin, G.W., Thomas, D.H., Loose, F., and Amaral, L.S. (2023). A review of cognitive hybrid radio frequency\/visible light communication systems for wireless sensor networks. Sensors, 23.","DOI":"10.3390\/s23187815"},{"key":"ref_33","unstructured":"Li, G., Nakajima, K., and Srivastava, A.K. (2023). Dynamic vehicular visible light communication for traffic management. Next-Generation Optical Communication: Components, Sub-Systems, and Systems XII., SPIE."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"666","DOI":"10.3390\/vehicles6020031","article-title":"Enhancing urban intersection efficiency: Utilizing visible light communication and learning-driven control for improved traffic signal performance","volume":"6","author":"Vieira","year":"2024","journal-title":"Vehicles"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"076101","DOI":"10.1117\/1.OE.57.7.076101","article-title":"Cooperative vehicular communication systems based on visible light communication","volume":"57","author":"Vieira","year":"2018","journal-title":"Opt. Eng."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/S1474-6670(17)30657-2","article-title":"Overview of road traffic control strategies","volume":"37","author":"Papageorgiou","year":"2004","journal-title":"IFAC Proc. Vol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1689","DOI":"10.1007\/s11277-007-9336-6","article-title":"A novel vehicular mobility model for wireless networks","volume":"43","author":"Vieira","year":"2007","journal-title":"Wirel. Pers. Commun."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Sousa, I., Queluz, P., Rodrigues, A., and Vieira, P. (2011, January 27\u201329). Realistic mobility modeling of pedestrian traffic in wireless networks. Proceedings of the 2011 IEEE EUROCON\u2014International Conference on Computer as a Tool, Lisbon, Portugal.","DOI":"10.1109\/EUROCON.2011.5929242"}],"container-title":["Sustainability"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2071-1050\/17\/22\/10056\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T05:21:15Z","timestamp":1763011275000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2071-1050\/17\/22\/10056"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":38,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["su172210056"],"URL":"https:\/\/doi.org\/10.3390\/su172210056","relation":{},"ISSN":["2071-1050"],"issn-type":[{"type":"electronic","value":"2071-1050"}],"subject":[],"published":{"date-parts":[[2025,11,11]]}}}