Machine Learning-Based Cooperative Vehicle and Traffic Control

Traffic in modern urban road networks is monitored by a variety of sensors such as loop detectors, traffic cameras, or even V2X-based solutions. Real-time traffic information and predictions of future events can be effectively used to control traffic lights in a way that minimizes queues at intersections, increases intersection throughput, and thus reduces congestion in the city. Machine learning-based traffic optimization aims to enable the traffic management system to recognize different traffic conditions and intervene effectively. Reinforcement learning can be used not only to control traffic lights but also to implement self-driving functions in vehicles or to change traffic rules dynamically.

Our research focuses on the highest (level 5) self-driving methods, which enable fully autonomous driving without human supervision. Our main goals are to use data streams from different sensors for machine learning-based traffic and vehicle control and to develop new cooperative self-driving methods.

Research areas:

  • Cooperative autonomous vehicle control in urban environments without traffic lights using multi-agent
  • Reinforcement learning-based road infrastructure management methods



  • Hasanain Alabbas, Árpád Huszák, „A New Gateway Selection Algorithm Based on Multi-Objective Integer Programming and Reinforcement Learning”, Infocommunications Journal, Vol. XIV, No 4, pp. 4-10., December 2022
  • Hasanain Alabbas, Árpád Huszák, „Reinforcement Learning based Gateway Selection in VANETs”, International Journal of Electrical and Computer Engineering Systems (ISSN 1847-6996, 1847-7003), Vol. 13 No. 3, pp 195-202, April 2022
  • Lincoln Teixeira, Árpád Huszák, „Reinforcement Learning Environment for Advanced Vehicular Ad Hoc Networks Communication Systems”, Sensors. 2022; vol. 22, no. 13: 4732, 23 June 2022
  • Lincoln Teixeira, Árpád Huszák, ” Service-based Network Selection in C-ITS Vehicular Networks,” International Journal of Communication Networks and Distributed Systems (IJCNDS), Inderscience Publishers, Vol. 26, No. 2, pp 135-158, 2021, DOI: 10.1504/IJCNDS.2021.10032088, online ISSN 1754-3924, 2021
  • Hasanain Alabbas, Árpád Huszák, ”A New Clustering Algorithm for Live Road Surveillance on Highways based on DBSCAN and Fuzzy Logic,” International Journal of Advanced Computer Science and Applications (IJACSA), Volume 11 Issue 8, 2020.
  • Péter Pálos, Árpád Huszák, „ReLight-WCTM: Multi-Agent Reinforcement Learning Approach for Traffic Light Control within a Realistic Traffic Simulation”, 2021 44th International Conference on Telecommunications and Signal Processing (TSP), pp. 62-65, 26-28 July 2021 (Best Student Paper Award)
  • Péter Pálos, Árpád Huszák, ” Comparison of Q-Learning based Traffic Light Control Methods and Objective Functions,” 2020 International Conference on Software, Telecommunications and Computer Networks (SoftCOM), Split, Hvar, Croatia, 17-19 Sept. 2020