Abstract
Urban traffic congestion is an increasingly pressing issue and advanced solutions like intelligent traffic control systems are becoming unavoidable. This paper explores the application of reinforcement learning to enhance traffic flow and reduce congestion. Our goal was to develop a reinforcement learning-based model that adapts to varying traffic conditions in real-time. Several methods are available for the real-time optimization of traffic, ranging from analytical methods to more flexible metaheuristic methods and reinforcement learning-based solutions. Each method lacks either adaptivity or scalability, or the completeness of the global optimization, or the performance requirement is too high. Based on the different requirements it is clearly a challenging task. The focus of our research is on the scalability, and computational efficiency of the model by using a method of sharing information that is similar to a cellular network. Our solution is not just easy to scale but also able to search for the global optimum with a low computational cost. A general model was trained to achieve out-of-the-box usage capability. The control network also can be finetuned for better performance. Our comprehensive analysis showed that smart traffic lights significantly enhance the efficiency of traffic systems, boasting improvements ranging from 10% to 80% compared to traditional and other reinforcement learning-based solutions. These intelligent controllers not only reduce waiting times but also contribute to environmental protection by reducing the carbon footprint.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alegre, L.N.: SUMO-RL (2019). https://github.com/LucasAlegre/sumo-rl. Accessed 31 Jan 2024
de Almeida, V.N., Bazzan, A.L., Abdoos, M.: Multiagent reinforcement learning for traffic signal control: a k-nearest neighbors based approach. In: ATT2022: Workshop Agents in Traffic and Transportation, vol. 3173 (2022)
Ault, J., Hanna, J., Sharon, G.: Learning an interpretable traffic signal control policy. arXiv preprint arXiv:1912.11023 (2019)
Ault, J., Sharon, G.: Reinforcement learning benchmarks for traffic signal control. In: Vanschoren, J., Yeung, S. (eds.) Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, vol. 1. Curran (2021)
Brockman, G., et al.: OpenAI Gym (2016)
Chen, C., et al.: Toward a thousand lights: decentralized deep reinforcement learning for large-scale traffic signal control. Proc. AAAI Conf. Artif. Intell 34, 3414–3421 (2020)
Petit, S.: World vehicle population rose 4.6% in 2016 (2017). https://wardsintelligence.informa.com/WI058630/World-Vehicle-Population-Rose-46-in-2016. Accessed 14 Sept 2023
Reza, S., Ferreira, M.C., Machado, J.J.M., Tavares, J.M.R.S.: A citywide TD-learning based intelligent traffic signal control for autonomous vehicles: performance evaluation using SUMO. Exp. Syst. 2013, e13301 (2023). https://doi.org/10.1111/exsy.13301
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Sohrabi, S., Zietsman, J., Khreis, H.: Burden of disease assessment of ambient air pollution and premature mortality in urban areas: the role of socioeconomic status and transportation. Int. J. Environ. Res. Public Health 17(4), 1166 (2020)
Stevanovic, A., Kergaye, C., Martin, P.: Scoot and scats: a closer look into their operations. In: Transportation Research Board 88th Annual Meeting (2009)
Terry, J.K., et al.: Pettingzoo: gym for multi-agent reinforcement learning (2021)
Wei, H., et al.: Presslight: learning max pressure control to coordinate traffic signals in arterial network. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2019), pp. 1290–1298. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3292500.3330949
Zang, X., Yao, H., Zheng, G., Xu, N., Xu, K., Li, Z.: Metalight: value-based meta-reinforcement learning for traffic signal control. Proc. AAAI Conf. Artif. Intell. 34(01), 1153–1160 (2020). https://doi.org/10.1609/aaai.v34i01.5467
Zheng, G., et al.: Learning phase competition for traffic signal control. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM 2019), pp. 1963–1972. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3357384.3357900
Zheng, G., et al.: Diagnosing reinforcement learning for traffic signal control. arXiv preprint arXiv:1905.04716 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Barta, Z., Kovács, S., Botzheim, J. (2024). Reinforcement Learning-Based Cooperative Traffic Control System. In: Nguyen, N.T., et al. Computational Collective Intelligence. ICCCI 2024. Lecture Notes in Computer Science(), vol 14811. Springer, Cham. https://doi.org/10.1007/978-3-031-70819-0_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-70819-0_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-70818-3
Online ISBN: 978-3-031-70819-0
eBook Packages: Computer ScienceComputer Science (R0)