Intelligent Traffic Control using Fuzzy Logic and Reinforcement Learning
Keywords:
Deep Q Network (DQN), Fuzzy inference system, Fuzzy logic, Reinforcement learning, Simulation of Urban Mobility (SUMO)Abstract
The increasing urbanisation and vehicular density in modern cities have rendered traditional traffic signal control systems inefficient, leading to frequent congestion, excessive fuel consumption, and elevated emissions. Static or rule-based traffic management techniques often fail to respond to real-time traffic dynamics, particularly under uncertain or fluctuating conditions. This paper presents an intelligent, adaptive traffic control framework that combines Fuzzy Logic and Reinforcement Learning (RL) to optimize traffic signal operations in real time.
Fuzzy Logic, with its ability to model human-like reasoning and handle imprecise data, enables the system to interpret ambiguous traffic conditions such as partially congested roads or inconsistent vehicle arrival patterns. Simultaneously, Reinforcement Learning empowers the system to learn from its interactions with the environment, refining its control strategies over time through trial and reward feedback mechanisms. The proposed hybrid model leverages fuzzy inference to guide the RL agent’s decisions, improving both convergence speed and decision reliability.
To evaluate the effectiveness of the approach, simulations were conducted using a realistic urban intersection environment within the SUMO (Simulation of Urban Mobility) platform. Input parameters included vehicle density, queue length, waiting time, and traffic flow direction. The hybrid fuzzy-RL model dynamically adjusted signal phase durations to minimize total delay and vehicle queuing while maximizing throughput. Results showed significant performance improvements over conventional fixed-time and isolated AI-based systems. On average, the system reduced waiting times by 45%, improved intersection throughput by 30%, and lowered CO₂ emissions due to idling vehicles.
This research demonstrates that combining fuzzy logic’s interpretability and RL’s adaptability can yield a robust, scalable solution for intelligent traffic signal control. The proposed architecture is highly suitable for integration into smart city infrastructures and can be extended to multi-agent coordination for city-wide traffic management.
References
P. Michailidis, I. Michailidis, C. R. Lazaridis, and E. Kosmatopoulos, “Traffic Signal Control via Reinforcement Learning: A Review on Applications and Innovations,” Infrastructures, vol. 10, no. 5, pp. 114–114, May 2025, doi: https://doi.org/10.3390/infrastructures10050114.
A. Saadi, N. Abghour, Z. Chiba, K. Moussaid, and S. Ali, “A survey of reinforcement and deep reinforcement learning for coordination in intelligent traffic light control,” Journal of Big Data, vol. 12, no. 1, Apr. 2025, doi: https://doi.org/10.1186/s40537-025-01104-x.
M. Li, J. Wang, B. Du, J. Shen, and Q. Wu, “FuzzyLight: A Robust Two-Stage Fuzzy Approach for Traffic Signal Control Works in Real Cities,” Arxiv.Org, 2025. https://arxiv.org/abs/2501.15820
Y. Bi, Q. Ding, Y. Du, D. Liu, and S. Ren, “Intelligent Traffic Control Decision-Making Based on Type-2 Fuzzy and Reinforcement Learning,” Electronics, vol. 13, no. 19, pp. 3894–3894, Oct. 2024, doi: https://doi.org/10.3390/electronics13193894.
I. Tunc and M. T. Soylemez, “Fuzzy logic and deep Q learning based control for traffic lights,” Alexandria Engineering Journal, vol. 67, pp. 343–359, Mar. 2023, doi: https://doi.org/10.1016/j.aej.2022.12.028.
I.-M. Vlasceanu, V.-C. - Doinita Ceapa, I. S. Sacala, and N. Constantin, “Comparative Evaluation of Fuzzy Logic and Q-Learning for Adaptive Urban Traffic Signal Control,” Electronics, vol. 14, no. 14, pp. 2759–2759, Jul. 2025, doi: https://doi.org/10.3390/electronics14142759.
S. Wang and S. Wang, “A Novel Multi-Agent Deep RL Approach for Traffic Signal Control,” arXiv.org, 2023. https://arxiv.org/abs/2306.02684
T. Tan, T. Chu, B. Peng, and J. Wang, “Large-Scale Traffic Grid Signal Control Using Decentralized Fuzzy Reinforcement Learning,” Lecture Notes in Networks and Systems, pp. 652–662, Aug. 2017, doi: https://doi.org/10.1007/978-3-319-56994-9_44.
Z. Li, H. Yu, G. Zhang, S. Dong, and C.-Z. Xu, “Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning,” Transportation Research Part C: Emerging Technologies, vol. 125, p. 103059, Apr. 2021, doi: https://doi.org/10.1016/j.trc.2021.103059.
A. M Rahmani, R. A. Naqvi, M. Hosseinzadeh, and K. Siddique, “A Q-Learning and Fuzzy Logic-Based Hierarchical Routing Scheme in the Intelligent Transportation System for Smart Cities,” Mathematics, vol. 10, no. 22, pp. 4192–4192, Nov. 2022, doi: https://doi.org/10.3390/math10224192.
W. Du, J. Ye, J. Gu, J. Li, H. Wei, and G. Wang, “SafeLight: A Reinforcement Learning Method toward Collision-Free Traffic Signal Control,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 12, pp. 14801–14810, Jun. 2023, doi: https://doi.org/10.1609/aaai.v37i12.26729.
M. Q. Zaman and H.-M. Wu, “An improved fuzzy inference strategy using reinforcement learning for trajectory-tracking of a mobile robot under a varying slip ratio,” Robotica, vol. 42, no. 4, pp. 1134–1152, Jan. 2024, doi: https://doi.org/10.1017/s0263574724000134.
T. Meepokgit and S. Wisayataksin, “Traffic Signal Control with State-Optimizing Deep Reinforcement Learning and Fuzzy Logic,” Applied Sciences, vol. 14, no. 17, p. 7908, Sep. 2024, doi: https://doi.org/10.3390/app14177908.
Z. Huang, “Reinforcement learning based adaptive control method for traffic lights in intelligent transportation,” Alexandria Engineering Journal, vol. 106, pp. 381–391, Nov. 2024, doi: https://doi.org/10.1016/j.aej.2024.07.046.
G. Han, X. Liu, Y. Han, X. Peng, and H. Wang, “CycLight: Learning traffic signal cooperation with a cycle-level strategy,” Expert Systems with Applications, vol. 255, pp. 124543–124543, Jun. 2024, doi: https://doi.org/10.1016/j.eswa.2024.124543.
H. Gu et al., “Large-Scale Traffic Signal Control Using Constrained Network Partition and Adaptive Deep Reinforcement Learning,” IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 7, pp. 7619–7632, Jul. 2024, doi: https://doi.org/10.1109/tits.2024.3352446.
J. Guo, L. Cheng, and S. Wang, “CoTV: Cooperative Control for Traffic Light Signals and Connected Autonomous Vehicles Using Deep Reinforcement Learning,” IEEE Transactions on Intelligent Transportation Systems, pp. 1–12, 2023, doi: https://doi.org/10.1109/TITS.2023.3276416.
M. Li, X. Pan, C. Liu, and Z. Li, “Federated deep reinforcement learning-based urban traffic signal optimal control,” Scientific Reports, vol. 15, no. 1, Apr. 2025, doi: https://doi.org/10.1038/s41598-025-91966-1.
