Authors : R. Sasi Vardhan; M. Lohith Reddy; N. Bhanu Prakash; S. Vidhya; Dr. T. Kumanan; Dr. M. Nisha

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/3svamhu8

Scribd : https://tinyurl.com/msbn9vsh

DOI : https://doi.org/10.38124/ijisrt/26mar1021

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Urban traffic is a problem in modern cities. It makes our travel time longer we use fuel and the air gets polluted. The old way of controlling traffic signals does not work well because it cannot adapt to the changing traffic. This paper talks about a way to manage urban traffic using Artificial Intelligence. It uses real time traffic data learning to predict traffic congestion and reinforcement learning to control traffic signals. We use a kind of computer network called Long Short- Term Memory to understand traffic patterns over time. Another kind of network called Deep Q-Network helps to adjust the traffic signals. We tested this system using a simulator called SUMO to see how well it works in traffic conditions. The results show that this system reduces the number of cars waiting in line and the time they wait compared to the way of controlling traffic signals. The new approach is good, for traffic management systems because it is scalable and efficient.

Keywords : Artificial Intelligence, Traffic Signal Optimization, Deep Learning, Reinforcement Learning, Intelligent Transportation Systems, Smart City

References :

1. T. Litman, "The costs of urban traffic congestion," Victoria Transport Policy Institute, 2020.\
2. P. B. Hunt, D. I. Robertson, R. D. Bretherton, and M. C. Royle, "The SCOOT on-line traffic signal optimization technique," Traffic Engineering & Control, vol. 23, no. 4, pp. 190–192, 1982.
3. M. Papageorgiou, H. Hadj-Salem, and J. Blosseville, "ALINEA: A local feedback control law for on-ramp metering," Transportation Research Record, no. 1320, pp. 58–64, 1991.
4. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA, USA: MIT Press, 2018.
5. L. Busoniu, R. Babuska, and B. De Schutter, "A comprehensive survey of multi-agent reinforcement learning," IEEE Trans. Systems, Man, and Cybernetics, vol. 38, no. 2, pp. 156–172, 2008.
6. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, real-time object detection," in Proc. IEEE CVPR, 2016, pp. 779–788.
7. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735–1780,1997.
8. Y. Lv, Y. Duan, W. Kang, Z. Li, and F.-Y. Wang, "Traffic flow prediction with big data: A deep learning approach," IEEE Trans. Intelligent Transportation Systems, vol. 16, no. 2, pp. 865–873, 2015.
9. X. Liang, X. Du, G. Wang, and Z. Han, "Deep reinforcement learning for traffic light control in vehicular networks," IEEE Trans. Vehicular Technology, vol. 68, no. 2, pp. 1243–1253, 2019.
10. C. J. C. H. Watkins and P. Dayan, "Q-learning," Machine Learning, vol. 8, no. 3–4, pp. 279–292, 1992.
11. D. Krajzewicz, G. Hertkorn, C. Rössel, and P. Wagner, "SUMO (Simulation of Urban MObility): An open-source traffic simulation," in Proc. 4th Middle East Symp. Simulation and Modelling, 2002
12. H. Wei, G. Zheng, H. Yao, and Z. Li, "IntelliLight: A reinforcement learning approach for intelligent traffic light control," in Proc. ACM KDD, 2018, pp. 2496–2505.
13. Z. Li, M. Shahidehpour, and S. Bahramirad, "Adaptive traffic signal controls using deep Q-learning," IEEE Trans. Smart Grid, vol. 10, no. 2, pp. 2142–2152, 2019.
14. V. Mnih et al., "Human-level control through deep reinforcement learning," Nature, vol. 518, no. 7540, pp. 529–533, 2015.
15. Y. Zhang, Y. Zheng, and D. Qi, "Deep spatio-temporal residual networks for citywide crowd flows prediction," in Proc. AAAI, 2017.
16. L. Chen, C. Englund, and J. N. Jonsson, "Cooperative intersection management: A survey," IEEE Trans. Intelligent Transportation Systems, vol. 17, no. 2, pp. 570–586, 2016.
17. F.-Y. Wang, "Parallel control and management for intelligent transportation systems," IEEE Trans. Intelligent Transportation Systems, vol. 11, no. 3, pp. 630–638, 2010.
18. M. Abadi et al., "TensorFlow: A system for large-scale machine learning," in Proc. OSDI, 2016, pp. 265–283.
19. A. Krizhevsky, I. Sutskever, and G. Hinton, "ImageNet classification with deep convolutional neural networks," in Proc. NIPS, 2012.
20. Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, pp. 436–444, 2015.
21. World Health Organization, "Ambient air pollution: Health impacts," WHO Report, 2021.
22. United Nations, "Sustainable Development Goal 11: Sustainable cities and communities," UN Report, 2015.
23. K. Shao, Z. Tang, Y. Zhu, N. Li, and D. Zhao, "A survey of deep reinforcement learning in traffic signal control," IEEE Trans. Neural Networks and Learning Systems, vol. 33, no. 8, pp. 3234–3248, 2022.
24. S. B. Gokulan and D. Srinivasan, "Distributed reinforcement learning agents for traffic signal control," IEEE Trans. Intelligent Transportation Systems, vol. 11, no. 4, pp. 909–920, 2010.
25. M. Van der Pol and F. A. Oliehoek, "Coordinated deep reinforcement learners for traffic light control," in Proc. NIPS Workshop on Learning, Inference and Control of Multi-Agent Systems, 2016.
26. P. Sharma et al., "Smart Traffic Signal Control Using CNN and IoT Sensors," IEEE Access, 2020.
27. J. Li and Q. Zhang, "Reinforcement Learning for Urban Traffic Optimization," International Journal of AI Research, 2021.
28. A. Kumar et al., "Image Processing Based Vehicle Detection for Adaptive Signals," Springer Lecture Notes in Networks and Systems, 2022.
29. S. Mehta et al., "Fuzzy Logic Approach to Traffic Flow Control," IJERT, 2023.