Authors : Sara Tazeen; Dr. Sudhakara A. M.

Volume/Issue : Volume 11 - 2026, Issue 9 - September

Google Scholar : https://tinyurl.com/2ufpnyx8

DOI : https://doi.org/10.38124/ijisrt/26sep221

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

Abstract : Emergency Vehicle Preemption (EVP) can substantially reduce response times during urban emergencies, yet aggressive green-wave strategies often induce severe secondary congestion on competing approaches and prolong network recovery. This paper presents a communication-aware Multi-Agent Proximal Policy Optimization (MAPPO) framework for coordinated Vehicle-to-Infrastructure (V2I) traffic signal control and Vehicle-to-Vehicle (V2V) cooperative lane yielding. Each signalized intersection is modeled as an autonomous agent that selects traffic-signal actions using localized queue measurements, emergency vehicle (EV) telemetry, corridor demand, and dynamic V2X communication state parameters. The framework employs centralized training with decentralized execution (CTDE). V2I communication transmits priority pre-emption requests to roadside controllers, whereas V2V communication enables Connected Autonomous Vehicles (CAVs) to execute cooperative yielding manoeuvres along the EV's projected path. Implemented in the Simulation of Urban Mobility (SUMO) environment via the Traffic Control Interface (TraCI), the proposed architecture is evaluated under diverse traffic-demand levels, CAV penetration rates, packet-loss profiles, and communication latencies. Comparative experiments against fixed-time control, distance-based rule pre-emption, and single-mode ablation baselines demonstrate that the joint V2X-MAPPO approach significantly minimizes EV travel times while bounding non-emergency vehicle delays and post-event queue recovery periods.

Keywords : Component; Formatting; Style; Styling; Insert (Keywords).

References :

1. P. A. Lopez, M. Behrisch, L. Bieker-Walz, J. Erdmann, Y.-P. Flötzeröd, R. Hilbrich, L. Lücken, J. Rummel, P. Wagner, and E. Wießner, "Microscopic Traffic Simulation using SUMO," IEEE International Conference on Intelligent Transportation Systems (ITSC), pp. 2575–2582, 2018.
2. C. Sommer, R. German, and F. Dressler, "A Bidirectional Coupling Simulation Framework for Vehicular Networks," IEEE Transactions on Mobile Computing, vol. 10, no. 1, pp. 3–15, 2011.
3. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, "Proximal Policy Optimization Algorithms," arXiv preprint arXiv:1707.06347, 2017.
4. H. Wei, C. Chen, G. Zheng, K. Wu, H. Vikalo, and Z. Li, "PressLight: Learning Max Pressure Control for Traffic Signal in Wireless Sensor Networks," ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 853–861, 2019.
5. K. Katsaros, C. Sommer, and F. Dressler, "Cooperative ITS Simulation Frameworks: Integrating SUMO and Network Simulators for V2X," IEEE Communications Magazine, vol. 62, no. 3, pp. 112–118, 2024.
6. J. Park, S.-L. Kim, and S.-Y. Choi, "C-V2X Direct Communication Protocols for Time-Critical Vehicular Emergency Applications," IEEE Wireless Communications, vol. 30, no. 4, pp. 88–95, 2023.
7. Y. Gu, L. Zhang, J. Sun, and X. Chen, "Multi-Agent Deep Reinforcement Learning for Emergency Vehicle Priority Signal Control With Connected Vehicles," IEEE Transactions on Vehicular Technology, vol. 72, no. 11, pp. 13982–13994, 2023.
8. S. Al-Majeed, O. Al-Heety, and A. Al-Kerawi, "V2X-Enabled Dynamic Traffic Signal Preemption Framework for Emergency Vehicles in Smart Cities," IEEE Access, vol. 11, pp. 45210–45223, 2023.
9. M. Noori, X. Zhao, and H. Wang, "Multi-agent reinforcement learning for emergency vehicle prioritization considering non-emergency vehicle delays," Transportation Research Part C: Emerging Technologies, vol. 148, p. 104032, 2023.
10. Z. Huang, K. Zhang, and Y. Liu, "MARL-EVP: Multi-Agent Reinforcement Learning with Action Masking for Urban Emergency Vehicle Preemption," Applied Soft Computing, vol. 146, p. 110650, 2023.
11. C. Ding, I. W.-H. Ho, E. Chung, and T. Fan, "V2X and Deep Reinforcement Learning-Aided Mobility-Aware Lane Changing for Emergency Vehicle Preemption in Connected Autonomous Transport Systems," IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 7, pp. 7281–7293, 2024.
12. C. Zhao, Y. Qiu, and L. Wang, "Deep Reinforcement Learning for Adaptive Traffic Signal Control Under Partial V2X Penetration Rates," IEEE Transactions on Automation Science and Engineering, vol. 21, no. 2, pp. 1890–1902, 2024.
13. Q. Tan, J. Liu, and X. Xia, "Cooperative routing and traffic signal preemption for emergency vehicles: A multi-agent DRL approach," Information Sciences, vol. 660, p. 120140, 2024.
14. R. Torres, C. Sanchez, and M. Gomez, "Performance Evaluation of DSRC vs. C-V2X for Emergency Vehicle Preemption under Congested Urban Trajectory," Ad Hoc Networks, vol. 153, p. 103340, 2024.
15. M. Reza, M. S. Alam, and T. Hassan, "SUMO-Gym-V2X: An Open Benchmarking Environment for RL-based Connected Autonomous Vehicle Research," Computer Communications, vol. 214, pp. 45–58, 2024.
16. B. M. Preksha and S. Nagaraj, "Emergency Vehicle Prioritization Using RL and V2X Aided SUMO Simulations," International Journal of Advanced Research in Computer and Communication Engineering, vol. 14, no. 1, pp. 149–158, 2025.
17. S. Roy, Y. Zhang, and A. Patel, "Development of Emergency Vehicle Preemption Strategies on Smart Corridors in a Digital Twin Environment," IEEE Transactions on Intelligent Transportation Systems, vol. 26, no. 2, pp. 1842–1854, 2025.