Contact : 9561854529 Email : submitpaper@ijaea.com editorinchief.ijaea@gmail.com Working Hours: 9am to 9PM

International Journal of Advanced Engineering Application

ISSN: 3048-6807

Submit Paper Apply for Reviewer

Decentralized Swarm Intelligence for Real-Time Traffic Orchestration in Autonomous Urban Corridors

Author(s):Rajesh K., Shalini V., Thomas M.

Affiliation: Intelligent Transport Systems (ITS) Group, Private Healthcare Systems Group, Kochi, Kerala

Page No: 6-10

Volume issue & Publishing Year: Volume 3, Issue 3, 2026/03/03

Journal: International Journal of Advanced Engineering Application (IJAEA)

ISSN NO: 3048-6807

DOI: https://doi.org/10.5281/zenodo.19342792

Download PDF

Article Indexing:

Abstract:
Traditional centralized traffic management systems are increasingly inadequate for handling the high-velocity data streams generated by fully autonomous and connected vehicle fleets. This paper proposes a decentralized "Swarm Intelligence" framework for real-time traffic orchestration in high-density urban corridors. By treating each autonomous vehicle (AV) as an intelligent agent capable of local decision-making and peer-to-peer (V2V) coordination, we eliminate the latency bottlenecks associated with cloud-based control. The study utilizes a bio-inspired ant-colony optimization (ACO) algorithm to manage intersection throughput and minimize "Stop-and-Go" waves without the need for traditional traffic signaling. Our methodology employs a high-fidelity microscopic traffic simulation to test the framework under varying levels of AV penetration. The results demonstrate that decentralized swarm coordination can reduce average travel time by 32% and carbon emissions by 14% through smoother velocity profiles. The findings provide a scalable architecture for future smart cities, where traffic flow is a self-organizing process rather than a centrally dictated command.

Keywords: Swarm Intelligence, Autonomous Vehicles (AV), Traffic Flow Optimization, Decentralized Control, V2X Communication, Edge Computing, Urban Mobility, Congestion Management, Multi-Agent Systems, Smart City Infrastructure.

Reference:

  • [1] Dorigo, M., et al. (2024). "Swarm Intelligence in Smart Cities: A Review of Decentralized Control Strategies." IEEE Transactions on Intelligent Transportation Systems, 25(2), 1150-1175.
  • [2] Wang, J., & Li, Q. (2025). "V2X-Enabled Cooperative Perception for Autonomous Swarms." Nature Communications, 16, 4021.
  • [3] Zhang, L., et al. (2025). "Physics-Informed Neural Networks for Real-Time Traffic Flow Prediction." Transportation Research Part C: Emerging Technologies, 162, 104521.
  • [4] Kumar, A., & Singh, P. (2026). "Decentralized Conflict Resolution at Signal-Free Intersections using Multi-Agent Reinforcement Learning." Journal of Robotics and Autonomous Systems, 174, 104689.
  • [5] Garcia, M., et al. (2024). "Latency Analysis of 6G-URLLC for Swarm Platooning." IEEE Communications Magazine, 62(5), 90-96.
  • [6] Chen, Y., et al. (2025). "Altruistic Path Planning in Mixed-Traffic Environments." ACM Transactions on Cyber-Physical Systems, 9(1), Article 4.
  • [7] Nguyen, T., & Park, H. (2026). "Bio-Inspired Traffic Orchestration: From Pheromones to Digital Twins." Renewable and Sustainable Energy Reviews, 210, 114920.
  • [8] Smith, J., et al. (2024). "The Impact of Swarm Intelligence on Urban Carbon Footprints." Energy Policy, 188, 114012.