ITSC 2025 Paper Abstract

Paper TH-EA-T25.2

Wang, Yafei (Kansai University), Tokunaga, Junpei (Kansai University), Ebara, Hiroyuki (Kansai University), ueda, naonori (RIKEN AIP)

Route Search Algorithm for Predicting Traffic Congestion Based on Other Vehicles' Routes

Scheduled for presentation during the Regular Session "S25b-Cooperative and Connected Autonomous Systems" (TH-EA-T25), Thursday, November 20, 2025, 13:50−14:10, Cooleangata 4

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords Cooperative Vehicle-to-Vehicle Data Sharing for Safe and Efficient Traffic Flow, AI, Machine Learning and Predictive Analytics for Traffic Incident Detection and Management, Real-time Motion Planning and Control for Autonomous Vehicles in ITS Networks

Abstract

This paper presents a congestion-aware route planning algorithm tailored for autonomous vehicles using vehicle-to-vehicle (V2V) communication and real-time traffic prediction. As connected and autonomous vehicles (CAVs) become more widespread, traditional navigation systems that rely on static shortest-path algorithms fall short in dynamic urban environments. To address this, the proposed method builds a cost-variable time-expanded network, where edge costs are updated based on traffic volume using the Bureau of Public Roads (BPR) function. By discretizing time and incorporating vehicle density, the method transforms fluctuating road conditions into a static graph, enabling efficient route calculation using Dijkstra’s algorithm. Simulations were conducted in two real world urban networks—Tokyo’s Imperial Palace area and Sakai City, Osaka— showing 8.1%–8.2% reductions in average travel time and 6.5%–8.3% more vehicles reaching their destinations compared to conventional methods. The algorithm also proved robust when only partial V2V communication was available, maintaining performance even when 30% of vehicles lacked shared route data. Key contributions include modeling traffic capacity via safe intervehicle spacing and adapting travel times dynamically. Overall, this study demonstrated the practical potential of predictive, communication-enabled routing in easing congestion and improving traffic flow in smart cities.