Merolla, Chiara (Politecnico di Milano), specchia, simone (Politecnico di Milano), Andrea, Galimberti (Politecnico di Milano), Corno, Matteo (Politecnico di Milano), Panzani, Giulio (Politecnico di Milano), Savaresi, Sergio M. (Politecnico di Milano)

Autonomous Vehicle Intersection Management through Speed Optimization and Finite State Machine-Based Decision Making

Scheduled for presentation during the Invited Session "S20b-Foundation Model-Enabled Scene Understanding, Reasoning, and Decision-Making for Autonomous Driving and ITS" (TH-EA-T20), Thursday, November 20, 2025, 13:30−13:50, Surfers Paradise 2

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

Abstract

In an autonomous driving system, intersection management consists in determining the sequence of actions allowing the vehicle to cross an intersection safely. This paper presents an intersection management strategy for urban environments, integrating decision-making and speed planning. The proposed algorithm features a decision-making module that determines the vehicle behavior based on traffic rules while ensuring collision avoidance. A comfort-oriented speed optimization module generates a speed profile that aligns with the high-level decision. The approach is validated through real-world testing on a fully autonomous vehicle operating on public roads open to traffic. Experimental results indicate that the proposed method achieves a driving style comparable to that of human drivers in terms of comfort. Moreover, the system exhibits a more cautious and safety-oriented behavior when navigating intersections, enhancing overall reliability in complex traffic scenarios.