Knezevic, Milan (University of Pittsburgh), Stevanovic, Aleksandar (University of Pittsburgh)

Dynamic Lane-Changing Strategy for Combined Flexible Lane Assignment and Reservation-Based Intersection Control

Scheduled for presentation during the Regular Session "S38a-Towards Scalable and Trustworthy AI in Connected Mobility" (FR-LM-T38), Friday, November 21, 2025, 12:10−12:30, Coolangata 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

This study proposes a dynamic lane-sharing algorithm to enhance the Combined Flexible Lane Assignment and Reservation-Based Intersection Control (CFLARIC) system. Traditional CFLARIC relies on fixed proportions of vehicles utilizing sharable lanes, which limits space utilization and system performance under high-demand conditions. To address this limitation, a dynamic lane-changing strategy is introduced, enabling vehicles to adjust their desired lane in real time to the adjacent lane with lower occupancy. The performance of Dynamic CFLARIC was compared against Fixed-Proportion CFLARIC, CADLARIC, Fully Reservation-Based Intersection Control (FRIC), and Fixed-Time Control (FTC). Results show that Dynamic CFLARIC significantly improves main performance measures relative to the baseline methods, particularly under congested conditions. Overall, the combination of spatial conflict resolution and dynamic lane selection fundamentally demonstrates that addressing conflicts upstream is a critical factor in achieving lower delays, improved space utilization, and enhanced traffic efficiency.