Monteiro, Fernando (University of Southern California), Savla, Ketan (University of Southern California)

Anytime CAV Sorting Algorithm for Mixed-Traffic Multi-Lane Highways

Scheduled for presentation during the Video Session "On-Demand Video Presentations" (VP-VP), Saturday, November 22, 2025, 08:00−18:00, On-Demand Platform

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 April 2, 2026

Abstract

This paper addresses the problem of ensuring Connected Autonomous Vehicles (CAVs) reach their desired lanes before some location downstream in mixed-traffic highways. We propose a centralized planning approach that issues high-level command sequences to each CAV, while relying on the CAVs' own onboard controllers to react in real-time to unexpected human behavior and decide when to start lateral maneuvers. The core of our method, based on the symbolic synthesis approach, discretizes the system into a graph of quantized states, where edges correspond to sets of commands. Given the combinatorial nature of the problem, it is essential to use an approach that can provide solutions within computational time constraints. This is achieved via a heuristic search that identifies an initial solution, followed by a cached branch-and-bound depth-first search. Simulations in dense, low-penetration scenarios demonstrate that the centralized controller can effectively bring distant CAVs together to facilitate cooperative lane changes and guide them to their desired lanes.