ITSC 2025 Paper Abstract

Paper WE-EA-T11.3

Lercher, Florian (Technical University of Munich), Althoff, Matthias (Technische Universität München)

Efficient Driving Corridor Extraction for Autonomous Vehicles Using Best-First Reachability Analysis

Scheduled for presentation during the Regular Session "S11b-Motion Planning, Trajectory Optimization, and Control for Autonomous Vehicles" (WE-EA-T11), Wednesday, November 19, 2025, 14:10−14:30, Broadbeach 1&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 19, 2025

Keywords Real-time Motion Planning and Control for Autonomous Vehicles in ITS Networks, Safety Verification and Validation Methods for Autonomous Vehicle Technologies, Methods for Verifying Safety and Security of Autonomous Traffic Systems

Abstract

Planning traffic rule-compliant trajectories for autonomous vehicles is computationally expensive. It has been shown that restricting the search space of the trajectory planner to a driving corridor facilitates planning. Existing methods based on reachability analysis have to compute the entire reachable set before they can provide a single corridor. Since planners often require only one corridor, the computation of reachable states irrelevant to that corridor is superfluous. To address this issue, we propose treating reachability analysis for driving corridor extraction as a best-first search problem. Thus, we quickly identify a first corridor to start trajectory planning as early as possible; additional corridors are computed on demand. We experimentally compare different best-first search strategies and demonstrate the advantages of our approach.