ITSC 2025 Paper Abstract

Paper TH-LM-T17.2

Wang, Youran (Technical University of Munich), Althoff, Matthias (Technische Universität München)

Determining Invariably Rule-Compliant States for Motion Planning of Autonomous Vehicles

Scheduled for presentation during the Invited Session "S17a-Synthetic-Data-Aided Safety-Critical Scenario Understanding in ITS" (TH-LM-T17), Thursday, November 20, 2025, 10:50−11:10, Southport 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

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

Abstract

Autonomous road vehicles must adhere to traffic rules. However, existing motion planning approaches typically only verify rule compliance for finite time horizons. As a result, the existence of rule-compliant trajectories is not ensured in subsequent planning cycles, potentially leading to traffic rule violations. To address this issue, we introduce invariably rule-compliant sets, defined as collections of states where a vehicle can maintain compliance with traffic rules over an infinite time horizon. Furthermore, we propose an efficient approach for determining the invariably rule-compliant sets online, which can be applied to traffic rules formalized in temporal logic. We evaluate the proposed approach using the CommonRoad benchmark suite, demonstrating that invariably rule-compliant sets facilitate motion planning by offering guarantees of rule compliance and assessing the criticality of traffic scenarios.