ITSC 2025 Paper Abstract

Paper TH-EA-T17.6

Cheng, Hao (Tsinghua University), Jiang, Yanbo (tsinghua university), SHI, Qingyuan (Tsinghua University), Qingwen, Meng (Tsinghua university), chen, keyu (tsinghua university), Yu, Wenhao (Tsinghua University), Wang, Jianqiang (Tsinghua University), Zheng, Sifa (Tsinghua University)

Modified-Emergency Index (MEI): Advanced Criticality Metric for Autonomous Driving in Lateral Conflict

Scheduled for presentation during the Invited Session "S17b-Synthetic-Data-Aided Safety-Critical Scenario Understanding in ITS" (TH-EA-T17), Thursday, November 20, 2025, 14:50−15:30, 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 Evaluation of Autonomous Vehicle Performance in Mixed Traffic Environments, Safety Verification and Validation Methods for Autonomous Vehicle Technologies, Methods for Verifying Safety and Security of Autonomous Traffic Systems

Abstract

Effective, reliable, and efficient evaluation of autonomous driving safety is essential to demonstrate its trustworthiness. Criticality metrics provide an objective means of assessing safety. However, as existing metrics primarily target longitudinal conflicts, accurately quantifying the risks of lateral conflicts—prevalent in urban settings—remains challenging. This paper proposes the Modified-Emergency Index (MEI), a metric designed to quantify evasive effort in lateral conflicts. Compared to the original Emergency Index (EI), MEI refines the estimation of the time available for evasive maneuvers, enabling more precise risk quantification. We validate MEI on a public lateral conflict dataset based on Argoverse-2, from which we extract over 1,500 high-quality AV conflict cases, including more than 500 critical events. MEI is then compared with the well-established ACT and the widely used PET metrics. Results show that MEI consistently outperforms them in accurately quantifying criticality and capturing risk evolution. Overall, these findings highlight MEI as a promising metric for evaluating urban conflicts and enhancing the safety assessment framework for autonomous driving.The open-source implementation is available at https://github.com/AutoChengh/MEI.