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

2025-10-31

AI Summary

To address the lack of effective quantitative metrics for lateral conflict risk in urban environments, this paper proposes the Modified Emergency Index (MEI), specifically designed for lateral evasive maneuvers. MEI reconstructs the time-prediction model by integrating kinematic analysis and time-margin modeling, enabling more accurate characterization of risk evolution with superior sensitivity to lateral risk and higher temporal resolution compared to conventional longitudinal-oriented metrics such as ACT and PET. We construct a high-fidelity lateral conflict dataset based on Argoverse-2 and validate MEI on over 1,500 real-world conflict scenarios; it achieves significantly improved detection accuracy for more than 500 high-risk events. The open-source implementation is publicly available and compatible with mainstream autonomous driving safety evaluation frameworks.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• Quantifying evasive effort in lateral conflicts for autonomous driving
• Addressing limitations of existing metrics in urban lateral conflict scenarios
• Enhancing safety assessment framework with improved criticality measurement

Innovation

• Proposes Modified-Emergency Index for lateral conflicts
• Refines time estimation for evasive maneuvers
• Outperforms ACT and PET in risk quantification