Driving risk emerges from the required two-dimensional joint evasive acceleration

TL;DR

Evasive acceleration (EA) offers a two-dimensional, physically interpretable risk measure for autonomous driving, outperforming traditional time-to-collision methods in early warning and outcome discrimination.

Contribution

This paper introduces EA, a novel 2D risk quantification paradigm that captures collision avoidance dynamics more faithfully than existing 1D TTC-based methods.

Findings

EA provides earlier statistically significant warnings across thresholds.

EA improves collision outcome discrimination and information retention.

Adding EA yields substantial information gain over existing methods.

Abstract

Most autonomous driving safety benchmarks use time-to-collision (TTC) to assess risk and guide safe behaviour. However, TTC-based methods treat risk as a one-dimensional closing problem, despite the inherently two-dimensional nature of collision avoidance, and therefore cannot faithfully capture risk or its evolution over time. Here, we report evasive acceleration (EA), a hyperparameter-free and physically interpretable two-dimensional paradigm for risk quantification. By evaluating all possible directions of collision avoidance, EA defines risk as the minimum magnitude of a constant relative acceleration vector required to alter the relative motion and make the interaction collision-free. Using interaction data from five open datasets and more than 600 real crashes, we derive percentile-based warning thresholds and show that EA provides the earliest statistically significant warning across all thresholds. Moreover, EA provides the best discrimination of eventual collision outcomes and improves information retention by 54.2-241.4% over all compared baselines. Adding EA to existing methods yields 17.5-95.5 times more information gain than adding existing methods to EA, indicating that EA captures much of the outcome-relevant information in existing methods while contributing substantial additional nonredundant information. Overall, EA better captures the structure of collision risk and provides a foundation for next-generation autonomous driving systems.