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.

翻译：大多数自动驾驶安全基准使用碰撞时间（TTC）评估风险并引导安全行为。然而，基于TTC的方法将风险视为一维接近问题，尽管碰撞规避本质上具有二维特性，因此无法准确捕捉风险及其随时间演变。本文提出规避加速度（EA），一种无超参数且物理可解释的二维风险量化范式。通过评估所有可能的碰撞规避方向，EA将风险定义为改变相对运动并使交互无碰撞所需的最小恒定相对加速度矢量幅值。利用来自五个开放数据集和超过600起真实碰撞的交互数据，我们推导出基于百分比的预警阈值，并证明EA在所有阈值下提供最早统计显著的预警。此外，EA对最终碰撞结果提供了最佳区分能力，与所有对比基线相比，信息保留率提升54.2%-241.4%。将EA添加到现有方法中获得的信息增益，比在EA基础上添加现有方法高17.5-95.5倍，表明EA捕捉了现有方法中大部分结果相关信息，同时贡献了显著的非冗余额外信息。总体而言，EA更好地捕捉了碰撞风险的结构，为下一代自动驾驶系统奠定了基础。