arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.17841cs.RO

驾驶风险源自所需二维联合规避加速度

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

School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China（车辆与移动系统学院，清华大学，北京100084，中国）；State Key Laboratory of Intelligent Green Vehicle and Mobility, Beijing 100084, China（智能绿色车辆与移动国家重点实验室，北京100084，中国）；School of Traffic & Transportation Engineering, Central South University, Changsha 410000, China（交通与运输工程学院，中南大学，长沙410000，中国）；Singapore-MIT Alliance for Research and Technology (SMART), Massachusetts Institute of Technology, Singapore 138602, Singapore（新加坡-麻省理工联合研究技术联盟（SMART），麻省理工学院，新加坡138602，新加坡）；School of Automotive Engineering, Chang’an University, Xi’an 710064, China（汽车工程学院，长安大学，西安710064，中国）

Hao Cheng, Yanbo Jiang, Wenhao Yu, Rui Zhou, Jiang Bian, Keyu Chen, Zhiyuan Liu, Heye Huang, Hailun Zhang, Fang Zhang, Jianqiang Wang, Sifa Zheng

备注：
23 pages, 5 figures; supplementary information provided as an ancillary file
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出二维规避加速度模型，用于更准确地量化碰撞风险，通过分析所有可能的规避方向，定义风险为所需最小相对加速度矢量的模，该方法在多个数据集上表现出更早的显著预警和更好的碰撞预测能力。

摘要：

大多数自动驾驶安全基准使用时间到碰撞（TTC）来评估风险并指导安全行为。然而，基于TTC的方法将风险视为一维的接近问题，尽管碰撞避免本质上是二维的，因此无法准确捕捉风险及其随时间的变化。本文报告了规避加速度（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将风险定义为所需最小的恒定相对加速度矢量的模，以改变相对运动并使交互无碰撞。使用五个开放数据集和超过600次真实碰撞数据，我们推导出基于百分位数的警告阈值，并证明EA在所有阈值下提供最早统计上显著的预警。此外，EA在最终碰撞结果的判别能力上最佳，并在所有比较基线上提高了54.2-241.4%的信息保留率。将EA加入现有方法可获得17.5-95.5倍的信息增益，表明EA捕获了现有方法中大部分结果相关的信息，同时贡献了大量非冗余信息。总体而言，EA更好地捕捉了碰撞风险的结构，并为下一代自动驾驶系统提供了基础。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑