arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

自动驾驶车辆:从最小风险状态过渡的挑战

Automated vehicles: Challenging transition from Minimal Risk Condition

Wolfgang Kröger, Leon Johann Brettin

arXiv 2608.07061首次发表:更新:

AI 中文总结

本文针对自动驾驶车辆无法执行驾驶任务时的滞留过渡问题,通过近30种原因及场景树分析其复杂性,提出需优化系统支持或外部协助,并为相关法规制定提供参考。

AI 中文摘要

若自动驾驶车辆不再具备执行动态驾驶任务的能力,法规要求其启动最小风险操作,以达成最小风险状态。但关于解决该停滞状态的措施与行动细节仍存在缺失。本文为填补这一空白提供线索,探讨了多种需人类干预操作员理解当前状况并决策的状态:例如,基于健康检查结果,操作员需判断是更宜保持车辆停在路肩,还是将车辆移回车流,或是“低速行驶(limp it)”至另一位置。我们基于近30种原因的列表及后续开发的“场景树(scenario trees)”开展研究,证明了该状况的复杂性及操作员正确处理时面临的巨大困难。我们还探讨了如何增强自动驾驶技术系统,使其能更好地支持操作员,甚至可取消人类干预。这在技术上可行,但相关限制也已显现,因此至少在自动驾驶车辆的起步阶段,外部协助似乎不可或缺。滞留车辆过渡这一非平凡问题需通过进一步法规解决,本文或可为其提供有用参考。

英文摘要

If an automated vehicle is no longer capable of handling the dynamic driving tasks, regulations require that a minimal risk manouvre is initiated aimed at achieving minimum risk condition. Details on measures and actions to resolve this standstill position are missing. This article provides clues for closing this gap and addresses various states in which the human intervention operator must understand the current situation and decide whether it is more acceptable to maintain the stay, e.g. on road-shoulder, or to move the vehicle back into traffic flow or 'limp it' to another position, depending on the outcome of a health check. Our investigations, based on a list of nearly 30 reasons and a subsequent development of 'scenario trees' prove the complexity of the situation and the heavy difficulties faced by the operator to handle in a correct manner. We also discuss how the technical automated driving system can be enhanced so that it stronger supports the operator or allows to even dismiss human intervention. This deems technically feasible but limits became obvious, so that assistance from out side appears indispensable at least for the ramp-up phase of respective automated vehicle. The non-trivial problem of transitioning the 'stranded' vehicle needs to be addressed by further regulation for which this paper may provide useful input.

CommentsThis work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Both authors contributed equally to this article. Corresponding author is Leon Johann Brettin

论文原文

arXiv 摘要页 · PDF 原文 · HTML 原文

↑