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~~
arXiv 2511.18092cs.SE
收藏

事件链分析用于自动驾驶和ADAS系统:确保安全并满足监管时间要求

Event-Chain Analysis for Automated Driving and ADAS Systems: Ensuring Safety and Meeting Regulatory Timing Requirements

Daimler Truck AG(戴姆勒卡车集团);INCHRON AG(INCHRON公司)

Sebastian Dingler, Philip Rehkop, Florian Mayer, Ralf Muenzenberger

AI总结:

本文提出基于事件链建模的白盒方法,用于解决自动驾驶和ADAS系统的时间约束问题,提升合规性与安全性。

摘要:

自动驾驶系统(ADS),包括高级驾驶辅助系统(ADAS),不仅要满足高功能期望,还必须满足国际法规和标准规定的严格时间限制。监管框架如联合国法规、NCAP标准、ISO规范和NHTSA指南对系统响应时间施加严格限制,以确保安全的车辆操作。本文提出了一种基于事件链建模的结构化、白盒方法,以解决这些时间挑战。与黑盒方法不同,事件链分析提供了对每个功能组件(从感知和规划到执行和人机交互)时间行为的透明洞察。这种视角也与多项法规一致,这些法规要求认证文件提供证据,证明所选系统架构适合确保符合规定的性能要求。我们的方法使能够在架构层面推导、建模和验证端到端的时间限制,并通过模拟促进早期验证。通过详细案例研究,我们展示了这种以事件链为中心的方法如何增强合规性、优化系统设计,并支持基于模型的安全分析技术,结果表明能够早期识别合规问题、系统参数优化以及通过概率分析生成定量证据。

英文摘要:

Automated Driving Systems (ADS), including Advanced Driver Assistance Systems (ADAS), must fulfill not only high functional expectations but also stringent timing constraints mandated by international regulations and standards. Regulatory frameworks such as UN regulations, NCAP standards, ISO norms, and NHTSA guidelines impose strict bounds on system reaction times to ensure safe vehicle operation. This paper presents a structured, White-Box methodology based on Event-Chain Modeling to address these timing challenges. Unlike Black-Box approaches, Event-Chain Analysis offers transparent insights into the timing behavior of each functional component - from perception and planning to actuation and human interaction. This perspective is also aligned with multiple regulations, which require that homologation dossiers provide evidence that the chosen system architecture is suitable to ensure compliance with the specified requirements. Our methodology enables the derivation, modeling, and validation of end-to-end timing constraints at the architectural level and facilitates early verification through simulation. Through a detailed case study, we demonstrate how this Event-Chain-centric approach enhances regulatory compliance, optimizes system design, and supports model-based safety analysis techniques, with results showing early identification of compliance issues, systematic parameter optimization, and quantitative evidence generation through probabilistic analysis.

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。

↑