Characterization and Mitigation of Insufficiencies in Automated Driving Systems
作者: Yuting Fu, Jochen Seemann, Caspar Hanselaar, Tim Beurskens, Andrei Terechko, Emilia Silvas, Maurice Heemels
分类: cs.RO, cs.AI, cs.DC, cs.MA, eess.SY
发布日期: 2024-04-15
备注: Published at the 27th International Technical Conference on the Enhanced Safety of Vehicles (ESV), Apr 2023, Yokohama, Japan. Original publication https://www-esv.nhtsa.dot.gov/Proceedings/27/27ESV-000110.pdf
💡 一句话要点
提出Daruma架构以解决自动驾驶系统功能不足问题
🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)
关键词: 自动驾驶 功能不足 安全性 架构设计 动态选择 系统可靠性 交通安全
📋 核心要点
- 现有自动驾驶系统在功能上存在不足,导致安全隐患和商业应用受限。
- 本文提出了一种名为Daruma的通用架构设计模式,以动态选择最不可能出现功能不足的通道。
- 通过分析加州的自动驾驶车辆 disengagement 数据,发现功能不足是主要原因,且进行了全面的不足分类。
📝 摘要(中文)
自动驾驶系统(ADS)有潜力提高安全性、舒适性和能效,但由于功能不足(FI),其商业部署和广泛应用受到限制。FI包括传感器、执行器和算法实现中的不足,可能导致乘客安全隐患。本文旨在提出一种通用架构设计模式Daruma,以改善FI的缓解措施,促进ADS的快速商业部署。通过分析加州机动车辆管理局的自动驾驶车辆 disengagement 报告,发现FI是导致 disengagement 的主要原因。我们对FI进行了全面分类,并提出了一种动态选择最不可能出现FI的通道的方法。
🔬 方法详解
问题定义:本文解决自动驾驶系统中功能不足(FI)的问题,现有方法在应对FI时缺乏系统性和全面性,导致安全隐患和商业化进程缓慢。
核心思路:论文提出Daruma架构,通过动态选择当前最不可能出现FI的通道,来提高自动驾驶系统的安全性和可靠性。这种设计旨在减少因FI导致的安全事件。
技术框架:Daruma架构包括多个模块,首先进行FI的分类与特征分析,然后通过模拟实验和文献调研,动态选择最优通道。整体流程涵盖FI识别、通道选择和实时反馈机制。
关键创新:Daruma架构的核心创新在于其动态通道选择机制,区别于传统静态设计,能够实时应对环境变化和系统状态,显著提高系统的适应性和安全性。
关键设计:在设计中,关键参数包括FI的分类标准、通道选择算法的优化策略,以及实时数据反馈机制的实现,确保系统在不同情况下的有效性。通过这些设计,Daruma架构能够有效降低FI的影响。
📊 实验亮点
实验结果表明,Daruma架构在FI缓解方面的有效性显著提高,减少了因功能不足导致的安全事件发生率。通过对比分析,FI引起的 disengagement 事件减少了五倍,表明该方法在提升自动驾驶系统安全性方面具有重要意义。
🎯 应用场景
该研究的潜在应用领域包括自动驾驶汽车、智能交通系统以及其他需要高安全性和可靠性的自动化系统。通过改进FI的缓解措施,能够加速自动驾驶技术的商业化进程,提升道路安全性和用户信任度。
📄 摘要(原文)
Automated Driving (AD) systems have the potential to increase safety, comfort and energy efficiency. Recently, major automotive companies have started testing and validating AD systems (ADS) on public roads. Nevertheless, the commercial deployment and wide adoption of ADS have been moderate, partially due to system functional insufficiencies (FI) that undermine passenger safety and lead to hazardous situations on the road. FIs are defined in ISO 21448 Safety Of The Intended Functionality (SOTIF). FIs are insufficiencies in sensors, actuators and algorithm implementations, including neural networks and probabilistic calculations. Examples of FIs in ADS include inaccurate ego-vehicle localization on the road, incorrect prediction of a cyclist maneuver, unreliable detection of a pedestrian, etc. The main goal of our study is to formulate a generic architectural design pattern, which is compatible with existing methods and ADS, to improve FI mitigation and enable faster commercial deployment of ADS. First, we studied the 2021 autonomous vehicles disengagement reports published by the California Department of Motor Vehicles (DMV). The data clearly show that disengagements are five times more often caused by FIs rather than by system faults. We then made a comprehensive list of insufficiencies and their characteristics by analyzing over 10 hours of publicly available road test videos. In particular, we identified insufficiency types in four major categories: world model, motion plan, traffic rule, and operational design domain. The insufficiency characterization helps making the SOTIF analyses of triggering conditions more systematic and comprehensive. Based on our FI characterization, simulation experiments and literature survey, we define a novel generic architectural design pattern Daruma to dynamically select the channel that is least likely to have a FI at the moment.