软件部署
风险分析(工程)
班级(哲学)
领域(数学分析)
运输工程
安全标准
可能性
车辆安全
系统安全
安全案例
计算机科学
功能安全
工程类
计算机安全
业务
可靠性工程
汽车工程
软件工程
数学分析
人工智能
逻辑回归
机器学习
数学
作者
Andrew Smart,Chess Stetson,Kiran Jesudesan
出处
期刊:SAE International Journal of Advances and Current Practices in Mobility
日期:2021-06-16
卷期号:4 (1): 270-277
被引量:2
摘要
<div class="section abstract"><div class="htmlview paragraph">We are in the midst of a vehicle safety revolution. Current vehicle safety standards, best practices, and approaches are not adequate to ensure the safety of an Automated Vehicle (AV), the motoring public, and vulnerable road users. Continued application of these nascent technologies prompts the question: How safe is safe enough and how do we know that these systems can handle inherent risks of a given deployment area? Current practices are very focused on vehicle safety elements. In fact, there is currently only one published safety standard, specifically for AVs [<span class="xref">1</span>], though there are instances where some vehicle system safety standards are being adapted for AV application and some safety standards from other industries (e.g. aerospace and nuclear) are being considered. Specific guidelines for AV safety metrics and AV safety performance are currently in the development stages and once published will require time to be fully understood, thresholds defined, and data collected and accepted by the AV community. A holistic approach to safety that considers all aspects of a safe AV deployment beyond increasing levels of vehicle technology is crucial. Included in this holistic approach, as a foundational element, is a fundamentally new way of assessing and quantifying risks within the Operational Design Domain (ODD). This is produced by breaking down the risk of a given ODD as a sum over the risk of component scenarios which make up the ODD. This means ODDs are fully specified and not defined by subjective assumptions. With no single standard, best practice, or guideline that covers AV safety in a holistic manner, an assessment process including a fully quantified ODD is seen as the most effective way to cover all aspects of safety, including the environment, management practices, and the vehicles.</div></div>
科研通智能强力驱动
Strongly Powered by AbleSci AI