一句话：构建 sUAS 领域级安全分析资产，系统识别 human-on-the-loop 交互点、危害因素与缓解措施。
随着 AI 技术发展，自主系统从 human-in-the-loop 转向 human-on-the-loop，更多责任由人转给系统，导致人机交互边界出现新型错误。传统安全分析多关注系统级危害，较少处理用户相关或用户诱发的危害。本文为 sUAS 应用构建领域级安全分析资产，并给出从系统危害中显式、系统地识别 Human Interaction Points、Hazard Factors 与 Mitigations 的流程。评估分两部分：一是检验近期 sUAS 事件在本文危害树中的覆盖程度；二是邀请六名领域专家使用危害树为 sUAS 使用场景识别和记录危害。结果表明，危害树对多种 sUAS 应用场景提供有效覆盖，并能激发安全思考，帮助用户识别并潜在缓解人机交互危害。
With the rise of new AI technologies, autonomous systems are moving towards a paradigm in which increasing levels of responsibility are shifted from the human to the system, creating a transition from human-in-the-loop systems to human-on-the-loop (HoTL) systems. This has a significant impact on the safety analysis of such systems, as new types of errors occurring at the boundaries of human-machine interactions need to be taken into consideration. Traditional safety analysis typically focuses on system-level hazards with little focus on user-related or user-induced hazards that can cause critical system failures. To address this issue, we construct domain-level safety analysis assets for sUAS (small unmanned aerial systems) applications and describe the process we followed to explicitly, and systematically identify Human Interaction Points (HiPs), Hazard Factors and Mitigations from system hazards. We evaluate our approach by first investigating the extent to which recent sUAS incidents are covered by our hazard trees, and second by performing a study with six domain experts using our hazard trees to identify and document hazards for sUAS usage scenarios. Our study showed that our hazard trees provided effective coverage for a wide variety of sUAS application scenarios and were useful for stimulating safety thinking and helping users to identify and potentially mitigate human-interaction hazards.
@inproceedings{paperbot6441,
title = {Hazard analysis for human-on-the-loop interactions in sUAS systems},
author = {Michael Vierhauser and Md Nafee Al Islam and Ankit Agrawal and Jane Cleland-Huang and James Mason},
booktitle = {FSE},
year = {2021},
doi = {10.1145/3468264.3468534}
}