一句话：构建 Defects4DeepNav，提供 100+ 个深度学习机器人导航真实故障、传感器数据与分析工具。
故障目录是推动程序分析技术演进与评估的关键基础设施，但面向新兴机器人系统仍属空白，构建成本高且需真实物理系统与多样故障。本文提出 Defects4DeepNav：从一台在真实世界运行的商用开源机器人中收集 100 余个故障，这些故障由学习组件导航并来自 30 个导航组件且持续增长；目录提供失败与非失败行为的完整传感器数据、数据分析工具，并展示潜在用例与扩展方向。
Failure catalogs have proven to be key instruments driving the evolution and assessment of program analysis techniques. However, such infrastructure does not support the development of techniques for the large number of emerging robotic systems. Developing such a catalog is costly and challenging because it requires access to the full physical system and the presentation of a diverse set of failures. We have started to tackle this challenge, building Defects4DeepNav, a growing catalog of over 100 failures from a commercial open source robot operating in the real world navigated by a learned component, with a diverse set of failures arising from 30 navigation components and growing. This paper introduces Defects4DeepNav, including a diverse set of failures, full sensor data for failing and non-failing behavior, tools to analyze the data, and illustrations of its potential use cases and extensions.
@inproceedings{paperbot8948,
title = {Steering the Future: A Catalog of Failures in Deep Learning-Enabled Robotic Navigation Systems},
author = {Meriel von Stein and Yili Bai and Trey Woodlief and Sebastian Elbaum},
booktitle = {FSE},
year = {2025},
doi = {10.1145/3696630.3728604}
}