Exploring Micro Accidents and Driver Responses in Automated Driving: Insights from Real-world Videos

2025-08-10

AI Summary

This paper addresses the long-overlooked “micro-accidents” in autonomous driving—non-fatal yet safety-critical anomalous driving behaviors (e.g., abrupt deceleration, serpentine trajectories) that serve as early indicators of system fragility. Method: We formally define and empirically analyze this class of safety-critical phenomena using multi-source naturalistic driving video data; apply machine learning to detect anomalous patterns; and conduct crowdsourced experiments to quantify human risk perception and response latency. Contribution/Results: We introduce the first standardized, annotated naturalistic driving video dataset dedicated to micro-accident research. Our analysis identifies key environmental triggers (e.g., edge cases, sensor occlusions) and architectural weaknesses in autonomy systems, while uncovering critical human–machine interaction blind spots in risk awareness and intervention timing. These findings establish a novel empirical paradigm for autonomous vehicle safety assessment, human–machine interface (HMI) optimization, and system robustness enhancement.

Technology Category

• Natural Language Processing: Safety and Robustness
• Computer Vision: Adversarial Attacks & Robustness
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Automated driving in level 3 autonomy has been adopted by multiple companies such as Tesla and BMW, alleviating the burden on drivers while unveiling new complexities. This article focused on the under-explored territory of micro accidents during automated driving, characterized as not fatal but abnormal aberrations such as abrupt deceleration and snake driving. These micro accidents are basic yet pervasive events that might results in more severe accidents. Through collecting a comprehensive dataset of user generated video recording such micro accidents in natural driving scenarios, this article locates key variables pertaining to environments and autonomous agents using machine learning methods. Subsequently, crowdsourcing method provides insights into human risk perceptions and reactions to these micro accidents. This article thus describes features of safety critical scenarios other than crashes and fatal accidents, informing and potentially advancing the design of automated driving systems.

Problem

• Study micro accidents in automated driving scenarios
• Analyze driver responses to abnormal aberrations
• Improve safety design for autonomous vehicles

Innovation

• Analyzing micro accidents using real-world video data
• Applying machine learning to identify key variables
• Studying human reactions via crowdsourcing methods