[Paper Review] Crash Themes in Automated Vehicles: A Topic Modeling Analysis of the California Department of Motor Vehicles Automated Vehicle Crash Database

Hananeh Alambeigi, Anthony D. McDonald+1 more|arXiv (Cornell University)|Jan 29, 2020

Computational and Text Analysis Methods27 references36 citations

TL;DR

The paper uses probabilistic topic modeling on California DMV automated vehicle crash narratives to identify five crash themes and highlight safety gaps in driver-automation interactions.

ABSTRACT

Automated vehicle technology promises to reduce the societal impact of traffic crashes. Early investigations of this technology suggest that significant safety issues remain during control transfers between the automation and human drivers and automation interactions with the transportation system. In order to address these issues, it is critical to understand both the behavior of human drivers during these events and the environments where they occur. This article analyzes automated vehicle crash narratives from the California Department of Motor Vehicles automated vehicle crash database to identify safety concerns and gaps between crash types and current areas of focus in the current research. The database was analyzed using probabilistic topic modeling of open-ended crash narratives. Topic modeling analysis identified five themes in the database: driver-initiated transition crashes, sideswipe crashes during left-side overtakes, and rear-end collisions while the vehicle was stopped at an intersection, in a turn lane, and when the crash involved oncoming traffic. Many crashes represented by the driver-initiated transitions topic were also associated with the side-swipe collisions. A substantial portion of the side-swipe collisions also involved motorcycles. These findings highlight previously raised safety concerns with transitions of control and interactions between vehicles in automated mode and the transportation social network. In response to these findings, future empirical work should focus on driver-initiated transitions, overtakes, silent failures, complex traffic situations, and adverse driving environments. Beyond this future work, the topic modeling analysis method may be used as a tool to monitor emergent safety issues.

Motivation & Objective

• Motivate understanding of how automated vehicle crashes occur in real-world contexts.
• Identify common crash themes from DMV AV crash narratives.
• Assess how crash types align with current research focus in AV safety.
• Suggest directions for empirical studies and monitoring approaches for emergent safety issues.

Proposed method

• Apply probabilistic topic modeling to open-ended AV crash narratives from the California DMV database.
• Identify coherent themes (topics) representing safety concerns in automated vehicle crashes.
• Analyze associations between topics (e.g., driver-initiated transitions and side-swipe events).
• Highlight the role of complex traffic interactions and adverse environments in crashes.
• Propose the topic modeling approach as a monitoring tool for emergent AV safety issues.

Experimental results

Research questions

• RQ1 What crash themes are most prevalent in the California DMV automated vehicle crash database?
• RQ2 How do driver-initiated transitions relate to other crash types such as side-swipes or rear-end collisions?
• RQ3 What safety concerns emerge in automated-vehicle crashes that are not fully addressed by current research?

Key findings

• Five themes were identified in the DMV AV crash narratives.
• Driver-initiated transition crashes often coincide with side-swipe crashes.
• Many side-swipe crashes involved motorcycles.
• Rear-end collisions occurred in scenarios such as stopped at an intersection, in a turn lane, or with oncoming traffic when in automated mode.
• Findings highlight safety concerns with transitions of control and interactions in automated mode, suggesting focus areas for future work.