Analyzing Pedestrian–Automated Vehicle Crash Dynamics: A Comparative Study of Autonomous and Conventional Precrash Mode

Pedestrian safety is a critical concern in urban environments, particularly with the increasing presence of automated vehicles (AVs) on the roads. Because of the unpredictable movement of pedestrians, a significant challenge lies in the limited understanding of factors contributing to pedestrian–AV collisions. This study addresses this gap by analyzing pedestrian crashes involving AVs using association rules mining (ARM). Data, including crash reports from the California Department of Motor Vehicles, comprised 46 pedestrian crashes involving AVs, categorized by precrash mode: autonomous mode (24 crashes) and conventional mode (22 crashes). The ARM algorithm was employed to uncover significant relationships and patterns in the crash data. A total of 67 association rules were generated across three distinct scenarios—intersections, within 150 ft of intersections, and midblock locations—revealing key associations between factors such as time of day, location, vehicle and pedestrian behavior, and environmental conditions. The study’s findings offer valuable insights into pedestrian safety in the context of precrash modes of AVs and provide important guidance for developing targeted safety measures and policies to reduce pedestrian–AV collisions.