search for




 

A statistical analysis of autonomous vehicle accident patterns and vehicle damage
Journal of the Korean Data & Information Science Society 2025;36:59-70
Published online January 31, 2025;  https://doi.org/10.7465/jkdi.2025.36.1.59
© 2025 Korean Data and Information Science Society.

Ki-Yeong Sim1 · In-Gyu Lee2 · Jung-A Yang3 · Kyupil Yeon4

123Department of Data Science, Hoseo University
4Division of Big Data and AI, Hoseo University
Correspondence to: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2020R1F1A1A01073456). This research was supported by ”Regional Innovation Strategy (RIS)” through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (MOE) (2021RIS-004).
1 Graduate student, Department of Data Science, Hoseo University.
2 Graduate student, Department of Data Science, Hoseo University.
3 Graduate student, Department of Data Science, Hoseo University.
4 (Corresponding Author) Professor, Division of Big Data and AI, Hoseo University. 20, Hoseo-ro 79beon-gil, Baebang-eup, Asan-si, Chungnam, 31499, Korea. E-mail: kpyeon1@hoseo.edu
Received October 8, 2024; Revised November 12, 2024; Accepted November 20, 2024.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
As autonomous vehicles (AV) are commercialized, they are expected to grow as a core technology field of the 4th industrial revolution, leading to major changes that bring new experiences to users. However, as the technology advances, the risk of autonomous vehicle accidents is inevitable. Accidents of autonomous vehicles cannot be judged as the fault of the autonomous vehicle, and traffic accidents or fatalities may occur due to unexpected circumstances or inadequate response of the technology. Therefore, this study aims to investigate the effects of accident types and environment on the degree of vehicle damage in autonomous vehicle accidents through mixed effect logistic regression. The data was collected using the autonomous vehicles collision reports provided by the California DMV. We found that autonomous driving mode tends to mitigate the damage of AV in accidents while some factors related on the accident environments such as the darker lighting condition, vehicle-to-vehicle accident, whether there were any injuries, and whether the AV has caused the accident, tend to increase the damage of a AV. We expect this study can help to better understand the causes of AV accidents and provide a guide to the development of autonomous vehicle technology.
Keywords : Autonomous vehicle, autonomous vehicle accident, California DMV, mixed effects logistic regression model