Investigating Collision Patterns to Support Autonomous Driving Safety

Lee, Carmen Kar Hang, Leung, Ka Ho ORCID: 0000-0003-2058-0287, Tse, Ying Kei and Tsao, Yu-Chung (2023) Investigating Collision Patterns to Support Autonomous Driving Safety Enterprise Information Systems, 18 (2). 2243460-. ISSN 1751-7575, 1751-7583

Text Author Accepted Manuscrupt_EIS.pdf - Author Accepted Manuscript Available under License Creative Commons Attribution Non-commercial. Download (611kB) | Preview

Abstract

There is a debate on the importance of autonomous vehicles (AVs) and the methods for ensuring AV safety. This paper analyses collision reports to determine the association between risk factors and the level of damage to an AV due to collisions. Association rule mining was used to develop methodologies that can advance result interpretability, which is crucial in the transportation field. Twenty-one rules were discovered to reveal the factors that co-occur with AV damage. This study demonstrates that collision data, when analysed using appropriate machine learning algorithms, can generate useful insights that complement current policies to enhance AV safety.

Item Type:	Article
Uncontrolled Keywords:	Autonomous driving, autonomous vehicle collision, traffic accident analysis, machine learning, association rule mining
Divisions:	Faculty of Humanities & Social Sciences > School of Management
Depositing User:	Symplectic Admin
Date Deposited:	04 Aug 2023 10:46
Last Modified:	28 Feb 2026 23:50
DOI:	10.1080/17517575.2023.2243460
Related Websites:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3172019
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.