Areas of Improvement for Autonomous Vehicles: A Machine Learning Analysis of Disengagement Reports
This work addresses safety and reliability issues for autonomous vehicles, but it is incremental as it applies standard methods to new data.
The paper analyzed 2023 autonomous vehicle disengagement reports using NLP and k-Means clustering to identify common failure factors, providing insights into areas for improvement in AV technology.
Since 2014, the California Department of Motor Vehicles (CDMV) has compiled information from manufacturers of autonomous vehicles (AVs) regarding factors that lead to the disengagement from autonomous driving mode in these vehicles. These disengagement reports (DRs) contain information detailing whether the AV disengaged from autonomous mode due to technology failure, manual override, or other factors during driving tests. This paper presents a machine learning (ML) based analysis of the information from the 2023 DRs. We use a natural language processing (NLP) approach to extract important information from the description of a disengagement, and use the k-Means clustering algorithm to group report entries together. The cluster frequency is then analyzed, and each cluster is manually categorized based on the factors leading to disengagement. We discuss findings from previous years' DRs, and provide our own analysis to identify areas of improvement for AVs.