Evaluating Autonomous Vehicle Safety Performance Through Analysis of Pre-Crash Trajectories of Powered Two-Wheelers

To ensure the safety of Autonomous Vehicles (AVs), thorough testing across virtual simulation environments, closed facilities, and public roads is essential. Scenario-based testing stands out as a crucial method for evaluating AVs, with a key focus on constructing appropriate testing scenarios. Given the vulnerability of Powered Two-Wheelers (PTWs) riders, it is essential to investigate typical and representative car-to-PTWs crash scenarios and validate AV system safety performance in such situations. This study introduces a new method for generating high-risk scenarios by extracting typical testing scenarios from real-world crashes, thereby enhancing the realism of testing conditions. To evaluate the safety performance of AV systems, a crash-based testing approach is proposed. First, 222 car-to-PTWs crashes were extracted from the China In-depth Mobility Safety Study-Traffic Accident (CIMSS-TA) database and the pre-crash trajectories of crash-involved parties were accurately obtained by reconstructing the crashes case-by-case. Second, utilizing the k-medoids algorithm based on the Hausdorff distance to cluster these trajectories, six typical pre-crash trajectory clusters were extracted. Third, six sets of high-risk scenarios were generated using parameter discretization and combination testing based on the cluster centers. Finally, we conducted safety testing on the black-box automated driving system, Baidu Apollo, using the SVL Simulator virtual simulation platform. We evaluated its performance by subjecting it to the six sets of high-risk scenarios generated in this study. The experimental results demonstrate that Apollo can operate safely in most high-risk scenarios, indicating that automated driving systems can handle crashes that some human drivers cannot avoid, thereby improve traffic safety.

I. Introduction

Autonomous vehicles (AVs) have the potential to revolutionize transportation by significantly improving traffic safety. However, before AVs can be widely adopted, their safety must be thoroughly tested and proven [1]. Research has indicated that conducting over 10 billion miles of public road testing is necessary to provide solid evidence that AVs are indeed safer than human drivers [2]. Moreover, public road scenarios often lack the complexity necessary to effectively assess the driving capability of AVs in high-risk situations. Consequently, virtual simulation testing has emerged as a popular and effective alternative that enables the cost-effective and efficient evaluation of AVs performance in high-risk scenarios [3].