EUVIMEDEUVIMED entdecken
Crossref

High-Risk Trajectories Generation for Safety Testing of Autonomous Vehicles Based on In-Depth Crash Data

Guoqing Zhang, Helai Huang, Rui Zhou, Shiqi Li, Jiang Bian

IEEE Transactions on Intelligent Transportation Systems · 2025-08 · 26 (8) · 11619-11630

DOI: 10.1109/tits.2025.3576236 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2025-08. Verfasst von Guoqing Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: National Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Scenario-based testing offers a robust method for evaluating the safety of Autonomous Vehicles (AVs). In this study, we introduce LSTM-CGAN to generate scenarios for assessing AV safety performance. First, we extract static, environmental, and dynamic elements from the China In-depth Mobility Safety Study-Traffic Accident (CIMSS-TA) dataset and reconstruct 630 real-world crashes to obtain pre-crash trajectories of the ego and objective vehicles. The proposed model then synthesizes samples by utilizing high-risk trajectories extracted from pre-crash trajectories, resulting in the generation of 6,300 trajectories, ten times the original dataset. The synthesized samples closely resemble real-world trajectories while enhancing diversity, with 61.9% of road segment and 55.5% of intersection trajectories scenes being classified as challenging. By integrating static and dynamic elements with the synthesized trajectories, critical scenarios for counterfactual simulations are generated. Finally, the Baidu Apollo, a well-known Autonomous Driving System (ADS), is tested in simulations using both generated and original scenarios. It is evidenced that the proposed method is effective in generating more safety-critical scenarios and that static and environmental factors have different impacts on AV performance. This study provides valuable insights into the unknown safety-critical scenario construction of AV safety testing, thereby facilitating the commercialization of AVs.

Förderung

  • National Research and Development Program of China

Zitieren

APA

Zhang, G., Huang, H., Zhou, R., Li, S., & Bian, J. (2025). High-Risk Trajectories Generation for Safety Testing of Autonomous Vehicles Based on In-Depth Crash Data. IEEE Transactions on Intelligent Transportation Systems, 26(8), 11619-11630. https://doi.org/10.1109/tits.2025.3576236

Vancouver

Zhang G, Huang H, Zhou R, Li S, Bian J. High-Risk Trajectories Generation for Safety Testing of Autonomous Vehicles Based on In-Depth Crash Data. IEEE Transactions on Intelligent Transportation Systems. 2025;26(8):11619-11630. doi:10.1109/tits.2025.3576236

BibTeX
@article{Zhang2025,
  author = {Zhang, Guoqing and Huang, Helai and Zhou, Rui and Li, Shiqi and Bian, Jiang},
  title = {High-Risk Trajectories Generation for Safety Testing of Autonomous Vehicles Based on In-Depth Crash Data},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2025},
  volume = {26},
  number = {8},
  pages = {11619--11630},
  doi = {10.1109/tits.2025.3576236}
}
Kostenlos starten →