EUVIMEDEUVIMED entdecken
Crossref

Quantitative Identification of Strong-Interaction Vehicles in Autonomous Driving

Jinghua Wang, Guangquan Lu, Ailing Yang, Zhao Zhang, Miaomiao Liu, Jinhao Liang

IEEE Transactions on Intelligent Transportation Systems · 2026-08 · 27 (8) · 9820-9833

DOI: 10.1109/tits.2026.3676614 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-08. Verfasst von Jinghua Wang und 5 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Beijing-Tianjin-Hebei Natural Science Cooperation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Understanding vehicle-to-vehicle interactions is critical for safe and efficient autonomous driving in complex traffic scenarios. However, most existing behavior prediction and planning models implicitly account for interactions through soft weighting or metrics based on distance and risk, without a clear or quantitative definition of vehicle interaction. This paper proposes a metric called Vehicle Interaction Level (VIL) to quantify the degree to which a vehicle’s behavior is constrained by another vehicle. By applying a VIL threshold, strong-interaction vehicles are distinguished from weak ones. Then, the Feature Difference Level (FDL) is proposed to analyze feature-level behavioral differences across interaction categories, which is quantified using the Random Forest (RF) and the Gini Index (GI). Based on real-world vehicle trajectory pairs, an optimal VIL threshold of 0.2 is determined by maximizing FDL to identify strong-interaction vehicles, providing a more discriminative and broadly applicable interaction characterization than distance-based and risk-based metrics. Furthermore, the application of this strong-interaction vehicle identification method to trajectory prediction achieves consistently better performance than the baseline across multiple evaluation metrics, demonstrating its practical value for downstream autonomous driving tasks. Owing to its lightweight and model-agnostic formulation, the VIL-based method can be integrated into existing autonomous driving systems operating in highly interactive traffic scenarios.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Beijing-Tianjin-Hebei Natural Science Cooperation Project
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Wang, J., Lu, G., Yang, A., Zhang, Z., Liu, M., & Liang, J. (2026). Quantitative Identification of Strong-Interaction Vehicles in Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems, 27(8), 9820-9833. https://doi.org/10.1109/tits.2026.3676614

Vancouver

Wang J, Lu G, Yang A, Zhang Z, Liu M, Liang J. Quantitative Identification of Strong-Interaction Vehicles in Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems. 2026;27(8):9820-9833. doi:10.1109/tits.2026.3676614

BibTeX
@article{Wang2026,
  author = {Wang, Jinghua and Lu, Guangquan and Yang, Ailing and Zhang, Zhao and Liu, Miaomiao and Liang, Jinhao},
  title = {Quantitative Identification of Strong-Interaction Vehicles in Autonomous Driving},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2026},
  volume = {27},
  number = {8},
  pages = {9820--9833},
  doi = {10.1109/tits.2026.3676614}
}
Kostenlos starten →