EUVIMEDEUVIMED entdecken
Crossref

Toward Human-Like Prediction: Vehicle Trajectory Prediction via Velocity-Aware Complementary Interaction Transformer

Xunhao Li, Jian Zhang, Yu Qian, Yongfu Li

IEEE Transactions on Intelligent Transportation Systems · 2025-10 · 26 (10) · 14665-14679

DOI: 10.1109/tits.2025.3576729 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2025-10. Verfasst von Xunhao Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Zhejiang Provincial Department of Transportation, Jiangsu Provincial Transportation Technology and Achievement Transformation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vehicle trajectory prediction (VTP) poses unique spatial-temporal modeling challenges, as a human-like prediction requires considering fine-grained interactions. Prior models have often used various attention mechanisms to extract key spatial-temporal interactions from the foreground, thus missing background information processing. However, this may result in the model’s insufficient generalization ability in a specific modality. Here this paper presents VCIFormer, a velocity-aware complementary interaction Transformer designed to enhance vehicle trajectory prediction by capturing complex spatial-temporal interactions between foreground and background with context awareness. VCIFormer combines inverse attention with traditional spatial-temporal attention as a complementary mechanism, applying bidirectional optimization to capture foreground and background attention flows. An adaptive visual mask is also developed to align attention allocation with human visual patterns at varying velocities. It enables the model to prioritize critical regions analogous to human driving behavior. Moreover, a context-aware encoder, consisting of a surround-aware module and a motion-enhancement module, is incorporated to provide additional interaction cues and spatial information. VCIFormer is evaluated on six real-world datasets (NGSIM, HighD, RounD, ExiD, Argoverse, and nuScenes) and attains state-of-the-art performance in critical metrics. For example, in comparison to baseline models, there are significant improvements in ADE and FDE by 2.84-18.18% and 9.88-13.33% on the NGSIM, HighD, RounD, and ExiD datasets, respectively. In sum, compared with previous architectures, VCIFormer presents a more effective combination of spatial-temporal interaction layers and context awareness for VTP.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Zhejiang Provincial Department of Transportation, Jiangsu Provincial Transportation Technology and Achievement Transformation Project
  • Natural Science Foundation of Tibet Autonomous Region of China
  • Natural Science Foundation of Chongqing Municipality
  • Talent Program of Chongqing
  • Science and Technology Research Program of Chongqing Municipal Education Commission

Zitieren

APA

Li, X., Zhang, J., Qian, Y., & Li, Y. (2025). Toward Human-Like Prediction: Vehicle Trajectory Prediction via Velocity-Aware Complementary Interaction Transformer. IEEE Transactions on Intelligent Transportation Systems, 26(10), 14665-14679. https://doi.org/10.1109/tits.2025.3576729

Vancouver

Li X, Zhang J, Qian Y, Li Y. Toward Human-Like Prediction: Vehicle Trajectory Prediction via Velocity-Aware Complementary Interaction Transformer. IEEE Transactions on Intelligent Transportation Systems. 2025;26(10):14665-14679. doi:10.1109/tits.2025.3576729

BibTeX
@article{Li2025,
  author = {Li, Xunhao and Zhang, Jian and Qian, Yu and Li, Yongfu},
  title = {Toward Human-Like Prediction: Vehicle Trajectory Prediction via Velocity-Aware Complementary Interaction Transformer},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2025},
  volume = {26},
  number = {10},
  pages = {14665--14679},
  doi = {10.1109/tits.2025.3576729}
}
Kostenlos starten →