EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vehicle Multimodal Trajectory Prediction Integrating Kinematics and Dynamic Interaction Features

Feiyan Li, Jiahao Li, Hongfei Jia, Xinxin Zhang, Tianci Gao, Zetong Qin, Hangtian Du

Mathematics · 04.08.2026 · 14 (15) · 2796

DOI: 10.3390/math14152796 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 04.08.2026. Verfasst von Feiyan Li und 6 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Development Plan Project of Jilin Province, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate vehicle trajectory prediction is essential for autonomous driving safety. However, existing data-driven models often ignore kinematic constraints, causing lateral jitter and trajectory distortion, while purely kinematics-based models lack flexibility in complex interactions. To address this, this paper presents a multimodal trajectory prediction method combining kinematics with dynamic interaction features. Operating in the Frenet coordinate system, the proposed model extracts historical features via a Bidirectional Gated Recurrent Unit (Bi-GRU) and utilizes an Adaptive Social Gating Network (ASGN) with multi-head attention to filter irrelevant interaction noise. This paper introduces a Stochastic Gating Decoder for multimodal latent variable sampling, adaptively fusing kinematics and data-driven paths to capture driver intention uncertainty while maintaining kinematic consistency. The model is trained using a composite loss function (Focal Loss and Best-of-K) to mitigate dataset long-tail distribution and trajectory divergence. Experiments on the HighD dataset show the proposed model achieves a minADE of 0.425 m and a minFDE of 0.955 m, outperforming baselines and reducing Lat-ADE by 53.9% compared to Social-GAN. These results confirm the model generates smoother, kinematically interpretable trajectories with higher accuracy in long-tail lane-changing scenarios.

Förderung

  • Science and Technology Development Plan Project of Jilin Province, China

Zitieren

APA

Li, F., Li, J., Jia, H., Zhang, X., Gao, T., Qin, Z., & Du, H. (2026). Vehicle Multimodal Trajectory Prediction Integrating Kinematics and Dynamic Interaction Features. Mathematics, 14(15), 2796. https://doi.org/10.3390/math14152796

Vancouver

Li F, Li J, Jia H, Zhang X, Gao T, Qin Z, et al. Vehicle Multimodal Trajectory Prediction Integrating Kinematics and Dynamic Interaction Features. Mathematics. 2026;14(15):2796. doi:10.3390/math14152796

BibTeX
@article{Li2026,
  author = {Li, Feiyan and Li, Jiahao and Jia, Hongfei and Zhang, Xinxin and Gao, Tianci and Qin, Zetong and Du, Hangtian},
  title = {Vehicle Multimodal Trajectory Prediction Integrating Kinematics and Dynamic Interaction Features},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {15},
  pages = {2796},
  doi = {10.3390/math14152796}
}
Kostenlos starten →