Vehicle Cross-modal Trajectory Prediction Model Based on Driving Style Hypergraphs

Authors

• Guozhu Cheng, School of Civil Engineering and Transportation, Northeast Forestry University, Harbin 150040, China
• Changyuan Wang, School of Civil Engineering and Transportation, Northeast Forestry University, Harbin 150040, China
• Wenzhi Wang, School of Civil Engineering and Transportation, Northeast Forestry University, Harbin 150040, China
• Yifan Zhang, School of Civil Engineering and Transportation, Northeast Forestry University, Harbin 150040, China
• Tianjun Feng, School of Transportation Science and Engineering, Jilin University of Architecture, Changchun 130118, China

Abstract

Abstract: To address the shortcomings of existing motorway vehicle trajectory prediction methods which overlook differences in driving styles and the future interactions between trajectories of different modes. This paper proposes a cross-modal trajectory prediction model based on a dual-hypergraph Transformer for driving styles. The method first quantifies driving styles by extracting vehicle kinematic features and calculates a similarity matrix between vehicles; it then constructs a dual-hypergraph Transformer, using a homogeneous hypergraph to model the group interactions of vehicles with similar driving styles, and a heterogeneous hypergraph to capture the interaction relationships between spatially neighbouring but stylistically dissimilar vehicles; Finally, a style-aware cross-modal interaction module is designed, utilising a multi-head attention mechanism to dynamically adjust the response weights of different driving styles to the interaction scenario, thereby enabling multi-modal trajectory generation. Experiments on the HighD and ExiD datasets demonstrate that this method achieves RMSE values of 1.69 m and 1.66 m, respectively, over a 5-second prediction horizon. Compared with state-of-the-art graph neural network models such as IPF-GCN, it achieves superior performance in terms of average RMSE. On the ExiD dataset, the average prediction accuracy improved by 30.6% and 12.8% compared to the MMnTP and POVL models, respectively. The experimental results demonstrate that the proposed model can effectively capture the interaction relationships within a group of vehicles and significantly enhance the accuracy and stability of vehicle trajectory prediction.

Recommended Citation

Cheng, Guozhu; Wang, Changyuan; Wang, Wenzhi; Zhang, Yifan; and Feng, Tianjun (2026) "Vehicle Cross-modal Trajectory Prediction Model Based on Driving Style Hypergraphs," Journal of System Simulation: Vol. 38: Iss. 9, Article 4.
DOI: 10.16182/j.issn1004731x.joss.26-0013
Available at: https://dc-china-simulation.researchcommons.org/journal/vol38/iss9/4

First Page

2486

Last Page

2501

CLC

TP391.9

Recommended Citation

Cheng Guozhu, Wang Changyuan, Wang Wenzhi, et al. Vehicle Cross-modal Trajectory Prediction Model Based on Driving Style Hypergraphs[J]. Journal of System Simulation, 2026, 38(9): 2486-2501.

DOI

10.16182/j.issn1004731x.joss.26-0013