@ARTICLE{Chen_Hao_GTC-DAN:_Early,
 author={Chen, Hao and Wu, Xuncheng and Zhang, Ruoping and Guo, Wenfeng and Chen, Yang and Xu, Jiejie and Zhang, Weiwei and Yu, Wangpengfei},
 pages={e152610},
 journal={Bulletin of the Polish Academy of Sciences Technical Sciences},
 howpublished={online},
 year={Early Access},
 abstract={Autonomous driving is currently a hot topic in automotive engineering. Accurately predicting the future trajectory of self-driving cars can significantly reduce the occurrence of traffic accidents. However, predicting the future trajectories of vehicles is a challenging task since it is influenced by the interaction behaviors of neighboring vehicles. This paper proposes a framework that allows for parameter sharing and cross-layer independence, based on a dynamic graph convolutional spatiotemporal network, to study the interactions between vehicles and the temporal dynamics in historical trajectories. By extracting dynamic adjacency matrices from different vehicle interaction features, the model can describe dynamic spatiotemporal relationships, enabling it to handle changes in traffic scenarios. Finally, the proposed model was experimentally compared with existing mainstream trajectory prediction methods using the NGSIM dataset. The results demonstrated that our trajectory prediction model achieved excellent performance in terms of model parameters and prediction accuracy. Compared to the four mainstream models, our model improved accuracy by 35.73%. In addition, we also analyze the relationship between model complexity and efficiency.},
 title={GTC-DAN: A Graph-Temporal Convolutional Model with Dynamic Adjacency for Vehicle Trajectory Prediction},
 type={Article},
 URL={http://czasopisma.pan.pl/Content/133342/PDF-MASTER/BPASTS-04639-EA.pdf},
 doi={10.24425/bpasts.2024.152610},
 keywords={autonomous driving, trajectory prediction, spatiotemporal modeling, dynamic interactions},
}