@article{Sheng2024, 
author = {Zihao Sheng and Zilin Huang and Sikai Chen},
title = {Kinematics-aware multigraph attention network with residual learning for heterogeneous trajectory prediction},
year = {2024},
journal = {Journal of Intelligent and Connected Vehicles},
volume = {7},
number = {2},
pages = {138-150},
keywords = {trajectory prediction, multigraph attention, physics-informed deep learning, residual learning, automated driving.},
url = {https://www.sciopen.com/article/10.26599/JICV.2023.9210036},
doi = {10.26599/JICV.2023.9210036},
abstract = {Trajectory prediction for heterogeneous traffic agents plays a crucial role in ensuring the safety and efficiency of automated driving in highly interactive traffic environments. Numerous studies in this area have focused on physics-based approaches because they can clearly interpret the dynamic evolution of trajectories. However, physics-based methods often suffer from limited accuracy. Recent learning-based methods have demonstrated better performance, but they cannot be fully trusted due to the insufficient incorporation of physical constraints. To mitigate the limitations of purely physics-based and learning-based approaches, this study proposes a kinematics-aware multigraph attention network (KA-MGAT) that incorporates physics models into a deep learning framework to improve the learning process of neural networks. Besides, we propose a residual prediction module to further refine the trajectory predictions and address the limitations arising from simplified assumptions in kinematic models. We evaluate our proposed model through experiments on two challenging trajectory datasets, namely, ApolloScape and NGSIM. Our findings from the experiments demonstrate that our model outperforms various kinematics-agnostic models with respect to prediction accuracy and learning efficiency.}
}