Kinematics-aware multigraph attention network with residual learning for heterogeneous trajectory prediction  

作　　者：Zihao Sheng Zilin Huang Sikai Chen 

机构地区：[1]Department of Civil and Environmental Engineering,University of Wisconsin–Madison,Madison,WI 53706,USA

出　　处：《Journal of Intelligent and Connected Vehicles》2024年第2期138-150,共13页智能网联汽车（英文）

基　　金：the University of Wisconsin-Madison’s Center for Connected and Automated Transportation(CCAT),a part of the larger CCAT consortium,a USDOT Region 5 University Transportation Center funded by the U.S.Department of Transportation,Award#69A3552348305.

摘　　要：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 physicsbased 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(KAMGAT)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.

关 键 词：trajectory prediction physics-informed deep learning multigraph attention residual learning automated driving 

分 类 号：U495[交通运输工程—交通运输规划与管理]