基于图注意力机制的无地图场景轨迹预测方法  

Graph Attention Mechanism-based Method for Trajectory Prediction in Map-Free Scenes

作　　者：刘建敏 林晖[1,2] 汪晓丁 LIU Jianmin;LIN Hui;WANG Xiaoding(College of Computer and Cyber Security,Fujian Normal University,Fuzhou 350117,Fujian,China;Engineering Research Center of Cyber Security and Education Informatization of Fujian Province University,Fuzhou 350117,Fujian,China)

机构地区：[1]福建师范大学计算机与网络空间安全学院,福建福州350117 [2]网络安全与教育信息化福建省高校工程研究中心,福建福州350117

出　　处：《计算机工程》2024年第7期144-153,共10页Computer Engineering

基　　金：国家自然科学基金(61702103,U1905211);福建省自然科学基金(2020J01167,2020J01169)。

摘　　要：现有的轨迹预测工作大多依赖于高精地图,但高精地图的采集耗时长、成本高、处理复杂,难以快速适应智能交通的大面积普及。为解决无地图场景下车辆轨迹预测问题,提出一种基于多模态数据时空特征的轨迹预测方法。构建多个历史轨迹时空交互图,交叉使用时间和空间注意力并进行深度融合,以建模道路上车辆之间的时空关联性。在此基础上,利用残差网络进行多目标多模态轨迹生成。在真实数据集Argoverse 2上进行模型的训练和测试,实验结果表明,相较于CRAT-Pred方法,该模型在单模态预测方面最小平均位移误差、最小最终位移误差和未命中率指标分别提升了3.86%、3.89%、0.48%,在多模态预测方面各项指标分别提升了0.78%、0.96%、0.42%。该方法能够有效地捕捉车辆移动轨迹的时间和空间特征,并可在自动驾驶等相关领域得到有效应用。Existing trajectory prediction methods rely heavily on high-definition maps,which are time-consuming,costly,and complex to acquire.This makes it difficult for them to quickly adapt to the widespread adoption of intelligent transportation.To address the problem of vehicle trajectory prediction in map-free scenes,a trajectory prediction method based on spatio-temporal features of multi-modal data is proposed in this paper.Multiple spatiotemporal interaction graphs are constructed from the history of the trajectory,temporal and spatial attention are cross-utilized and deeply fused to model the spatio-temporal correlations between vehicles on the road.Finally,a residual network is used for a multi-objective and multi-modal trajectory generation.The model is trained and tested on the real dataset,Argoverse 2,and the experimental results show that compared with the CRAT-Pred,this model can improve minADE,minFDE and Miss Rate(MR)metrics in single-modal prediction by 3.86%,3.89%,and 0.48%,and in multi-modal prediction by 0.78%,0.96% and 0.42%.Hence,the proposed trajectory prediction method can efficiently capture the temporal and spatial characteristics of vehicle movement trajectories and can be effectively applied in related fields such as autonomous driving.

关 键 词：多模态任务 轨迹预测 时空特征 注意力机制 交叉注意力 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]