交通运输研究2023，Vol.9Issue(6)：12-20,9.DOI:10.16503/j.cnki.2095-9931.2023.06.002
基于潜在特征的时空图卷积网络轨迹预测方法
A Trajectory Prediction Method with Spatial-Temporal Graph Convolutional Network Based on Latent Features
摘要
Abstract
In order to increase the accuracy of vehicle trajectory prediction,this paper proposed a trajecto-ry prediction method with Spatial-Temporal Graph Convolutional Network:CR-STGCN,which was based on latent features.Firstly,an earlier and longer historical trajectory was added specially as input,and a la-tent feature encoding layer was established based on the input.Next,CR-STGCN concatenated and fused the latent features encoded by the encoding layer of the latent features with the mobility and dynamic fea-tures encoded by the spatial-temporal graph convolutional network,and then the predicted trajectory was decoded using a two-layer gate loop unit GRU.Finally,the predicted trajectory model STGCN using spa-tial-temporal convolutional network encoding and two-layer GRU decoding was compared with CR-STGCN on the NGSIM dataset.The results show that the prediction accuracy of CR-STGCN is higher than STGCN in different types of maneuvers and traffic density scenarios,demonstrating the effective-ness of this method in vehicle trajectory prediction and providing a new approach for feature selection in trajectory prediction.关键词
智能交通/时空图卷积网络/轨迹预测/潜在特征/交通密度Key words
intelligent traffic/Spatial-Temporal Graph Convolutional Network/trajectory predic-tion/latent feature/traffic density分类
信息技术与安全科学引用本文复制引用
姚宝珍,吴粤隆,荆治家,陈思轩,仲潜,刘振国..基于潜在特征的时空图卷积网络轨迹预测方法[J].交通运输研究,2023,9(6):12-20,9.基金项目
国家自然科学基金项目(52372313) （52372313）
