LSTM-based graph attention network for vehicle trajectory prediction

被引:9
作者
Wang, Jiaqin [1 ,2 ]
Liu, Kai [1 ,2 ]
Li, Hantao [1 ,2 ]
机构
[1] Beihang Univ, Sch Elect & Informat Engn, Beijing 100191, Peoples R China
[2] Beihang Univ, Hangzhou Innovat Inst, Hangzhou 310051, Peoples R China
关键词
Vehicle trajectory prediction; Graph attention network; LSTM; Vehicle interaction; Spatial-temporal relationship; MODEL;
D O I
10.1016/j.comnet.2024.110477
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Vehicle Trajectory Prediction (VTP) is one of the key technologies for autonomous driving, which can improve the safety and collaboration of the autonomous driving system. The interaction behavior among vehicles in reality has an impact on VTP. However, many methods ignore the interaction among vehicles, which results in limited accuracy of prediction results. Therefore, we propose a Long Short -Term Memory (LSTM)-based Graph Attention Network (GAT) method for VTP, which encodes vehicle trajectory information with LSTM networks and represents vehicle interactions with GAT. Firstly, in order to capture the temporal relationship between positions and consider their influence, we use LSTM model to encode the position data. Meanwhile, to comprehensively model vehicle motion and use multidimensional feature representation, we employ another LSTM model to encode the motion data, including position, velocity and acceleration. Secondly, to learn distinct feature representation, we use one GAT module to process the LSTM position encoding features for capturing spatial relationships of position information. Another GAT module is employed to process the LSTM motion encoding features for fully considering multidimensional motion dynamics and spatial-temporal dependencies. Finally, the LSTM decoder receives all features and predicts the vehicle trajectory. The experimental results show that the proposed method demonstrates superior predictive performance by using the Next Generation Simulation (NGSIM) dataset.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Vehicle Trajectory Prediction Using Hierarchical LSTM and Graph Attention Network
    Wang, Jiaqin
    Liu, Kai
    Li, Hantao
    Gao, Qiang
    Wang, Xiangfen
    IEEE INTERNET OF THINGS JOURNAL, 2025, 12 (06): : 7010 - 7025
  • [2] A Hierarchical LSTM-Based Vehicle Trajectory Prediction Method Considering Interaction Information
    Min, Haitao
    Xiong, Xiaoyong
    Wang, Pengyu
    Zhang, Zhaopu
    AUTOMOTIVE INNOVATION, 2024, 7 (01) : 71 - 81
  • [3] Sparse Attention Graph Convolution Network for Vehicle Trajectory Prediction
    Chen, Chongpu
    Chen, Xinbo
    Yang, Yi
    Hang, Peng
    IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2024, 73 (12) : 18294 - 18306
  • [4] An LSTM-based Traffic Prediction Algorithm with Attention Mechanism for Satellite Network
    Zhu, Feiyue
    Liu, Lixiang
    Lin, Teng
    AIPR 2020: 2020 3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND PATTERN RECOGNITION, 2020, : 205 - 209
  • [5] Vehicle Trajectory Prediction Based on Dynamic Graph Neural Network
    Cai, Jijing
    Zhu, Han
    Feng, Hailin
    Wen, Long
    Wang, Wei
    Lv, Meilei
    Fang, Kai
    PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 67 - 72
  • [6] Two-stream LSTM Network with Hybrid Attention for Vehicle Trajectory Prediction
    Li, Chao
    Liu, Zhanwen
    Zhang, Jiaying
    Wang, Yang
    Ding, Fan
    Zhao, Xiangmo
    2022 IEEE 25TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2022, : 1927 - 1934
  • [7] Surrounding vehicle trajectory prediction under mixed traffic flow based on graph attention network
    Gao, Yuan
    Fu, Jinlong
    Feng, Wenwen
    Xu, Tiandong
    Yang, Kaifeng
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2024, 639
  • [8] Vehicle Trajectory Prediction Method Based on Graph Models and Attention Mechanism
    Lian J.
    Ding R.
    Li L.
    Wang X.
    Zhou Y.
    Binggong Xuebao/Acta Armamentarii, 2023, 44 (07): : 2162 - 2170
  • [9] Vehicle Interactive Dynamic Graph Neural Network-Based Trajectory Prediction for Internet of Vehicles
    Yang, Mingxia
    Zhang, Boliang
    Wang, Tingting
    Cai, Jijing
    Weng, Xiang
    Feng, Hailin
    Fang, Kai
    IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (22): : 35777 - 35790
  • [10] A text classification method based on LSTM and graph attention network
    Wang, Haitao
    Li, Fangbing
    CONNECTION SCIENCE, 2022, 34 (01) : 2466 - 2480