西安电子科技大学学报 ›› 2023, Vol. 50 ›› Issue (3): 50-60.doi: 10.19665/j.issn1001-2400.2023.03.005

• 面向IT3.0的感通算融合6G关键技术专题 • 上一篇    下一篇

基于GNN-LSTM-CNN网络的6G车辆轨迹预测算法

蔡国庆1,2,3(),刘玲2,3,4(),张冲2,3,4(),周一青2,3,4()   

  1. 1.郑州大学 河南先进技术研究院,河南 郑州 450001
    2.中国科学院计算技术研究所 处理器芯片全国重点实验室,北京 100190
    3.移动计算与新型终端北京市重点实验室,北京 100190
    4.中国科学院大学,北京 100049
  • 收稿日期:2022-12-16 出版日期:2023-06-20 发布日期:2023-10-13
  • 通讯作者: 刘玲
  • 作者简介:蔡国庆(1998—),男,郑州大学硕士研究生,E-mail:cgq18652931731@163.com;|张 冲(1995—),男,中国科学院大学计算技术研究所博士研究生,E-mail:zhangchong@ict.ac.cn;|周一青(1975—),女,研究员,博士生导师,E-mail:zhouyiqing@ict.ac.cn
  • 基金资助:
    国家自然科学基金(U21A20449)

Algorithm for prediction of the 6G vehicle trajectory based on the GNN-LSTM-CNN network

CAI Gouqing1,2,3(),LIU Ling2,3,4(),ZHANG Chong2,3,4(),ZHOU Yiqing2,3,4()   

  1. 1. Henan Advanced Technology Research Institute,Zhengzhou University,Zhengzhou,450001,China
    2. State Key Lab of Processors,Institute of Computing Technology,Beijing,100190,China
    3. Beijing Key Laboratory of Mobile Computing and New Terminals,Beijing,100190,China
    4. University of Chinese Academy of Sciences,Beijing,100049,China
  • Received:2022-12-16 Online:2023-06-20 Published:2023-10-13
  • Contact: Ling LIU

摘要:

6G时代将实现万物互联,建立多层级、全覆盖的无缝连接,车联网作为通信、交通、汽车等多个行业融合交叉的关键领域将借助6G技术发展、部署。针对6G车联网中车辆轨迹预测精度不足的问题,采用深度学习的方法,提出了一种三通道神经网络模型。该模型考虑了车辆之间的交互信息、目标车辆的轨迹信息和车道结构信息对轨迹的影响。模型使用长短期记忆网络(LSTM)提取车辆轨迹信息特征,使用图神经网络(GNN)提取不同车辆之间的交互特征,使用卷积神经网络(CNN)提取车道结构特征。通过计算三通道特征向量的权重得到目标车辆预测的轨迹;通过NGSIM数据集对模型进行训练和测试。测试结果表明:与其他预测模型相比,考虑多维度信息的三通道网络预测方法在预测精度和长时域预测上有优势,预测精度提高了20%以上。降低6G车联网系统的数据传输量,可提升车联网系统的用户隐私安全。

关键词: 自动驾驶, 轨迹预测, 神经网络, 长短期记忆网络

Abstract:

The 6G era will realize the interconnection of all things and establish a multi-layer and full-coverage seamless connection.The Internet of Vehicles will be developed and deployed with the help of the 6G technology as a key area for the integration and intersection of communication,transportation,automobile and other industries.Aiming at the insufficient accuracy of the prediction of vehicle trajectories in the 6G Internet of Vehicles,this paper proposes a three-channel neural network model with the method of deep learning.This model takes the impacts of vehicle interaction information,target vehicle trajectories and lane structure information on trajectories into consideration.The long short-term memory network (LSTM) is used to extract the vehicle track information features,graph neural network (GNN) to extract interaction features between different vehicles,and the convolution neural network (CNN) is used to extract lane structure features.The predicted trajectory of the target vehicle is obtained by calculating the weight of the three-channel feature vector and the model is trained and tested by the NGSIM data set.The test results show that the three-channel network prediction method considering multi-dimension information has advantages in prediction accuracy and long time domain prediction compared with other prediction models,and the prediction accuracy is improved by more than 20%.Reducing the data transmission volume of the 6G Internet of Vehicles system can improve the user’s privacy security of the Internet of Vehicles system.

Key words: autopilot, trajectory prediction, neural network, long and short term memory network

中图分类号: 

  • U461