基于迁移学习的高速公路交织区车辆轨迹预测  

Vehicle trajectory prediction in weaving area of expressway based on transfer learning

作　　者：殷子健 徐良杰[1] 刘伟[1] 马宇康 林海[2] YIN Zijian;XU Liangjie;LIU Wei;MA Yukang;LIN Hai(School of Transportation and Logistics Engineering,Wuhan University of Technology,Wuhan 430063,Hubei Province,P.R.China;School of Cyber Science and Engineering,Wuhan University,Wuhan 430072,Hubei Province,P.R.China)

机构地区：[1]武汉理工大学交通与物流工程学院,湖北武汉430063 [2]武汉大学国家网络安全学院,湖北武汉430072

出　　处：《深圳大学学报（理工版）》2024年第1期92-100,共9页Journal of Shenzhen University(Science and Engineering)

基　　金：国家自然科学基金资助项目(52072290);湖北省重点研发计划资助项目(2023BAB022);国家重点研发计划资助项目(2022YFB3102100)

摘　　要：高速公路交织区复杂场景下的车辆轨迹预测对智能汽车的决策与控制具有重要意义.为应对交织区复杂交通流带来的轨迹预测实时性与精确性等挑战,提出一种基于迁移学习的车辆轨迹预测方法,利用已有的高速公路直线段轨迹预测模型进行迁移学习训练,从而实现在交织区场景中更快速精准地轨迹预测.使用NGSIM(next generation simulation)数据集中的交织区轨迹数据,采用长短时记忆神经网络模型,在已充分训练的高速公路直线段模型基础上对交织区进行迁移学习,并采用时间序列滚动预测法逐帧精准预测轨迹.实验结果表明,横向和纵向行为预测准确率可达98.35%和93.01%,轨迹预测值的均方根误差为2.04 cm.交织区迁移学习能够缩短61.1%的模型训练时间,同时提高预测准确率和模型泛化能力.Vehicle trajectory prediction in complex highway weaving areas plays a crucial role in the decisionmaking and control of intelligent vehicles.To address the challenges of agility and accuracy issues for trajectory prediction brought by the complex traffic flow in weaving areas,we propose a vehicle trajectory prediction method based on transfer learning.By utilizing an existing highway straight-line segment trajectory prediction model for transfer learning training,faster and more accurate trajectory predictions can be achieved in weaving areas.Leveraging trajectory data from the next generation simulation(NGSIM)dataset in weaving areas,a long short-term memory(LSTM)neural network model is adapted through transfer learning,building upon the well-trained highway straight-line segment model.Furthermore,a rolling prediction method is adopted for frame-by-frame precise trajectory prediction in time series.The experimental results show that the accuracy of lateral and longitudinal behavior prediction can reach 98.35%and 93.01%,respectively,and the root mean square error of trajectory prediction is 2.04 cm.Transfer learning in the weaving area can shorten the model training time by 61.1%,while simultaneously improving prediction accuracy and model generalization capabilities.

关 键 词：交通工程 车辆轨迹预测 迁移学习 交织区 长短时记忆神经网络 滚动预测 

分 类 号：U491.2[交通运输工程—交通运输规划与管理] TP242.6[交通运输工程—道路与铁道工程]