深圳大学学报（理工版）2024，Vol.41Issue(1)：92-100,9.DOI:10.3724/SP.J.1249.2024.01092
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
摘要
Abstract
Vehicle trajectory prediction in complex highway weaving areas plays a crucial role in the decision-making 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Key words
traffic engineering/vehicle trajectory prediction/transfer learning/weaving area/long short-term memory neural network/rolling prediction分类
交通工程引用本文复制引用
殷子健,徐良杰,刘伟,马宇康,林海..基于迁移学习的高速公路交织区车辆轨迹预测[J].深圳大学学报（理工版）,2024,41(1):92-100,9.基金项目
National Natural Science Foundation of China(52072290) （52072290）
Key R&D Program of Hubei Province(2023BAB022) （2023BAB022）
National Key R&D Program of China(2022YFB3102100) 国家自然科学基金资助项目(52072290) （2022YFB3102100）
湖北省重点研发计划资助项目(2023BAB022) （2023BAB022）
国家重点研发计划资助项目(2022YFB3102100) （2022YFB3102100）
