摘要
为了全面了解基于深度学习的智能车辆轨迹预测研究方法和现状,通过对现有文献进行分析和总结,分析了基于深度学习的轨迹预测模型的输入表示、输出类型和预测方法。结果表明,基于深度学习的轨迹预测方法在长时域、多模态运动及车路交互场景中能够取得优异表现。
In order to fully understand the research methods and current status of deep learning-based trajectory prediction of intelligent vehicles,through the analysis and summary of existing literature,the input representation,output types,and prediction methods of deep learning-based trajectory prediction models are analyzed.The results show that trajectory prediction methods based on deep learning demonstrate outstanding performance in long-term,multi-modal motion and vehicle-road interaction scenarios.
作者
杨荣淼
张国宗
Yang Rongmiao;Zhang Guozong(School of Mechatronics and Vehicle Engineering,Chongqing Jiaotong University,Chongqing 400074;School of Mechanical Engineering,Sichuan University of Science&Engineering,Yibing 643002)
出处
《汽车文摘》
2024年第2期1-9,共9页
Automotive Digest
基金
研究生创新基金项目(Y2023082)。
关键词
自动驾驶
车辆轨迹预测
深度学习
复杂行车场景
Autonomous driving
Vehicle trajectory prediction
Deep learning
Complex driving scenarios