摘要
为了准确、合理地预测车辆未来轨迹并且理解周围交通流的变化,提出了一种图注意力模式下融合高精地图的轨迹预测方法。设计了基于长短期记忆(LSTM)网络的编码-解码框架,建立了以车辆历史状态和高精地图信息为输入的模型结构,提出了结合车辆局部特征和全局特征的图查询机制输出车辆预测轨迹。在公开数据集nuScenes上的实验结果表明,该模型的综合预测性能优于Traj++、CoverNet等其他先进方法,且具有良好的抗干扰性。
In order to accurately and reasonably predict the future trajectories of vehicles and understand the changes of surrounding traffic flow,a trajectory prediction method combined with high definition map in graph attention mode was proposed.The encoder-decoder framework based on LSTM network was designed,and the model structure with vehicle historical status and high-precision map information as input was established.A graph query mechanism combining local and global features of vehicles was proposed to output vehicle prediction trajectory.The results of experiments carried out on the nuScenes dataset show that the comprehensive prediction performance of our model is better than other state-of-the-art methods,such as Traj++,CoverNet,etc.,and it has good anti-interference.
作者
刘嫣然
孟庆瑜
郭洪艳
李嘉霖
LIU Yan-ran;MENG Qing-yu;GUO Hong-yan;LI Jia-lin(State Key Laboratory of Automotive Simulation and Control,Jilin University,Changchun 130022,China;Collegeof Communication Engineering,Jilin University,Changchun 130022,China)
出处
《吉林大学学报(工学版)》
EI
CAS
CSCD
北大核心
2023年第3期792-801,共10页
Journal of Jilin University:Engineering and Technology Edition
基金
国家自然科学基金项目(U19A2069)
吉林省科技厅重大科技专项项目(20200501011GX)
吉林省科技发展计划重点研发项目(20200401088GX)
吉林省自然科学基金项目(YDZJ202101ZYTS017)。
关键词
车辆工程
轨迹预测
长短时记忆网络
图注意力网络
高精地图
vehicle engineering
trajectory prediction
long-short term memory network
graph attention network
high definition map