版权说明 操作指南
首页 > 成果 > 详情

STMF-IE: A Spatial-Temporal Multi-Feature Fusion and Intention-Enlightened Decoding Model for Vehicle Trajectory Prediction

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Gao, Kai;Li, Xunhao;Hu, Lin;Liu, Xinyu;Zhang, Jinlai;...
通讯作者:
Hu, L
作者机构:
[Liu, Xinyu; Zhang, Jinlai; Hu, Lin; Hu, L; Du, Ronghua; Gao, Kai; Li, Xunhao] Changsha Univ Sci & Technol, Coll Automot & Mech Engn, Changsha 410205, Peoples R China.
[Gao, Kai] Hunan Univ, HNU Coll Mech & Vehicle Engn, Changsha 410012, Peoples R China.
Southeast Univ, Sch Transportat, Dept Intelligent Transportat & Spatial Informat, Jiangsu Key Lab Urban ITS, Nanjing 211189, Peoples R China.
[Li, Yongfu] Chongqing Univ Posts & Telecommun, Coll Automat, Key Lab Intelligent Air Ground Cooperat Control Un, Chongqing 400065, Peoples R China.
通讯机构:
[Hu, L ] C
Changsha Univ Sci & Technol, Coll Automot & Mech Engn, Changsha 410205, Peoples R China.
语种:
英文
关键词:
Trajectory;TV;Predictive models;Feature extraction;Attention mechanisms;Decoding;Autonomous vehicles;Transformers;Decision making;Visualization;Interpretation;multi-feature fusion;multi-head attention;trajectory prediction
期刊:
IEEE Transactions on Vehicular Technology
ISSN:
0018-9545
年:
2025
卷:
74
期:
3
页码:
4004-4018
基金类别:
10.13039/100014717-National Outstanding Youth Science Fund Project of National Natural Science Foundation of China (Grant Number: 52325211) 10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 52172399) Natural Science Foundation of Hunan (Grant Number: 2024JJ5023) 10.13039/501100005230-Natural Science Foundation of Chongqing (Grant Number: CSTB2022NSCQ-LZX0025) 10.13039/501100012269-Science and Technology Innovative Research Team in Higher Educational Institutions of Hunan Province
机构署名:
本校为第一且通讯机构
院系归属:
汽车与机械工程学院
摘要:
Accurate trajectory prediction of surrounding vehicles is crucial for ensuring the safety of autonomous vehicles. However, current methods based on neural networks still have room for improvement by further reducing their long-term error. This challenge stems from extracting temporal feature dependencies and mining spatial interactions in lane change scenarios. Previous research has not adequately established the connection between the past and the future features. To this end, we propose a spatial-temporal multi-feature fusion and intention-enlightened decoding (STMF-IE) model that jointly co...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com