End-to-End Online Vectorized Map Construction With Confidence Estimates

This study proposes an end-to-end online vector map generation method, termed COMap, which integrates confidence estimation to enhance the robustness and reliability of environmental perception systems in autonomous driving. The method is based on the DETR framework and introduces a dynamic instance...

Full description

Saved in:
Bibliographic Details
Main Authors: Bo Huang, Feng Du, Tao Peng, Xiao-Long Zheng, Ji-Quan Wu, Jun-Hui Zhang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11028039/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849689657336397824
author Bo Huang
Feng Du
Tao Peng
Xiao-Long Zheng
Ji-Quan Wu
Jun-Hui Zhang
author_facet Bo Huang
Feng Du
Tao Peng
Xiao-Long Zheng
Ji-Quan Wu
Jun-Hui Zhang
author_sort Bo Huang
collection DOAJ
description This study proposes an end-to-end online vector map generation method, termed COMap, which integrates confidence estimation to enhance the robustness and reliability of environmental perception systems in autonomous driving. The method is based on the DETR framework and introduces a dynamic instance query mechanism to strengthen the geometric representation capabilities of map elements. Additionally, it employs a full-covariance Gaussian distribution for confidence modeling, effectively quantifying prediction uncertainty and thereby improving the reliability of the map data. Experimental results demonstrate that COMap achieves a higher mean Average Precision (mAP) value on the nuScenes dataset compared to existing methods and significantly reduces the false detection rate in complex scenarios, thereby enhancing the accuracy of road structure representation. This method not only improves the stability of online map generation but also provides more reliable data support for downstream tasks such as path planning and decision-making in autonomous driving.
format Article
id doaj-art-3171911b1bbc4f13965a9986a3a8affc
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-3171911b1bbc4f13965a9986a3a8affc2025-08-20T03:21:32ZengIEEEIEEE Access2169-35362025-01-011310119610121010.1109/ACCESS.2025.357775111028039End-to-End Online Vectorized Map Construction With Confidence EstimatesBo Huang0https://orcid.org/0009-0001-2653-265XFeng Du1https://orcid.org/0000-0003-1833-1476Tao Peng2Xiao-Long Zheng3https://orcid.org/0009-0007-0668-5871Ji-Quan Wu4https://orcid.org/0009-0002-1602-4931Jun-Hui Zhang5School of Automobile and Transportation, Tianjin University of Technology and Education, Tianjin, ChinaSchool of Automobile and Transportation, Tianjin University of Technology and Education, Tianjin, ChinaSchool of Automobile and Transportation, Tianjin University of Technology and Education, Tianjin, ChinaSchool of Automobile and Transportation, Tianjin University of Technology and Education, Tianjin, ChinaSchool of Automobile and Transportation, Tianjin University of Technology and Education, Tianjin, ChinaSchool of Automobile and Transportation, Tianjin University of Technology and Education, Tianjin, ChinaThis study proposes an end-to-end online vector map generation method, termed COMap, which integrates confidence estimation to enhance the robustness and reliability of environmental perception systems in autonomous driving. The method is based on the DETR framework and introduces a dynamic instance query mechanism to strengthen the geometric representation capabilities of map elements. Additionally, it employs a full-covariance Gaussian distribution for confidence modeling, effectively quantifying prediction uncertainty and thereby improving the reliability of the map data. Experimental results demonstrate that COMap achieves a higher mean Average Precision (mAP) value on the nuScenes dataset compared to existing methods and significantly reduces the false detection rate in complex scenarios, thereby enhancing the accuracy of road structure representation. This method not only improves the stability of online map generation but also provides more reliable data support for downstream tasks such as path planning and decision-making in autonomous driving.https://ieeexplore.ieee.org/document/11028039/Online vector map generationconfidence estimationend-to-end map buildingautonomous driving perception
spellingShingle Bo Huang
Feng Du
Tao Peng
Xiao-Long Zheng
Ji-Quan Wu
Jun-Hui Zhang
End-to-End Online Vectorized Map Construction With Confidence Estimates
IEEE Access
Online vector map generation
confidence estimation
end-to-end map building
autonomous driving perception
title End-to-End Online Vectorized Map Construction With Confidence Estimates
title_full End-to-End Online Vectorized Map Construction With Confidence Estimates
title_fullStr End-to-End Online Vectorized Map Construction With Confidence Estimates
title_full_unstemmed End-to-End Online Vectorized Map Construction With Confidence Estimates
title_short End-to-End Online Vectorized Map Construction With Confidence Estimates
title_sort end to end online vectorized map construction with confidence estimates
topic Online vector map generation
confidence estimation
end-to-end map building
autonomous driving perception
url https://ieeexplore.ieee.org/document/11028039/
work_keys_str_mv AT bohuang endtoendonlinevectorizedmapconstructionwithconfidenceestimates
AT fengdu endtoendonlinevectorizedmapconstructionwithconfidenceestimates
AT taopeng endtoendonlinevectorizedmapconstructionwithconfidenceestimates
AT xiaolongzheng endtoendonlinevectorizedmapconstructionwithconfidenceestimates
AT jiquanwu endtoendonlinevectorizedmapconstructionwithconfidenceestimates
AT junhuizhang endtoendonlinevectorizedmapconstructionwithconfidenceestimates