Page 57 - Read Online
P. 57
Huang et al. Complex Eng Syst 2023;3:2 Complex Engineering
DOI: 10.20517/ces.2022.43 Systems
Research Article Open Access
Generation of high definition map for accurate and ro-
bust localization
2
1
1
1
1
Zhengjie Huang , Sijie Chen , Xing Xi , Yanzhou Li , Ya Li , Shuanglin Wu 3
1 School of Automation, Guangdong University of Technology, Guangzhou 510006, Guangdong, China.
2 Ningbo Artificial Intelligence Institute, Shanghai Jiaotong University, Ningbo 315000, Zhejiang, China.
3 State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China.
Correspondence to: Dr. Yanzhou Li, School of Automation, Guangdong University of Technology, No.100, Waihuan Xi Road,
Guangzhou 510006, Guangdong, China. E-mail: lyz19921207@163.com
How to cite this article: Huang Z, Chen S, Xi X, Li Y, Li Y, Wu S. Generation of high definition map for accurate and robust localization.
Complex Eng Syst 2023;3:2. http://dx.doi.org/10.20517/ces.2022.43
Received: 17 Oct 2022 First Decision: 24 Nov 2022 Revised: 2 Dec 2022 Accepted: 11 Jan 2023 Published: 31 Jan 2023
Academic Editor: Hamid Reza Karimi Copy Editor: Fanglin Lan Production Editor: Fanglin Lan
Abstract
This paper presents a framework for generating high-definition (HD) map, and then achieves accurate and robust
localization by virtue of the map. An iterative approximation based method is developed to generate a HD map in
Lanelet2 format. A feature association method based on structural consistency and feature similarity is proposed to
match the elements of the HD map and the actual detected elements. The feature association results from the HD
map are used to correct lateral drift in the light detection and ranging odometry. Finally, some experimental results
are presented to verify the reliability and accuracy of autonomous driving localization.
Keywords: High definition map, factor graph optimization, localization, reprojection error
1. INTRODUCTION
In recent years, vehicle localization has been treated as an important part of an autonomous driving system.
However, conventional odometry methods have drift problems with long-term use. An inertial navigation
[1]
system (INS) will likely fail in scenarios with poor GNSS signals, such as tunnel and urban canyon scenarios .
For the sake of more accurate localization, multisensor fusion is developed to compensate for the respective
deficiencies of various sensors. HD maps, as stable prior information, can provide reliable location constraints.
© The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, shar-
ing, adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as long as you
give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate
if changes were made.
www.comengsys.com