A survey on deep learning-based lidar place recognition

LiDAR-based place recognition (LPR) technology processes 3D LiDAR point clouds and encodes them into feature descriptors, enabling mobile robots to recognize previously visited locations. This capability supports critical tasks such as loop closure detection and re-localization. With the rapid advan...

Full description

Saved in:
Bibliographic Details
Main Authors: Weizhong Jiang, Shubin Si, Hanzhang Xue, Yiming Nie, Zhipeng Xiao, Qi Zhu, Liang Xiao
Format: Article
Language:English
Published: ELS Publishing (ELSP) 2025-03-01
Series:Artificial Intelligence and Autonomous Systems
Subjects:
Online Access:https://elsp-homepage.oss-cn-hongkong.aliyuncs.compaper/journal/open/AIAS/2025/aias20250003.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239745343782912
author Weizhong Jiang
Shubin Si
Hanzhang Xue
Yiming Nie
Zhipeng Xiao
Qi Zhu
Liang Xiao
author_facet Weizhong Jiang
Shubin Si
Hanzhang Xue
Yiming Nie
Zhipeng Xiao
Qi Zhu
Liang Xiao
author_sort Weizhong Jiang
collection DOAJ
description LiDAR-based place recognition (LPR) technology processes 3D LiDAR point clouds and encodes them into feature descriptors, enabling mobile robots to recognize previously visited locations. This capability supports critical tasks such as loop closure detection and re-localization. With the rapid advancements in deep learning, deep learning-based LiDAR place recognition (DL-LPR) has emerged as the dominant research direction in this field. However, existing reviews on DL-LPR remain limited in scope. To address this gap, this paper focuses on DL-LPR, introducing its core concepts, system structures, and applications. It presents a coarse-to-fine classification framework to systematically categorize and review existing methods, based on two dimensions: input data structure and model architecture. Furthermore, this paper summarizes commonly used datasets and performance evaluation metrics, along with performance comparisons of representative methods. Finally, it provides an in-depth analysis of the challenges faced by DL-LPR in complex environments, such as long-term, large-scale, and dynamic settings, and offers insights into future development trends.
format Article
id doaj-art-ad6f3bd0a22c4302aff8b184384aef1d
institution Kabale University
issn 2959-0744
2959-0752
language English
publishDate 2025-03-01
publisher ELS Publishing (ELSP)
record_format Article
series Artificial Intelligence and Autonomous Systems
spelling doaj-art-ad6f3bd0a22c4302aff8b184384aef1d2025-08-20T04:00:51ZengELS Publishing (ELSP)Artificial Intelligence and Autonomous Systems2959-07442959-07522025-03-012114310.55092/aias202500031866020103581896704A survey on deep learning-based lidar place recognitionWeizhong Jiang0Shubin Si1Hanzhang Xue2Yiming Nie3Zhipeng Xiao4Qi Zhu5Liang Xiao6Unmanned Systems Technology Research Center, Defense Innovation Institute, Beijing, ChinaUnmanned Systems Technology Research Center, Defense Innovation Institute, Beijing, ChinaTest Center, National University of Defense Technology, Xi’an, ChinaUnmanned Systems Technology Research Center, Defense Innovation Institute, Beijing, ChinaUnmanned Systems Technology Research Center, Defense Innovation Institute, Beijing, ChinaUnmanned Systems Technology Research Center, Defense Innovation Institute, Beijing, ChinaUnmanned Systems Technology Research Center, Defense Innovation Institute, Beijing, ChinaLiDAR-based place recognition (LPR) technology processes 3D LiDAR point clouds and encodes them into feature descriptors, enabling mobile robots to recognize previously visited locations. This capability supports critical tasks such as loop closure detection and re-localization. With the rapid advancements in deep learning, deep learning-based LiDAR place recognition (DL-LPR) has emerged as the dominant research direction in this field. However, existing reviews on DL-LPR remain limited in scope. To address this gap, this paper focuses on DL-LPR, introducing its core concepts, system structures, and applications. It presents a coarse-to-fine classification framework to systematically categorize and review existing methods, based on two dimensions: input data structure and model architecture. Furthermore, this paper summarizes commonly used datasets and performance evaluation metrics, along with performance comparisons of representative methods. Finally, it provides an in-depth analysis of the challenges faced by DL-LPR in complex environments, such as long-term, large-scale, and dynamic settings, and offers insights into future development trends.https://elsp-homepage.oss-cn-hongkong.aliyuncs.compaper/journal/open/AIAS/2025/aias20250003.pdfplace recognitionlidardeep learningmobile robotsnavigationre-localizationloop closure detection
spellingShingle Weizhong Jiang
Shubin Si
Hanzhang Xue
Yiming Nie
Zhipeng Xiao
Qi Zhu
Liang Xiao
A survey on deep learning-based lidar place recognition
Artificial Intelligence and Autonomous Systems
place recognition
lidar
deep learning
mobile robots
navigation
re-localization
loop closure detection
title A survey on deep learning-based lidar place recognition
title_full A survey on deep learning-based lidar place recognition
title_fullStr A survey on deep learning-based lidar place recognition
title_full_unstemmed A survey on deep learning-based lidar place recognition
title_short A survey on deep learning-based lidar place recognition
title_sort survey on deep learning based lidar place recognition
topic place recognition
lidar
deep learning
mobile robots
navigation
re-localization
loop closure detection
url https://elsp-homepage.oss-cn-hongkong.aliyuncs.compaper/journal/open/AIAS/2025/aias20250003.pdf
work_keys_str_mv AT weizhongjiang asurveyondeeplearningbasedlidarplacerecognition
AT shubinsi asurveyondeeplearningbasedlidarplacerecognition
AT hanzhangxue asurveyondeeplearningbasedlidarplacerecognition
AT yimingnie asurveyondeeplearningbasedlidarplacerecognition
AT zhipengxiao asurveyondeeplearningbasedlidarplacerecognition
AT qizhu asurveyondeeplearningbasedlidarplacerecognition
AT liangxiao asurveyondeeplearningbasedlidarplacerecognition
AT weizhongjiang surveyondeeplearningbasedlidarplacerecognition
AT shubinsi surveyondeeplearningbasedlidarplacerecognition
AT hanzhangxue surveyondeeplearningbasedlidarplacerecognition
AT yimingnie surveyondeeplearningbasedlidarplacerecognition
AT zhipengxiao surveyondeeplearningbasedlidarplacerecognition
AT qizhu surveyondeeplearningbasedlidarplacerecognition
AT liangxiao surveyondeeplearningbasedlidarplacerecognition