RadarSLAM: Radar based large-scale SLAM in all weathers

Ziyang Hong; Yvan Petillot; Sen Wang

doi:10.1109/IROS45743.2020.9341287

RadarSLAM: Radar based large-scale SLAM in all weathers

Ziyang Hong, Yvan Petillot, Sen Wang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

81 Citations (Scopus)

Abstract

Numerous Simultaneous Localization and Mapping (SLAM) algorithms have been presented in last decade using different sensor modalities. However, robust SLAM in extreme weather conditions is still an open research problem. In this paper, RadarSLAM, a full radar based graph SLAM system, is proposed for reliable localization and mapping in large-scale environments. It is composed of pose tracking, local mapping, loop closure detection and pose graph optimization, enhanced by novel feature matching and probabilistic point cloud generation on radar images. Extensive experiments are conducted on a public radar dataset and several self-collected radar sequences, demonstrating the state-of-the-art reliability and localization accuracy in various adverse weather conditions, such as dark night, dense fog and heavy snowfall.

Original language	English
Title of host publication	2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Publisher	IEEE
Pages	5164-5170
Number of pages	7
ISBN (Electronic)	9781728162126
DOIs	https://doi.org/10.1109/IROS45743.2020.9341287
Publication status	Published - 10 Feb 2021
Event	2020 IEEE/RSJ International Conference on Intelligent Robots and Systems - Las Vegas, United States Duration: 25 Oct 2020 → 29 Oct 2020 https://www.iros2020.org/

Conference

Conference	2020 IEEE/RSJ International Conference on Intelligent Robots and Systems
Abbreviated title	IROS 2020
Country/Territory	United States
City	Las Vegas
Period	25/10/20 → 29/10/20
Internet address	https://www.iros2020.org/

ASJC Scopus subject areas

Control and Systems Engineering
Software
Computer Vision and Pattern Recognition
Computer Science Applications

Access to Document

10.1109/IROS45743.2020.9341287

Cite this

@inproceedings{5d0d7281da3644d386b0b97de4681640,

title = "RadarSLAM: Radar based large-scale SLAM in all weathers",

abstract = "Numerous Simultaneous Localization and Mapping (SLAM) algorithms have been presented in last decade using different sensor modalities. However, robust SLAM in extreme weather conditions is still an open research problem. In this paper, RadarSLAM, a full radar based graph SLAM system, is proposed for reliable localization and mapping in large-scale environments. It is composed of pose tracking, local mapping, loop closure detection and pose graph optimization, enhanced by novel feature matching and probabilistic point cloud generation on radar images. Extensive experiments are conducted on a public radar dataset and several self-collected radar sequences, demonstrating the state-of-the-art reliability and localization accuracy in various adverse weather conditions, such as dark night, dense fog and heavy snowfall.",

author = "Ziyang Hong and Yvan Petillot and Sen Wang",

note = "Funding Information: ACKNOWLEDGEMENTS We thank Saptarshi Mukherjee, Marcel Sheeny and Dr. Yun Wu for the help of our data collection. This work was supported by EPSRC Robotics and Artificial Intelligence ORCA Hub (grant No. EP/R026173/1) and EU H2020 Programme under EUMarineRobots project (grant ID 731103). We thank Raul Mur-Artal for making ORB-SLAM code open-source, which greatly inspires our implementation. Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020 ; Conference date: 25-10-2020 Through 29-10-2020",

year = "2021",

month = feb,

day = "10",

doi = "10.1109/IROS45743.2020.9341287",

language = "English",

pages = "5164--5170",

booktitle = "2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",

publisher = "IEEE",

address = "United States",

url = "https://www.iros2020.org/",

}

TY - GEN

T1 - RadarSLAM

T2 - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems

AU - Hong, Ziyang

AU - Petillot, Yvan

AU - Wang, Sen

N1 - Funding Information: ACKNOWLEDGEMENTS We thank Saptarshi Mukherjee, Marcel Sheeny and Dr. Yun Wu for the help of our data collection. This work was supported by EPSRC Robotics and Artificial Intelligence ORCA Hub (grant No. EP/R026173/1) and EU H2020 Programme under EUMarineRobots project (grant ID 731103). We thank Raul Mur-Artal for making ORB-SLAM code open-source, which greatly inspires our implementation. Publisher Copyright: © 2020 IEEE.

PY - 2021/2/10

Y1 - 2021/2/10

N2 - Numerous Simultaneous Localization and Mapping (SLAM) algorithms have been presented in last decade using different sensor modalities. However, robust SLAM in extreme weather conditions is still an open research problem. In this paper, RadarSLAM, a full radar based graph SLAM system, is proposed for reliable localization and mapping in large-scale environments. It is composed of pose tracking, local mapping, loop closure detection and pose graph optimization, enhanced by novel feature matching and probabilistic point cloud generation on radar images. Extensive experiments are conducted on a public radar dataset and several self-collected radar sequences, demonstrating the state-of-the-art reliability and localization accuracy in various adverse weather conditions, such as dark night, dense fog and heavy snowfall.

AB - Numerous Simultaneous Localization and Mapping (SLAM) algorithms have been presented in last decade using different sensor modalities. However, robust SLAM in extreme weather conditions is still an open research problem. In this paper, RadarSLAM, a full radar based graph SLAM system, is proposed for reliable localization and mapping in large-scale environments. It is composed of pose tracking, local mapping, loop closure detection and pose graph optimization, enhanced by novel feature matching and probabilistic point cloud generation on radar images. Extensive experiments are conducted on a public radar dataset and several self-collected radar sequences, demonstrating the state-of-the-art reliability and localization accuracy in various adverse weather conditions, such as dark night, dense fog and heavy snowfall.

UR - http://www.scopus.com/inward/record.url?scp=85102023260&partnerID=8YFLogxK

U2 - 10.1109/IROS45743.2020.9341287

DO - 10.1109/IROS45743.2020.9341287

M3 - Conference contribution

AN - SCOPUS:85102023260

SP - 5164

EP - 5170

BT - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

PB - IEEE

Y2 - 25 October 2020 through 29 October 2020

ER -

RadarSLAM: Radar based large-scale SLAM in all weathers

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this