AutoPlace: Robust Place Recognition with Single-chip Automotive Radar

Kaiwen Cai; Bing Wang; Chris Xiaoxuan Lu

doi:10.1109/ICRA46639.2022.9811869

AutoPlace: Robust Place Recognition with Single-chip Automotive Radar

Kaiwen Cai, Bing Wang, Chris Xiaoxuan Lu

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

Abstract

This paper presents a novel place recognition approach to autonomous vehicles by using low-cost, single-chip automotive radar. Aimed at improving recognition robustness and fully exploiting the rich information provided by this emerging automotive radar, our approach follows a principled pipeline that comprises (1) dynamic points removal from instant Doppler measurement, (2) spatial-temporal feature embedding on radar point clouds, and (3) retrieved candidates refinement from Radar Cross Section measurement. Extensive experimental results on the public nuScenes dataset demonstrate that existing visual/LiDAR/spinning radar place recognition approaches are less suitable for single-chip automotive radar. In contrast, our purpose-built approach for automotive radar consistently outperforms a variety of baseline methods via a comprehensive set of metrics, providing insights into the efficacy when used in a realistic system.

Original language	English
Title of host publication	Proceedings of 2022 IEEE International Conference on Robotics and Automation
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	2222-2228
Number of pages	7
ISBN (Electronic)	978-1-7281-9681-7
ISBN (Print)	978-1-7281-9682-4
DOIs	https://doi.org/10.1109/ICRA46639.2022.9811869
Publication status	Published - 12 Jul 2022
Event	2022 IEEE International Conference on Robotics and Automation - Philadelphia , United States Duration: 23 May 2022 → 27 May 2022 https://www.icra2022.org/

Conference

Conference	2022 IEEE International Conference on Robotics and Automation
Abbreviated title	ICRA 2022
Country/Territory	United States
City	Philadelphia
Period	23/05/22 → 27/05/22
Internet address	https://www.icra2022.org/

Access to Document

10.1109/ICRA46639.2022.9811869Licence: All Rights Reserved

AutoPlace_CAI_DOA31012022_AFVAccepted author manuscript, 1.93 MBLicence: All Rights Reserved

https://ieeexplore.ieee.org/document/9811869Licence: All Rights Reserved

Cite this

@inproceedings{abfb69cfaff941a7b6bcf773ba259aca,

title = "AutoPlace: Robust Place Recognition with Single-chip Automotive Radar",

abstract = "This paper presents a novel place recognition approach to autonomous vehicles by using low-cost, single-chip automotive radar. Aimed at improving recognition robustness and fully exploiting the rich information provided by this emerging automotive radar, our approach follows a principled pipeline that comprises (1) dynamic points removal from instant Doppler measurement, (2) spatial-temporal feature embedding on radar point clouds, and (3) retrieved candidates refinement from Radar Cross Section measurement. Extensive experimental results on the public nuScenes dataset demonstrate that existing visual/LiDAR/spinning radar place recognition approaches are less suitable for single-chip automotive radar. In contrast, our purpose-built approach for automotive radar consistently outperforms a variety of baseline methods via a comprehensive set of metrics, providing insights into the efficacy when used in a realistic system.",

author = "Kaiwen Cai and Bing Wang and Lu, {Chris Xiaoxuan}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Robotics and Automation, ICRA 2022 ; Conference date: 23-05-2022 Through 27-05-2022",

year = "2022",

month = jul,

day = "12",

doi = "10.1109/ICRA46639.2022.9811869",

language = "English",

isbn = "978-1-7281-9682-4",

pages = "2222--2228",

booktitle = "Proceedings of 2022 IEEE International Conference on Robotics and Automation",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

url = "https://www.icra2022.org/",

}

Cai, K, Wang, B & Lu, CX 2022, AutoPlace: Robust Place Recognition with Single-chip Automotive Radar. in Proceedings of 2022 IEEE International Conference on Robotics and Automation. Institute of Electrical and Electronics Engineers (IEEE), pp. 2222-2228, 2022 IEEE International Conference on Robotics and Automation, Philadelphia , Pennsylvania, United States, 23/05/22. https://doi.org/10.1109/ICRA46639.2022.9811869

TY - GEN

T1 - AutoPlace: Robust Place Recognition with Single-chip Automotive Radar

AU - Cai, Kaiwen

AU - Wang, Bing

AU - Lu, Chris Xiaoxuan

PY - 2022/7/12

Y1 - 2022/7/12

N2 - This paper presents a novel place recognition approach to autonomous vehicles by using low-cost, single-chip automotive radar. Aimed at improving recognition robustness and fully exploiting the rich information provided by this emerging automotive radar, our approach follows a principled pipeline that comprises (1) dynamic points removal from instant Doppler measurement, (2) spatial-temporal feature embedding on radar point clouds, and (3) retrieved candidates refinement from Radar Cross Section measurement. Extensive experimental results on the public nuScenes dataset demonstrate that existing visual/LiDAR/spinning radar place recognition approaches are less suitable for single-chip automotive radar. In contrast, our purpose-built approach for automotive radar consistently outperforms a variety of baseline methods via a comprehensive set of metrics, providing insights into the efficacy when used in a realistic system.

AB - This paper presents a novel place recognition approach to autonomous vehicles by using low-cost, single-chip automotive radar. Aimed at improving recognition robustness and fully exploiting the rich information provided by this emerging automotive radar, our approach follows a principled pipeline that comprises (1) dynamic points removal from instant Doppler measurement, (2) spatial-temporal feature embedding on radar point clouds, and (3) retrieved candidates refinement from Radar Cross Section measurement. Extensive experimental results on the public nuScenes dataset demonstrate that existing visual/LiDAR/spinning radar place recognition approaches are less suitable for single-chip automotive radar. In contrast, our purpose-built approach for automotive radar consistently outperforms a variety of baseline methods via a comprehensive set of metrics, providing insights into the efficacy when used in a realistic system.

U2 - 10.1109/ICRA46639.2022.9811869

DO - 10.1109/ICRA46639.2022.9811869

M3 - Conference contribution

SN - 978-1-7281-9682-4

SP - 2222

EP - 2228

BT - Proceedings of 2022 IEEE International Conference on Robotics and Automation

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2022 IEEE International Conference on Robotics and Automation

Y2 - 23 May 2022 through 27 May 2022

ER -

AutoPlace: Robust Place Recognition with Single-chip Automotive Radar

Abstract

Conference

Access to Document

Fingerprint

Cite this