A triangle feature based map-to-map matching and loop closure for 2D graph SLAM

Binqian Jiang; Yilong Zhu; Ming Liu

doi:10.1109/robio49542.2019.8961777

A triangle feature based map-to-map matching and loop closure for 2D graph SLAM

Binqian Jiang
, Yilong Zhu
, Ming Liu

Department of Computer Science and Engineering

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

9 Citations (Scopus)

Abstract

The loop closure problem in 2D LiDAR simultaneous localization and mapping (SLAM) is interesting yet to be solved efficiently, as it suffers from a lack of information in 2D laser rangefinder readings. For this reason, we compare two grid submaps, where features and constraints are enriched, to find loops. We propose a geometric environment descriptor called a Triangle Feature (TF). It exploits the Euclidean distance constraint any three feature points in a submap can form. A 2D graph SLAM system using TF to close loops is also developed. The global maps we build outperform some popular open-source SLAM solutions, and the system can run up to 2.4 times of real-time in our experiments.

Original language	English
Title of host publication	IEEE International Conference on Robotics and Biomimetics, ROBIO 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2719-2725
Number of pages	7
ISBN (Electronic)	9781728163215
DOIs	https://doi.org/10.1109/robio49542.2019.8961777
Publication status	Published - Dec 2019
Event	2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019 - Dali, China Duration: 6 Dec 2019 → 8 Dec 2019

Publication series

Name	IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

Conference

Conference	2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019
Country/Territory	China
City	Dali
Period	6/12/19 → 8/12/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Graph SLAM
Grid map matching
LiDAR
Loop closure

Access to Document

10.1109/robio49542.2019.8961777

Cite this

Jiang, B., Zhu, Y., & Liu, M. (2019). A triangle feature based map-to-map matching and loop closure for 2D graph SLAM. In IEEE International Conference on Robotics and Biomimetics, ROBIO 2019 (pp. 2719-2725). Article 8961777 (IEEE International Conference on Robotics and Biomimetics, ROBIO 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/robio49542.2019.8961777

@inproceedings{bee6a767df824472bc46386aa857ecad,

title = "A triangle feature based map-to-map matching and loop closure for 2D graph SLAM",

abstract = "The loop closure problem in 2D LiDAR simultaneous localization and mapping (SLAM) is interesting yet to be solved efficiently, as it suffers from a lack of information in 2D laser rangefinder readings. For this reason, we compare two grid submaps, where features and constraints are enriched, to find loops. We propose a geometric environment descriptor called a Triangle Feature (TF). It exploits the Euclidean distance constraint any three feature points in a submap can form. A 2D graph SLAM system using TF to close loops is also developed. The global maps we build outperform some popular open-source SLAM solutions, and the system can run up to 2.4 times of real-time in our experiments.",

keywords = "Graph SLAM, Grid map matching, LiDAR, Loop closure",

author = "Binqian Jiang and Yilong Zhu and Ming Liu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019 ; Conference date: 06-12-2019 Through 08-12-2019",

year = "2019",

month = dec,

doi = "10.1109/robio49542.2019.8961777",

language = "English",

series = "IEEE International Conference on Robotics and Biomimetics, ROBIO 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2719--2725",

booktitle = "IEEE International Conference on Robotics and Biomimetics, ROBIO 2019",

}

Jiang, B, Zhu, Y & Liu, M 2019, A triangle feature based map-to-map matching and loop closure for 2D graph SLAM. in IEEE International Conference on Robotics and Biomimetics, ROBIO 2019., 8961777, IEEE International Conference on Robotics and Biomimetics, ROBIO 2019, Institute of Electrical and Electronics Engineers Inc., pp. 2719-2725, 2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019, Dali, China, 6/12/19. https://doi.org/10.1109/robio49542.2019.8961777

A triangle feature based map-to-map matching and loop closure for 2D graph SLAM. / Jiang, Binqian; Zhu, Yilong; Liu, Ming.
IEEE International Conference on Robotics and Biomimetics, ROBIO 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2719-2725 8961777 (IEEE International Conference on Robotics and Biomimetics, ROBIO 2019).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - A triangle feature based map-to-map matching and loop closure for 2D graph SLAM

AU - Jiang, Binqian

AU - Zhu, Yilong

AU - Liu, Ming

PY - 2019/12

Y1 - 2019/12

N2 - The loop closure problem in 2D LiDAR simultaneous localization and mapping (SLAM) is interesting yet to be solved efficiently, as it suffers from a lack of information in 2D laser rangefinder readings. For this reason, we compare two grid submaps, where features and constraints are enriched, to find loops. We propose a geometric environment descriptor called a Triangle Feature (TF). It exploits the Euclidean distance constraint any three feature points in a submap can form. A 2D graph SLAM system using TF to close loops is also developed. The global maps we build outperform some popular open-source SLAM solutions, and the system can run up to 2.4 times of real-time in our experiments.

AB - The loop closure problem in 2D LiDAR simultaneous localization and mapping (SLAM) is interesting yet to be solved efficiently, as it suffers from a lack of information in 2D laser rangefinder readings. For this reason, we compare two grid submaps, where features and constraints are enriched, to find loops. We propose a geometric environment descriptor called a Triangle Feature (TF). It exploits the Euclidean distance constraint any three feature points in a submap can form. A 2D graph SLAM system using TF to close loops is also developed. The global maps we build outperform some popular open-source SLAM solutions, and the system can run up to 2.4 times of real-time in our experiments.

KW - Graph SLAM

KW - Grid map matching

KW - LiDAR

KW - Loop closure

UR - https://www.scopus.com/pages/publications/85079072057

U2 - 10.1109/robio49542.2019.8961777

DO - 10.1109/robio49542.2019.8961777

M3 - Conference Paper published in a book

AN - SCOPUS:85079072057

T3 - IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

SP - 2719

EP - 2725

BT - IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

Y2 - 6 December 2019 through 8 December 2019

ER -

Jiang B, Zhu Y, Liu M. A triangle feature based map-to-map matching and loop closure for 2D graph SLAM. In IEEE International Conference on Robotics and Biomimetics, ROBIO 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 2719-2725. 8961777. (IEEE International Conference on Robotics and Biomimetics, ROBIO 2019). doi: 10.1109/robio49542.2019.8961777

A triangle feature based map-to-map matching and loop closure for 2D graph SLAM

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this