LSH-RANSAC: Incremental matching of large-size maps

Kanji Tanaka, Ken Ichi Saeki, Mamoru Minami, Takeshi Ueda

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a novel approach for robot localization using landmark maps. With recent progress in SLAM researches, it has become crucial for a robot to obtain and use large-size maps that are incrementally built by other mapper robots. Our localization approach successfully works with such incremental and large-size maps. In literature, RANSAC map-matching has been a promising approach for large-size maps. We extend the RANSAC map-matching so as to deal with incremental maps. We combine the incremental RANSAC with an incremental LSH database and develop a hybrid of the position-based and the appearance-based approaches. A series of experiments using radish dataset show promising results.

Original languageEnglish
Pages (from-to)326-334
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE93-D
Issue number2
DOIs
Publication statusPublished - 2010
Externally publishedYes

Fingerprint

Robots
Experiments

Keywords

  • Incremental map-matching
  • LSH
  • Mobile robot
  • RANSAC
  • Self-localization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

LSH-RANSAC : Incremental matching of large-size maps. / Tanaka, Kanji; Saeki, Ken Ichi; Minami, Mamoru; Ueda, Takeshi.

In: IEICE Transactions on Information and Systems, Vol. E93-D, No. 2, 2010, p. 326-334.

Research output: Contribution to journalArticle

Tanaka, Kanji ; Saeki, Ken Ichi ; Minami, Mamoru ; Ueda, Takeshi. / LSH-RANSAC : Incremental matching of large-size maps. In: IEICE Transactions on Information and Systems. 2010 ; Vol. E93-D, No. 2. pp. 326-334.
@article{e9efe6db9322450fbb8b785189bf4e08,
title = "LSH-RANSAC: Incremental matching of large-size maps",
abstract = "This paper presents a novel approach for robot localization using landmark maps. With recent progress in SLAM researches, it has become crucial for a robot to obtain and use large-size maps that are incrementally built by other mapper robots. Our localization approach successfully works with such incremental and large-size maps. In literature, RANSAC map-matching has been a promising approach for large-size maps. We extend the RANSAC map-matching so as to deal with incremental maps. We combine the incremental RANSAC with an incremental LSH database and develop a hybrid of the position-based and the appearance-based approaches. A series of experiments using radish dataset show promising results.",
keywords = "Incremental map-matching, LSH, Mobile robot, RANSAC, Self-localization",
author = "Kanji Tanaka and Saeki, {Ken Ichi} and Mamoru Minami and Takeshi Ueda",
year = "2010",
doi = "10.1587/transinf.E93.D.326",
language = "English",
volume = "E93-D",
pages = "326--334",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "2",

}

TY - JOUR

T1 - LSH-RANSAC

T2 - Incremental matching of large-size maps

AU - Tanaka, Kanji

AU - Saeki, Ken Ichi

AU - Minami, Mamoru

AU - Ueda, Takeshi

PY - 2010

Y1 - 2010

N2 - This paper presents a novel approach for robot localization using landmark maps. With recent progress in SLAM researches, it has become crucial for a robot to obtain and use large-size maps that are incrementally built by other mapper robots. Our localization approach successfully works with such incremental and large-size maps. In literature, RANSAC map-matching has been a promising approach for large-size maps. We extend the RANSAC map-matching so as to deal with incremental maps. We combine the incremental RANSAC with an incremental LSH database and develop a hybrid of the position-based and the appearance-based approaches. A series of experiments using radish dataset show promising results.

AB - This paper presents a novel approach for robot localization using landmark maps. With recent progress in SLAM researches, it has become crucial for a robot to obtain and use large-size maps that are incrementally built by other mapper robots. Our localization approach successfully works with such incremental and large-size maps. In literature, RANSAC map-matching has been a promising approach for large-size maps. We extend the RANSAC map-matching so as to deal with incremental maps. We combine the incremental RANSAC with an incremental LSH database and develop a hybrid of the position-based and the appearance-based approaches. A series of experiments using radish dataset show promising results.

KW - Incremental map-matching

KW - LSH

KW - Mobile robot

KW - RANSAC

KW - Self-localization

UR - http://www.scopus.com/inward/record.url?scp=77950250426&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950250426&partnerID=8YFLogxK

U2 - 10.1587/transinf.E93.D.326

DO - 10.1587/transinf.E93.D.326

M3 - Article

AN - SCOPUS:77950250426

VL - E93-D

SP - 326

EP - 334

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 2

ER -