MCL-based global localization of cleaning robot using fast rotation-invariant corner matching method

Tae Bum Kwon, Jae-Bok Song, Sung Chul Kang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Mobile robot navigation with ceiling features such as a corner which is one of the most popular visual features used in robotics has been widely studied because of its practicality and high performance, and recently low-cost robots have started to use this navigation technique. A cleaning robot is a good example. This study is focused on global localization of a cleaning robot and MCL, one of the popular localization methods, was used with ceiling corners. However, MCL-based global localization is a very time consuming task even on a PC, and so a fast rotation-invariant corner matching method was proposed in this study to reduce the time of global localization with corner features. A pixel-based sum of squared differences (SSD) method has been widely used for corner matching. However, because this method cannot match corners with rotation changes, it is unsuitable for a cleaning robot where corners observed from the robot have rotation changes. In our approach, the image around a corner is divided into some partitions and the representative values of all partitions are computed to generate a rotation-invariant descriptor. This descriptor consists of a small number of values, and two descriptors are simply compared to match two corners. Various experiments on a PC and an embedded system verify that matching by the proposed method is very fast and invariant to a rotation change, and is more suitable for a cleaning robot than the pixel-based SSD method. Moreover, global localization can be conducted using this matching method.

Original languageEnglish
Title of host publicationICCAS 2010 - International Conference on Control, Automation and Systems
Pages1988-1992
Number of pages5
Publication statusPublished - 2010 Dec 1
EventInternational Conference on Control, Automation and Systems, ICCAS 2010 - Gyeonggi-do, Korea, Republic of
Duration: 2010 Oct 272010 Oct 30

Other

OtherInternational Conference on Control, Automation and Systems, ICCAS 2010
CountryKorea, Republic of
CityGyeonggi-do
Period10/10/2710/10/30

Fingerprint

Cleaning
Robots
Ceilings
Navigation
Pixels
Embedded systems
Mobile robots
Robotics
Costs
Experiments

Keywords

  • Ceiling corner
  • Cleaning robot localization
  • Rotation-invariant corner matching

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Kwon, T. B., Song, J-B., & Kang, S. C. (2010). MCL-based global localization of cleaning robot using fast rotation-invariant corner matching method. In ICCAS 2010 - International Conference on Control, Automation and Systems (pp. 1988-1992). [5669754]

MCL-based global localization of cleaning robot using fast rotation-invariant corner matching method. / Kwon, Tae Bum; Song, Jae-Bok; Kang, Sung Chul.

ICCAS 2010 - International Conference on Control, Automation and Systems. 2010. p. 1988-1992 5669754.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kwon, TB, Song, J-B & Kang, SC 2010, MCL-based global localization of cleaning robot using fast rotation-invariant corner matching method. in ICCAS 2010 - International Conference on Control, Automation and Systems., 5669754, pp. 1988-1992, International Conference on Control, Automation and Systems, ICCAS 2010, Gyeonggi-do, Korea, Republic of, 10/10/27.
Kwon TB, Song J-B, Kang SC. MCL-based global localization of cleaning robot using fast rotation-invariant corner matching method. In ICCAS 2010 - International Conference on Control, Automation and Systems. 2010. p. 1988-1992. 5669754
Kwon, Tae Bum ; Song, Jae-Bok ; Kang, Sung Chul. / MCL-based global localization of cleaning robot using fast rotation-invariant corner matching method. ICCAS 2010 - International Conference on Control, Automation and Systems. 2010. pp. 1988-1992
@inproceedings{2fea328b967d48149120848c8a918125,
title = "MCL-based global localization of cleaning robot using fast rotation-invariant corner matching method",
abstract = "Mobile robot navigation with ceiling features such as a corner which is one of the most popular visual features used in robotics has been widely studied because of its practicality and high performance, and recently low-cost robots have started to use this navigation technique. A cleaning robot is a good example. This study is focused on global localization of a cleaning robot and MCL, one of the popular localization methods, was used with ceiling corners. However, MCL-based global localization is a very time consuming task even on a PC, and so a fast rotation-invariant corner matching method was proposed in this study to reduce the time of global localization with corner features. A pixel-based sum of squared differences (SSD) method has been widely used for corner matching. However, because this method cannot match corners with rotation changes, it is unsuitable for a cleaning robot where corners observed from the robot have rotation changes. In our approach, the image around a corner is divided into some partitions and the representative values of all partitions are computed to generate a rotation-invariant descriptor. This descriptor consists of a small number of values, and two descriptors are simply compared to match two corners. Various experiments on a PC and an embedded system verify that matching by the proposed method is very fast and invariant to a rotation change, and is more suitable for a cleaning robot than the pixel-based SSD method. Moreover, global localization can be conducted using this matching method.",
keywords = "Ceiling corner, Cleaning robot localization, Rotation-invariant corner matching",
author = "Kwon, {Tae Bum} and Jae-Bok Song and Kang, {Sung Chul}",
year = "2010",
month = "12",
day = "1",
language = "English",
isbn = "9781424474530",
pages = "1988--1992",
booktitle = "ICCAS 2010 - International Conference on Control, Automation and Systems",

}

TY - GEN

T1 - MCL-based global localization of cleaning robot using fast rotation-invariant corner matching method

AU - Kwon, Tae Bum

AU - Song, Jae-Bok

AU - Kang, Sung Chul

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Mobile robot navigation with ceiling features such as a corner which is one of the most popular visual features used in robotics has been widely studied because of its practicality and high performance, and recently low-cost robots have started to use this navigation technique. A cleaning robot is a good example. This study is focused on global localization of a cleaning robot and MCL, one of the popular localization methods, was used with ceiling corners. However, MCL-based global localization is a very time consuming task even on a PC, and so a fast rotation-invariant corner matching method was proposed in this study to reduce the time of global localization with corner features. A pixel-based sum of squared differences (SSD) method has been widely used for corner matching. However, because this method cannot match corners with rotation changes, it is unsuitable for a cleaning robot where corners observed from the robot have rotation changes. In our approach, the image around a corner is divided into some partitions and the representative values of all partitions are computed to generate a rotation-invariant descriptor. This descriptor consists of a small number of values, and two descriptors are simply compared to match two corners. Various experiments on a PC and an embedded system verify that matching by the proposed method is very fast and invariant to a rotation change, and is more suitable for a cleaning robot than the pixel-based SSD method. Moreover, global localization can be conducted using this matching method.

AB - Mobile robot navigation with ceiling features such as a corner which is one of the most popular visual features used in robotics has been widely studied because of its practicality and high performance, and recently low-cost robots have started to use this navigation technique. A cleaning robot is a good example. This study is focused on global localization of a cleaning robot and MCL, one of the popular localization methods, was used with ceiling corners. However, MCL-based global localization is a very time consuming task even on a PC, and so a fast rotation-invariant corner matching method was proposed in this study to reduce the time of global localization with corner features. A pixel-based sum of squared differences (SSD) method has been widely used for corner matching. However, because this method cannot match corners with rotation changes, it is unsuitable for a cleaning robot where corners observed from the robot have rotation changes. In our approach, the image around a corner is divided into some partitions and the representative values of all partitions are computed to generate a rotation-invariant descriptor. This descriptor consists of a small number of values, and two descriptors are simply compared to match two corners. Various experiments on a PC and an embedded system verify that matching by the proposed method is very fast and invariant to a rotation change, and is more suitable for a cleaning robot than the pixel-based SSD method. Moreover, global localization can be conducted using this matching method.

KW - Ceiling corner

KW - Cleaning robot localization

KW - Rotation-invariant corner matching

UR - http://www.scopus.com/inward/record.url?scp=78751550197&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78751550197&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78751550197

SN - 9781424474530

SP - 1988

EP - 1992

BT - ICCAS 2010 - International Conference on Control, Automation and Systems

ER -