Dual-circle self-localization for soccer robots with omnidirectional vision

Chen Chien Hsu, Ching Chang Wong, Hung Chih Teng, Cheng Yao Ho

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

A self-localization method entitled dual-circle self-localization (DCSL) for mobile robots in a soccer robot game field is proposed in this article. To evaluate the performance of the proposed localization method, an omnidirectional vision device is installed on top of the robot to capture images for recognizing objects in the environment via a hybrid scanning method. Three reliable objects recognized are then chosen as landmarks to calculate the position of the robot in the game field via the proposed DCSL based on relative positions between the robot and landmarks in the omnidirectional images. Since only simple geometric manipulations are required for the DCSL algorithm, localization efficiency can be significantly improved while maintaining a relatively smaller mean error in comparison to Monte Carlo localization techniques as demonstrated in both simulation results and practical experiments in this article.

Original languageEnglish
Pages (from-to)619-631
Number of pages13
JournalJournal of the Chinese Institute of Engineers, Transactions of the Chinese Institute of Engineers,Series A/Chung-kuo Kung Ch'eng Hsuch K'an
Volume35
Issue number6
DOIs
Publication statusPublished - 2012 Sep 1

Fingerprint

Robots
Mobile robots
Scanning
Experiments

Keywords

  • Autonomous robots
  • Omnidirectional vision
  • Self-localization
  • Soccer robots

ASJC Scopus subject areas

  • Engineering(all)

Cite this

@article{bc17fbad6d5945d188db5d183be23bb0,
title = "Dual-circle self-localization for soccer robots with omnidirectional vision",
abstract = "A self-localization method entitled dual-circle self-localization (DCSL) for mobile robots in a soccer robot game field is proposed in this article. To evaluate the performance of the proposed localization method, an omnidirectional vision device is installed on top of the robot to capture images for recognizing objects in the environment via a hybrid scanning method. Three reliable objects recognized are then chosen as landmarks to calculate the position of the robot in the game field via the proposed DCSL based on relative positions between the robot and landmarks in the omnidirectional images. Since only simple geometric manipulations are required for the DCSL algorithm, localization efficiency can be significantly improved while maintaining a relatively smaller mean error in comparison to Monte Carlo localization techniques as demonstrated in both simulation results and practical experiments in this article.",
keywords = "Autonomous robots, Omnidirectional vision, Self-localization, Soccer robots",
author = "Hsu, {Chen Chien} and Wong, {Ching Chang} and Teng, {Hung Chih} and Ho, {Cheng Yao}",
year = "2012",
month = "9",
day = "1",
doi = "10.1080/02533839.2012.701835",
language = "English",
volume = "35",
pages = "619--631",
journal = "Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers",
issn = "0253-3839",
publisher = "Chinese Institute of Engineers",
number = "6",

}

TY - JOUR

T1 - Dual-circle self-localization for soccer robots with omnidirectional vision

AU - Hsu, Chen Chien

AU - Wong, Ching Chang

AU - Teng, Hung Chih

AU - Ho, Cheng Yao

PY - 2012/9/1

Y1 - 2012/9/1

N2 - A self-localization method entitled dual-circle self-localization (DCSL) for mobile robots in a soccer robot game field is proposed in this article. To evaluate the performance of the proposed localization method, an omnidirectional vision device is installed on top of the robot to capture images for recognizing objects in the environment via a hybrid scanning method. Three reliable objects recognized are then chosen as landmarks to calculate the position of the robot in the game field via the proposed DCSL based on relative positions between the robot and landmarks in the omnidirectional images. Since only simple geometric manipulations are required for the DCSL algorithm, localization efficiency can be significantly improved while maintaining a relatively smaller mean error in comparison to Monte Carlo localization techniques as demonstrated in both simulation results and practical experiments in this article.

AB - A self-localization method entitled dual-circle self-localization (DCSL) for mobile robots in a soccer robot game field is proposed in this article. To evaluate the performance of the proposed localization method, an omnidirectional vision device is installed on top of the robot to capture images for recognizing objects in the environment via a hybrid scanning method. Three reliable objects recognized are then chosen as landmarks to calculate the position of the robot in the game field via the proposed DCSL based on relative positions between the robot and landmarks in the omnidirectional images. Since only simple geometric manipulations are required for the DCSL algorithm, localization efficiency can be significantly improved while maintaining a relatively smaller mean error in comparison to Monte Carlo localization techniques as demonstrated in both simulation results and practical experiments in this article.

KW - Autonomous robots

KW - Omnidirectional vision

KW - Self-localization

KW - Soccer robots

UR - http://www.scopus.com/inward/record.url?scp=84867222917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867222917&partnerID=8YFLogxK

U2 - 10.1080/02533839.2012.701835

DO - 10.1080/02533839.2012.701835

M3 - Article

AN - SCOPUS:84867222917

VL - 35

SP - 619

EP - 631

JO - Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers

JF - Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers

SN - 0253-3839

IS - 6

ER -