New solutions to the premature convergence problem in Monte Carlo localization

Chiang Heng Chien, Chen Chien Hsu, Wei Yen Wang, Wen Chung Kao, Chiang Ju Chien

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

Abstract

In this paper, a new solution towards the premature convergence problem in Monte Carlo Localization for global localization under highly symmetrical environments is proposed. The algorithm employs a "standard direction" to allow particles to move so as to rearrange weights, providing better exploration as a result. Therefore, there are higher opportunities for particles to converge to the real robot pose and prevent premature convergence accordingly. Experiments have verified the proposed algorithm to be reliable and robust by offering notable improvements in the global localization performance.

Original languageEnglish
Title of host publication2016 IEEE 6th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016
EditorsTom Wilson, Wolfgang Endemann, Hans L. Cycon, Dietmar Hepper, Jose Maria Flores-Arias
PublisherIEEE Computer Society
Pages83-84
Number of pages2
ISBN (Electronic)9781509020966
DOIs
Publication statusPublished - 2016 Oct 25
Event6th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016 - Berlin, Germany
Duration: 2016 Sep 52016 Sep 7

Publication series

NameIEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin
Volume2016-October
ISSN (Print)2166-6814
ISSN (Electronic)2166-6822

Other

Other6th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016
CountryGermany
CityBerlin
Period16/9/516/9/7

Fingerprint

Robots
Experiments

Keywords

  • Global Localization
  • Monte Carlo Localization
  • Premature Convergence

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering
  • Media Technology

Cite this

Chien, C. H., Hsu, C. C., Wang, W. Y., Kao, W. C., & Chien, C. J. (2016). New solutions to the premature convergence problem in Monte Carlo localization. In T. Wilson, W. Endemann, H. L. Cycon, D. Hepper, & J. M. Flores-Arias (Eds.), 2016 IEEE 6th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016 (pp. 83-84). [7684723] (IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin; Vol. 2016-October). IEEE Computer Society. https://doi.org/10.1109/ICCE-Berlin.2016.7684723

New solutions to the premature convergence problem in Monte Carlo localization. / Chien, Chiang Heng; Hsu, Chen Chien; Wang, Wei Yen; Kao, Wen Chung; Chien, Chiang Ju.

2016 IEEE 6th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016. ed. / Tom Wilson; Wolfgang Endemann; Hans L. Cycon; Dietmar Hepper; Jose Maria Flores-Arias. IEEE Computer Society, 2016. p. 83-84 7684723 (IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin; Vol. 2016-October).

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

Chien, CH, Hsu, CC, Wang, WY, Kao, WC & Chien, CJ 2016, New solutions to the premature convergence problem in Monte Carlo localization. in T Wilson, W Endemann, HL Cycon, D Hepper & JM Flores-Arias (eds), 2016 IEEE 6th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016., 7684723, IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin, vol. 2016-October, IEEE Computer Society, pp. 83-84, 6th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016, Berlin, Germany, 16/9/5. https://doi.org/10.1109/ICCE-Berlin.2016.7684723
Chien CH, Hsu CC, Wang WY, Kao WC, Chien CJ. New solutions to the premature convergence problem in Monte Carlo localization. In Wilson T, Endemann W, Cycon HL, Hepper D, Flores-Arias JM, editors, 2016 IEEE 6th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016. IEEE Computer Society. 2016. p. 83-84. 7684723. (IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin). https://doi.org/10.1109/ICCE-Berlin.2016.7684723
Chien, Chiang Heng ; Hsu, Chen Chien ; Wang, Wei Yen ; Kao, Wen Chung ; Chien, Chiang Ju. / New solutions to the premature convergence problem in Monte Carlo localization. 2016 IEEE 6th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016. editor / Tom Wilson ; Wolfgang Endemann ; Hans L. Cycon ; Dietmar Hepper ; Jose Maria Flores-Arias. IEEE Computer Society, 2016. pp. 83-84 (IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin).
@inproceedings{f6d3aa4e52b54a99bdb309fa540fddf3,
title = "New solutions to the premature convergence problem in Monte Carlo localization",
abstract = "In this paper, a new solution towards the premature convergence problem in Monte Carlo Localization for global localization under highly symmetrical environments is proposed. The algorithm employs a {"}standard direction{"} to allow particles to move so as to rearrange weights, providing better exploration as a result. Therefore, there are higher opportunities for particles to converge to the real robot pose and prevent premature convergence accordingly. Experiments have verified the proposed algorithm to be reliable and robust by offering notable improvements in the global localization performance.",
keywords = "Global Localization, Monte Carlo Localization, Premature Convergence",
author = "Chien, {Chiang Heng} and Hsu, {Chen Chien} and Wang, {Wei Yen} and Kao, {Wen Chung} and Chien, {Chiang Ju}",
year = "2016",
month = "10",
day = "25",
doi = "10.1109/ICCE-Berlin.2016.7684723",
language = "English",
series = "IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin",
publisher = "IEEE Computer Society",
pages = "83--84",
editor = "Tom Wilson and Wolfgang Endemann and Cycon, {Hans L.} and Dietmar Hepper and Flores-Arias, {Jose Maria}",
booktitle = "2016 IEEE 6th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016",

}

TY - GEN

T1 - New solutions to the premature convergence problem in Monte Carlo localization

AU - Chien, Chiang Heng

AU - Hsu, Chen Chien

AU - Wang, Wei Yen

AU - Kao, Wen Chung

AU - Chien, Chiang Ju

PY - 2016/10/25

Y1 - 2016/10/25

N2 - In this paper, a new solution towards the premature convergence problem in Monte Carlo Localization for global localization under highly symmetrical environments is proposed. The algorithm employs a "standard direction" to allow particles to move so as to rearrange weights, providing better exploration as a result. Therefore, there are higher opportunities for particles to converge to the real robot pose and prevent premature convergence accordingly. Experiments have verified the proposed algorithm to be reliable and robust by offering notable improvements in the global localization performance.

AB - In this paper, a new solution towards the premature convergence problem in Monte Carlo Localization for global localization under highly symmetrical environments is proposed. The algorithm employs a "standard direction" to allow particles to move so as to rearrange weights, providing better exploration as a result. Therefore, there are higher opportunities for particles to converge to the real robot pose and prevent premature convergence accordingly. Experiments have verified the proposed algorithm to be reliable and robust by offering notable improvements in the global localization performance.

KW - Global Localization

KW - Monte Carlo Localization

KW - Premature Convergence

UR - http://www.scopus.com/inward/record.url?scp=84994840423&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994840423&partnerID=8YFLogxK

U2 - 10.1109/ICCE-Berlin.2016.7684723

DO - 10.1109/ICCE-Berlin.2016.7684723

M3 - Conference contribution

AN - SCOPUS:84994840423

T3 - IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin

SP - 83

EP - 84

BT - 2016 IEEE 6th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2016

A2 - Wilson, Tom

A2 - Endemann, Wolfgang

A2 - Cycon, Hans L.

A2 - Hepper, Dietmar

A2 - Flores-Arias, Jose Maria

PB - IEEE Computer Society

ER -