Improvement of outdoor localization based on particle filter through video information's variable uncertainty

Dong Kim, Jae-Bok Song, Ji Hoon Choi

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

Abstract

Localization of a mobile robot is a very important issue for robot's navigation. However, localization method with conventional wheel odometry has limits in case the wheel faces slippery conditions. As an alternative way, visual odometry has been researched continuously. However, this method alone has also difficulty for robust localization because wrong depth measurement can frequently occur and the error is accumulated continuously. Even though localization can be improved by using particle filter, this method is dependent on the accuracy of the reference map. For improving these drawbacks, this research utilized variable uncertainty useful for denoting accuracy of motion model from video information. Consequently, localization in the environments represented by inaccurate maps was improved compared to the conventional method.

Original languageEnglish
Title of host publication2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012
Pages163-166
Number of pages4
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012 - Daejeon, Korea, Republic of
Duration: 2012 Nov 262012 Nov 29

Other

Other2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012
CountryKorea, Republic of
CityDaejeon
Period12/11/2612/11/29

Fingerprint

Wheels
Mobile robots
Navigation
Robots
Uncertainty

Keywords

  • Monte Carlo Localization(MCL)
  • Particle filter
  • Visual odometry

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Kim, D., Song, J-B., & Choi, J. H. (2012). Improvement of outdoor localization based on particle filter through video information's variable uncertainty. In 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012 (pp. 163-166). [6462958] https://doi.org/10.1109/URAI.2012.6462958

Improvement of outdoor localization based on particle filter through video information's variable uncertainty. / Kim, Dong; Song, Jae-Bok; Choi, Ji Hoon.

2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012. 2012. p. 163-166 6462958.

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

Kim, D, Song, J-B & Choi, JH 2012, Improvement of outdoor localization based on particle filter through video information's variable uncertainty. in 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012., 6462958, pp. 163-166, 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012, Daejeon, Korea, Republic of, 12/11/26. https://doi.org/10.1109/URAI.2012.6462958
Kim D, Song J-B, Choi JH. Improvement of outdoor localization based on particle filter through video information's variable uncertainty. In 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012. 2012. p. 163-166. 6462958 https://doi.org/10.1109/URAI.2012.6462958
Kim, Dong ; Song, Jae-Bok ; Choi, Ji Hoon. / Improvement of outdoor localization based on particle filter through video information's variable uncertainty. 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012. 2012. pp. 163-166
@inproceedings{0d86c29fb789472ebbbfcb08d8cba3b0,
title = "Improvement of outdoor localization based on particle filter through video information's variable uncertainty",
abstract = "Localization of a mobile robot is a very important issue for robot's navigation. However, localization method with conventional wheel odometry has limits in case the wheel faces slippery conditions. As an alternative way, visual odometry has been researched continuously. However, this method alone has also difficulty for robust localization because wrong depth measurement can frequently occur and the error is accumulated continuously. Even though localization can be improved by using particle filter, this method is dependent on the accuracy of the reference map. For improving these drawbacks, this research utilized variable uncertainty useful for denoting accuracy of motion model from video information. Consequently, localization in the environments represented by inaccurate maps was improved compared to the conventional method.",
keywords = "Monte Carlo Localization(MCL), Particle filter, Visual odometry",
author = "Dong Kim and Jae-Bok Song and Choi, {Ji Hoon}",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/URAI.2012.6462958",
language = "English",
isbn = "9781467331104",
pages = "163--166",
booktitle = "2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012",

}

TY - GEN

T1 - Improvement of outdoor localization based on particle filter through video information's variable uncertainty

AU - Kim, Dong

AU - Song, Jae-Bok

AU - Choi, Ji Hoon

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Localization of a mobile robot is a very important issue for robot's navigation. However, localization method with conventional wheel odometry has limits in case the wheel faces slippery conditions. As an alternative way, visual odometry has been researched continuously. However, this method alone has also difficulty for robust localization because wrong depth measurement can frequently occur and the error is accumulated continuously. Even though localization can be improved by using particle filter, this method is dependent on the accuracy of the reference map. For improving these drawbacks, this research utilized variable uncertainty useful for denoting accuracy of motion model from video information. Consequently, localization in the environments represented by inaccurate maps was improved compared to the conventional method.

AB - Localization of a mobile robot is a very important issue for robot's navigation. However, localization method with conventional wheel odometry has limits in case the wheel faces slippery conditions. As an alternative way, visual odometry has been researched continuously. However, this method alone has also difficulty for robust localization because wrong depth measurement can frequently occur and the error is accumulated continuously. Even though localization can be improved by using particle filter, this method is dependent on the accuracy of the reference map. For improving these drawbacks, this research utilized variable uncertainty useful for denoting accuracy of motion model from video information. Consequently, localization in the environments represented by inaccurate maps was improved compared to the conventional method.

KW - Monte Carlo Localization(MCL)

KW - Particle filter

KW - Visual odometry

UR - http://www.scopus.com/inward/record.url?scp=84874693560&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874693560&partnerID=8YFLogxK

U2 - 10.1109/URAI.2012.6462958

DO - 10.1109/URAI.2012.6462958

M3 - Conference contribution

SN - 9781467331104

SP - 163

EP - 166

BT - 2012 9th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2012

ER -