Bayesian robot localization with action-associated sparse appearance-based map in a dynamic indoor environment

Young Bin Park, Il Hong Suh, Byung Uk Choi

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

1 Citation (Scopus)

Abstract

This work considers robot localization with an action-associated sparse appearance-based map, under conditions with dynamic change in the environment. In this case, two significant problems must be solved for robust localization. The first involves variations in the environment caused by dynamic objects and changes in illumination, and the second arises from the nature of sparse appearance-based map. That is, a robot must be able to recognize observations taken at slightly different positions and angles within a certain region as identical. In this paper, we address a possible solution to these problems on the basis of a probabilistic model called the Bayes filter. Here, we propose an observation model based LeTO2 function and an action-associated sparse appearance-based map to be used for prediction, update, and final localization steps. In addition, multiple visual features are used to increase the reliability of the observation model. We performed experiments to demonstrate the validity of the proposed approach under various conditions with regard to dynamic objects, illumination, and viewpoint. The results clearly demonstrated the value of our approach.

Original languageEnglish
Title of host publication2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
Pages3459-3466
Number of pages8
DOIs
StatePublished - 2009 Dec 11
Event2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009 - St. Louis, MO, United States
Duration: 2009 Oct 112009 Oct 15

Publication series

Name2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009

Other

Other2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
CountryUnited States
CitySt. Louis, MO
Period09/10/1109/10/15

Fingerprint

Robots
Lighting
Experiments
Statistical Models

Cite this

Park, Y. B., Suh, I. H., & Choi, B. U. (2009). Bayesian robot localization with action-associated sparse appearance-based map in a dynamic indoor environment. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009 (pp. 3459-3466). [5354259] (2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009). https://doi.org/10.1109/IROS.2009.5354259
Park, Young Bin ; Suh, Il Hong ; Choi, Byung Uk. / Bayesian robot localization with action-associated sparse appearance-based map in a dynamic indoor environment. 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. pp. 3459-3466 (2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009).
@inproceedings{b29a3c9110cf4950a725853f4655ce2a,
title = "Bayesian robot localization with action-associated sparse appearance-based map in a dynamic indoor environment",
abstract = "This work considers robot localization with an action-associated sparse appearance-based map, under conditions with dynamic change in the environment. In this case, two significant problems must be solved for robust localization. The first involves variations in the environment caused by dynamic objects and changes in illumination, and the second arises from the nature of sparse appearance-based map. That is, a robot must be able to recognize observations taken at slightly different positions and angles within a certain region as identical. In this paper, we address a possible solution to these problems on the basis of a probabilistic model called the Bayes filter. Here, we propose an observation model based LeTO2 function and an action-associated sparse appearance-based map to be used for prediction, update, and final localization steps. In addition, multiple visual features are used to increase the reliability of the observation model. We performed experiments to demonstrate the validity of the proposed approach under various conditions with regard to dynamic objects, illumination, and viewpoint. The results clearly demonstrated the value of our approach.",
author = "Park, {Young Bin} and Suh, {Il Hong} and Choi, {Byung Uk}",
year = "2009",
month = "12",
day = "11",
doi = "10.1109/IROS.2009.5354259",
language = "English",
isbn = "9781424438044",
series = "2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009",
pages = "3459--3466",
booktitle = "2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009",

}

Park, YB, Suh, IH & Choi, BU 2009, Bayesian robot localization with action-associated sparse appearance-based map in a dynamic indoor environment. in 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009., 5354259, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009, pp. 3459-3466, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009, St. Louis, MO, United States, 09/10/11. https://doi.org/10.1109/IROS.2009.5354259

Bayesian robot localization with action-associated sparse appearance-based map in a dynamic indoor environment. / Park, Young Bin; Suh, Il Hong; Choi, Byung Uk.

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. p. 3459-3466 5354259 (2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009).

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

TY - GEN

T1 - Bayesian robot localization with action-associated sparse appearance-based map in a dynamic indoor environment

AU - Park, Young Bin

AU - Suh, Il Hong

AU - Choi, Byung Uk

PY - 2009/12/11

Y1 - 2009/12/11

N2 - This work considers robot localization with an action-associated sparse appearance-based map, under conditions with dynamic change in the environment. In this case, two significant problems must be solved for robust localization. The first involves variations in the environment caused by dynamic objects and changes in illumination, and the second arises from the nature of sparse appearance-based map. That is, a robot must be able to recognize observations taken at slightly different positions and angles within a certain region as identical. In this paper, we address a possible solution to these problems on the basis of a probabilistic model called the Bayes filter. Here, we propose an observation model based LeTO2 function and an action-associated sparse appearance-based map to be used for prediction, update, and final localization steps. In addition, multiple visual features are used to increase the reliability of the observation model. We performed experiments to demonstrate the validity of the proposed approach under various conditions with regard to dynamic objects, illumination, and viewpoint. The results clearly demonstrated the value of our approach.

AB - This work considers robot localization with an action-associated sparse appearance-based map, under conditions with dynamic change in the environment. In this case, two significant problems must be solved for robust localization. The first involves variations in the environment caused by dynamic objects and changes in illumination, and the second arises from the nature of sparse appearance-based map. That is, a robot must be able to recognize observations taken at slightly different positions and angles within a certain region as identical. In this paper, we address a possible solution to these problems on the basis of a probabilistic model called the Bayes filter. Here, we propose an observation model based LeTO2 function and an action-associated sparse appearance-based map to be used for prediction, update, and final localization steps. In addition, multiple visual features are used to increase the reliability of the observation model. We performed experiments to demonstrate the validity of the proposed approach under various conditions with regard to dynamic objects, illumination, and viewpoint. The results clearly demonstrated the value of our approach.

UR - http://www.scopus.com/inward/record.url?scp=76249102989&partnerID=8YFLogxK

U2 - 10.1109/IROS.2009.5354259

DO - 10.1109/IROS.2009.5354259

M3 - Conference contribution

AN - SCOPUS:76249102989

SN - 9781424438044

T3 - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009

SP - 3459

EP - 3466

BT - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009

ER -

Park YB, Suh IH, Choi BU. Bayesian robot localization with action-associated sparse appearance-based map in a dynamic indoor environment. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. p. 3459-3466. 5354259. (2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009). https://doi.org/10.1109/IROS.2009.5354259