A new sonar salient feature structure for EKF-based SLAM

Se Jin Lee, Jae-Bok Song

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

12 Citations (Scopus)

Abstract

Not all line or point features capable of being extracted by sonar sensors from cluttered home environments are useful for simultaneous localization and mapping (SLAM) due to their ambiguity. We present a new sonar feature structure suitable for a cluttered environment and the extended Kalman filter (EKF)-based SLAM scheme. The key concept is to extract circle feature clouds on salient convex objects by sonar data association. The centroid of each circle cloud, called a sonar salient feature, is used as a natural landmark for EKF-based SLAM. After completing initial exploration in an unknown environment, SLAM-able areas with sonar salient features can be defined, and cylindrical objects are placed conveniently at weak SLAM-able areas as a supplemental environmental saliency to enhance SLAM performance. Experimental results demonstrate the validity and robustness of the proposed sonar salient feature structure for EKF-based SLAM.

Original languageEnglish
Title of host publicationIEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings
Pages5966-5971
Number of pages6
DOIs
Publication statusPublished - 2010 Dec 1
Event23rd IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Taipei, Taiwan, Province of China
Duration: 2010 Oct 182010 Oct 22

Other

Other23rd IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010
CountryTaiwan, Province of China
CityTaipei
Period10/10/1810/10/22

Fingerprint

Sonar
Extended Kalman filters
Sensors

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Control and Systems Engineering

Cite this

Lee, S. J., & Song, J-B. (2010). A new sonar salient feature structure for EKF-based SLAM. In IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings (pp. 5966-5971). [5650169] https://doi.org/10.1109/IROS.2010.5650169

A new sonar salient feature structure for EKF-based SLAM. / Lee, Se Jin; Song, Jae-Bok.

IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings. 2010. p. 5966-5971 5650169.

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

Lee, SJ & Song, J-B 2010, A new sonar salient feature structure for EKF-based SLAM. in IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings., 5650169, pp. 5966-5971, 23rd IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010, Taipei, Taiwan, Province of China, 10/10/18. https://doi.org/10.1109/IROS.2010.5650169
Lee SJ, Song J-B. A new sonar salient feature structure for EKF-based SLAM. In IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings. 2010. p. 5966-5971. 5650169 https://doi.org/10.1109/IROS.2010.5650169
Lee, Se Jin ; Song, Jae-Bok. / A new sonar salient feature structure for EKF-based SLAM. IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings. 2010. pp. 5966-5971
@inproceedings{c671c1ebbba547e78f2d2a7e83793694,
title = "A new sonar salient feature structure for EKF-based SLAM",
abstract = "Not all line or point features capable of being extracted by sonar sensors from cluttered home environments are useful for simultaneous localization and mapping (SLAM) due to their ambiguity. We present a new sonar feature structure suitable for a cluttered environment and the extended Kalman filter (EKF)-based SLAM scheme. The key concept is to extract circle feature clouds on salient convex objects by sonar data association. The centroid of each circle cloud, called a sonar salient feature, is used as a natural landmark for EKF-based SLAM. After completing initial exploration in an unknown environment, SLAM-able areas with sonar salient features can be defined, and cylindrical objects are placed conveniently at weak SLAM-able areas as a supplemental environmental saliency to enhance SLAM performance. Experimental results demonstrate the validity and robustness of the proposed sonar salient feature structure for EKF-based SLAM.",
author = "Lee, {Se Jin} and Jae-Bok Song",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/IROS.2010.5650169",
language = "English",
isbn = "9781424466757",
pages = "5966--5971",
booktitle = "IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings",

}

TY - GEN

T1 - A new sonar salient feature structure for EKF-based SLAM

AU - Lee, Se Jin

AU - Song, Jae-Bok

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Not all line or point features capable of being extracted by sonar sensors from cluttered home environments are useful for simultaneous localization and mapping (SLAM) due to their ambiguity. We present a new sonar feature structure suitable for a cluttered environment and the extended Kalman filter (EKF)-based SLAM scheme. The key concept is to extract circle feature clouds on salient convex objects by sonar data association. The centroid of each circle cloud, called a sonar salient feature, is used as a natural landmark for EKF-based SLAM. After completing initial exploration in an unknown environment, SLAM-able areas with sonar salient features can be defined, and cylindrical objects are placed conveniently at weak SLAM-able areas as a supplemental environmental saliency to enhance SLAM performance. Experimental results demonstrate the validity and robustness of the proposed sonar salient feature structure for EKF-based SLAM.

AB - Not all line or point features capable of being extracted by sonar sensors from cluttered home environments are useful for simultaneous localization and mapping (SLAM) due to their ambiguity. We present a new sonar feature structure suitable for a cluttered environment and the extended Kalman filter (EKF)-based SLAM scheme. The key concept is to extract circle feature clouds on salient convex objects by sonar data association. The centroid of each circle cloud, called a sonar salient feature, is used as a natural landmark for EKF-based SLAM. After completing initial exploration in an unknown environment, SLAM-able areas with sonar salient features can be defined, and cylindrical objects are placed conveniently at weak SLAM-able areas as a supplemental environmental saliency to enhance SLAM performance. Experimental results demonstrate the validity and robustness of the proposed sonar salient feature structure for EKF-based SLAM.

UR - http://www.scopus.com/inward/record.url?scp=78651503282&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651503282&partnerID=8YFLogxK

U2 - 10.1109/IROS.2010.5650169

DO - 10.1109/IROS.2010.5650169

M3 - Conference contribution

SN - 9781424466757

SP - 5966

EP - 5971

BT - IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings

ER -