Mobile Robot Navigation in a Corridor Using Visual Odometry

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

768 Downloads (Pure)

Abstract

Incorporation of computer vision into mobile robot localization is studied in this work. It includes the generation of localization information from raw images and its fusion with the odometric pose estimation. The technique is then implemented on a small mobile robot operating at a corridor environment. A new segmented Hough transform with an improved way of discretization is used for image line extraction. The vanishing point concept is then incorporated to classify lines as well as to estimate the orientation. A method involving the iterative elimination of the outliers is employed to find both the vanishing point and the camera position. The fusion between the vision based pose estimation and the odometry is achieved with an extended Kalman filter. A distance driven error model is used for the odometry while a simple error model with constant noise is assumed for the vision. An extended Kalman filter as a parameter estimator is also applied to estimate odometry parameters. Experimental results are included. The robustness and the precision of the entire system is illustrated by performing simple navigation tasks.
Original languageEnglish
Title of host publicationProoceedings of the 14th International Conference on Advanced Robotics
PublisherIEEE
Publication date2009
Pages58
ISBN (Print)978-1-4244-4855-5
Publication statusPublished - 2009
EventInternational Conference on Advanced Robotics - Munich, Germany
Duration: 1 Jan 2009 → …
Conference number: 14th

Conference

ConferenceInternational Conference on Advanced Robotics
Number14th
CityMunich, Germany
Period01/01/2009 → …

Bibliographical note

Copyright: 2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

Keywords

  • Line Extraction
  • Vision
  • Sensor Fusion
  • Localization
  • Navigation
  • Mobile Robot

Cite this

Bayramoglu, E., Andersen, N. A., Poulsen, N. K., Andersen, J. C., & Ravn, O. (2009). Mobile Robot Navigation in a Corridor Using Visual Odometry. In Prooceedings of the 14th International Conference on Advanced Robotics (pp. 58). IEEE.
Bayramoglu, Enis ; Andersen, Nils Axel ; Poulsen, Niels Kjølstad ; Andersen, Jens Christian ; Ravn, Ole. / Mobile Robot Navigation in a Corridor Using Visual Odometry. Prooceedings of the 14th International Conference on Advanced Robotics. IEEE, 2009. pp. 58
@inproceedings{755dfd7b5c7b4207b1ab6ec86a247487,
title = "Mobile Robot Navigation in a Corridor Using Visual Odometry",
abstract = "Incorporation of computer vision into mobile robot localization is studied in this work. It includes the generation of localization information from raw images and its fusion with the odometric pose estimation. The technique is then implemented on a small mobile robot operating at a corridor environment. A new segmented Hough transform with an improved way of discretization is used for image line extraction. The vanishing point concept is then incorporated to classify lines as well as to estimate the orientation. A method involving the iterative elimination of the outliers is employed to find both the vanishing point and the camera position. The fusion between the vision based pose estimation and the odometry is achieved with an extended Kalman filter. A distance driven error model is used for the odometry while a simple error model with constant noise is assumed for the vision. An extended Kalman filter as a parameter estimator is also applied to estimate odometry parameters. Experimental results are included. The robustness and the precision of the entire system is illustrated by performing simple navigation tasks.",
keywords = "Line Extraction, Vision, Sensor Fusion, Localization, Navigation, Mobile Robot",
author = "Enis Bayramoglu and Andersen, {Nils Axel} and Poulsen, {Niels Kj{\o}lstad} and Andersen, {Jens Christian} and Ole Ravn",
note = "Copyright: 2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE",
year = "2009",
language = "English",
isbn = "978-1-4244-4855-5",
pages = "58",
booktitle = "Prooceedings of the 14th International Conference on Advanced Robotics",
publisher = "IEEE",
address = "United States",

}

Bayramoglu, E, Andersen, NA, Poulsen, NK, Andersen, JC & Ravn, O 2009, Mobile Robot Navigation in a Corridor Using Visual Odometry. in Prooceedings of the 14th International Conference on Advanced Robotics. IEEE, pp. 58, International Conference on Advanced Robotics, Munich, Germany, 01/01/2009.

Mobile Robot Navigation in a Corridor Using Visual Odometry. / Bayramoglu, Enis; Andersen, Nils Axel; Poulsen, Niels Kjølstad; Andersen, Jens Christian; Ravn, Ole.

Prooceedings of the 14th International Conference on Advanced Robotics. IEEE, 2009. p. 58.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Mobile Robot Navigation in a Corridor Using Visual Odometry

AU - Bayramoglu, Enis

AU - Andersen, Nils Axel

AU - Poulsen, Niels Kjølstad

AU - Andersen, Jens Christian

AU - Ravn, Ole

N1 - Copyright: 2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

PY - 2009

Y1 - 2009

N2 - Incorporation of computer vision into mobile robot localization is studied in this work. It includes the generation of localization information from raw images and its fusion with the odometric pose estimation. The technique is then implemented on a small mobile robot operating at a corridor environment. A new segmented Hough transform with an improved way of discretization is used for image line extraction. The vanishing point concept is then incorporated to classify lines as well as to estimate the orientation. A method involving the iterative elimination of the outliers is employed to find both the vanishing point and the camera position. The fusion between the vision based pose estimation and the odometry is achieved with an extended Kalman filter. A distance driven error model is used for the odometry while a simple error model with constant noise is assumed for the vision. An extended Kalman filter as a parameter estimator is also applied to estimate odometry parameters. Experimental results are included. The robustness and the precision of the entire system is illustrated by performing simple navigation tasks.

AB - Incorporation of computer vision into mobile robot localization is studied in this work. It includes the generation of localization information from raw images and its fusion with the odometric pose estimation. The technique is then implemented on a small mobile robot operating at a corridor environment. A new segmented Hough transform with an improved way of discretization is used for image line extraction. The vanishing point concept is then incorporated to classify lines as well as to estimate the orientation. A method involving the iterative elimination of the outliers is employed to find both the vanishing point and the camera position. The fusion between the vision based pose estimation and the odometry is achieved with an extended Kalman filter. A distance driven error model is used for the odometry while a simple error model with constant noise is assumed for the vision. An extended Kalman filter as a parameter estimator is also applied to estimate odometry parameters. Experimental results are included. The robustness and the precision of the entire system is illustrated by performing simple navigation tasks.

KW - Line Extraction

KW - Vision

KW - Sensor Fusion

KW - Localization

KW - Navigation

KW - Mobile Robot

M3 - Article in proceedings

SN - 978-1-4244-4855-5

SP - 58

BT - Prooceedings of the 14th International Conference on Advanced Robotics

PB - IEEE

ER -

Bayramoglu E, Andersen NA, Poulsen NK, Andersen JC, Ravn O. Mobile Robot Navigation in a Corridor Using Visual Odometry. In Prooceedings of the 14th International Conference on Advanced Robotics. IEEE. 2009. p. 58