Using visual features to build topological maps of indoor environments

Paul E. Rybski, Franziska Zacharias, Jean Francois Lett, Osama Masoud, Maria Gini, Nikolaos Papanikolopoulos

Research output: Contribution to journalConference article

23 Citations (Scopus)

Abstract

This paper addresses the problem of localization and map construction by a mobile robot in an indoor environment. Instead of trying to build high-fidelity geometric maps, we focus on constructing topological maps as they are less sensitive to poor odometry estimates and position errors. We propose a method for incrementally building topological maps for a robot which uses a panoramic camera to obtain images at various locations along its path and uses the features it tracks in the images to update the topological map. The method is very general and does not require the environment to have uniquely distinctive features.

Original languageEnglish (US)
Pages (from-to)850-855
Number of pages6
JournalProceedings - IEEE International Conference on Robotics and Automation
Volume1
StatePublished - Dec 9 2003
Event2003 IEEE International Conference on Robotics and Automation - Taipei, Taiwan, Province of China
Duration: Sep 14 2003Sep 19 2003

Fingerprint

Mobile robots
Cameras
Robots

Cite this

Using visual features to build topological maps of indoor environments. / Rybski, Paul E.; Zacharias, Franziska; Lett, Jean Francois; Masoud, Osama; Gini, Maria; Papanikolopoulos, Nikolaos.

In: Proceedings - IEEE International Conference on Robotics and Automation, Vol. 1, 09.12.2003, p. 850-855.

Research output: Contribution to journalConference article

@article{d779f5504ca1464b9b6c1efb0f002508,
title = "Using visual features to build topological maps of indoor environments",
abstract = "This paper addresses the problem of localization and map construction by a mobile robot in an indoor environment. Instead of trying to build high-fidelity geometric maps, we focus on constructing topological maps as they are less sensitive to poor odometry estimates and position errors. We propose a method for incrementally building topological maps for a robot which uses a panoramic camera to obtain images at various locations along its path and uses the features it tracks in the images to update the topological map. The method is very general and does not require the environment to have uniquely distinctive features.",
author = "Rybski, {Paul E.} and Franziska Zacharias and Lett, {Jean Francois} and Osama Masoud and Maria Gini and Nikolaos Papanikolopoulos",
year = "2003",
month = "12",
day = "9",
language = "English (US)",
volume = "1",
pages = "850--855",
journal = "Proceedings - IEEE International Conference on Robotics and Automation",
issn = "1050-4729",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Using visual features to build topological maps of indoor environments

AU - Rybski, Paul E.

AU - Zacharias, Franziska

AU - Lett, Jean Francois

AU - Masoud, Osama

AU - Gini, Maria

AU - Papanikolopoulos, Nikolaos

PY - 2003/12/9

Y1 - 2003/12/9

N2 - This paper addresses the problem of localization and map construction by a mobile robot in an indoor environment. Instead of trying to build high-fidelity geometric maps, we focus on constructing topological maps as they are less sensitive to poor odometry estimates and position errors. We propose a method for incrementally building topological maps for a robot which uses a panoramic camera to obtain images at various locations along its path and uses the features it tracks in the images to update the topological map. The method is very general and does not require the environment to have uniquely distinctive features.

AB - This paper addresses the problem of localization and map construction by a mobile robot in an indoor environment. Instead of trying to build high-fidelity geometric maps, we focus on constructing topological maps as they are less sensitive to poor odometry estimates and position errors. We propose a method for incrementally building topological maps for a robot which uses a panoramic camera to obtain images at various locations along its path and uses the features it tracks in the images to update the topological map. The method is very general and does not require the environment to have uniquely distinctive features.

UR - http://www.scopus.com/inward/record.url?scp=0344444738&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0344444738&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0344444738

VL - 1

SP - 850

EP - 855

JO - Proceedings - IEEE International Conference on Robotics and Automation

JF - Proceedings - IEEE International Conference on Robotics and Automation

SN - 1050-4729

ER -