Real-Time Vision-Based Robot Localization

Sami Atiya; Gregory D. Hager

doi:10.1109/70.265922

Real-Time Vision-Based Robot Localization

Sami Atiya
, Gregory D. Hager

Research output: Contribution to journal › Article › peer-review

132 Scopus citations

Abstract

This paper describes an algorithm for determining robot location from visual landmarks. This algorithm determines both the correspondence between observed landmarks (in this case vertical edges in the environment) and a stored map, and computes the location of the robot using those correspondences. The primary advantages of this algorithm are its use of a single geometric tolerance to describe observation error, its ability to recognize ambiguous sets of correspondences, its ability to compute bounds on the error in localization, and fast execution. The algorithm has been implemented and tested on a mobile robot system. In several hundred trials it has never failed, and computes location accurate to within a centimeter in less than 0.5 s.

Original language	English (US)
Pages (from-to)	785-800
Number of pages	16
Journal	IEEE Transactions on Robotics and Automation
Volume	9
Issue number	6
DOIs	https://doi.org/10.1109/70.265922
State	Published - Dec 1993
Externally published	Yes

ASJC Scopus subject areas

Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/70.265922

Cite this

@article{1010415eec884ed4a28a63ac68ca0188,

title = "Real-Time Vision-Based Robot Localization",

abstract = "This paper describes an algorithm for determining robot location from visual landmarks. This algorithm determines both the correspondence between observed landmarks (in this case vertical edges in the environment) and a stored map, and computes the location of the robot using those correspondences. The primary advantages of this algorithm are its use of a single geometric tolerance to describe observation error, its ability to recognize ambiguous sets of correspondences, its ability to compute bounds on the error in localization, and fast execution. The algorithm has been implemented and tested on a mobile robot system. In several hundred trials it has never failed, and computes location accurate to within a centimeter in less than 0.5 s.",

author = "Sami Atiya and Hager, \{Gregory D.\}",

note = "Funding Information: Manuscript received September 30, 1991; revised January 21, 1993. S. Atiya was supported by the Deutsche Forschungsgemeinschaft as part of a cooperative research project on artificial intelligence (Sonderforschungber-eich Kunstliche Intelligenz). G. Hager was supported by a Fulbright Junior Research Grant. This work was also supported in part by the Office of Naval Research under DARPA Grant N0014-88-K-0630, by DARPA Grant N00014-91-3-1577, by the Air Force Office of Scientific Research under Grants 88-0244 and 88-0296, by ArmyiDAAL Grant 03-89-C-003 lPRI, by the National Science Foundation under Grants CISE/CDA 88-22719 and IRI 89-06770, by Yale University, and by the DuPont Corporation. S. Atiya is with the Institut fur Algorithmen und Kognitive Systeme, Universitat Karlsruhe (TH) and the Fraunhofer-Institute fur Informations-und Datenverarbeitung, D-7500 Karlsruhe 1, Germany. G. D. Hager was with the Institut fur Algorithmen und Kognitive Sys- teme, Universitat Karlsruhe (TH), D-7500 Karlsruhe I, Germany. He is now with the Department of Computer Science, Yale University, New Haven, CT 06520. IEEE Log Number 9212597.",

year = "1993",

month = dec,

doi = "10.1109/70.265922",

language = "English (US)",

volume = "9",

pages = "785--800",

journal = "IEEE Transactions on Robotics and Automation",

issn = "1042-296X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "6",

}

TY - JOUR

T1 - Real-Time Vision-Based Robot Localization

AU - Atiya, Sami

AU - Hager, Gregory D.

N1 - Funding Information: Manuscript received September 30, 1991; revised January 21, 1993. S. Atiya was supported by the Deutsche Forschungsgemeinschaft as part of a cooperative research project on artificial intelligence (Sonderforschungber-eich Kunstliche Intelligenz). G. Hager was supported by a Fulbright Junior Research Grant. This work was also supported in part by the Office of Naval Research under DARPA Grant N0014-88-K-0630, by DARPA Grant N00014-91-3-1577, by the Air Force Office of Scientific Research under Grants 88-0244 and 88-0296, by ArmyiDAAL Grant 03-89-C-003 lPRI, by the National Science Foundation under Grants CISE/CDA 88-22719 and IRI 89-06770, by Yale University, and by the DuPont Corporation. S. Atiya is with the Institut fur Algorithmen und Kognitive Systeme, Universitat Karlsruhe (TH) and the Fraunhofer-Institute fur Informations-und Datenverarbeitung, D-7500 Karlsruhe 1, Germany. G. D. Hager was with the Institut fur Algorithmen und Kognitive Sys- teme, Universitat Karlsruhe (TH), D-7500 Karlsruhe I, Germany. He is now with the Department of Computer Science, Yale University, New Haven, CT 06520. IEEE Log Number 9212597.

PY - 1993/12

Y1 - 1993/12

N2 - This paper describes an algorithm for determining robot location from visual landmarks. This algorithm determines both the correspondence between observed landmarks (in this case vertical edges in the environment) and a stored map, and computes the location of the robot using those correspondences. The primary advantages of this algorithm are its use of a single geometric tolerance to describe observation error, its ability to recognize ambiguous sets of correspondences, its ability to compute bounds on the error in localization, and fast execution. The algorithm has been implemented and tested on a mobile robot system. In several hundred trials it has never failed, and computes location accurate to within a centimeter in less than 0.5 s.

AB - This paper describes an algorithm for determining robot location from visual landmarks. This algorithm determines both the correspondence between observed landmarks (in this case vertical edges in the environment) and a stored map, and computes the location of the robot using those correspondences. The primary advantages of this algorithm are its use of a single geometric tolerance to describe observation error, its ability to recognize ambiguous sets of correspondences, its ability to compute bounds on the error in localization, and fast execution. The algorithm has been implemented and tested on a mobile robot system. In several hundred trials it has never failed, and computes location accurate to within a centimeter in less than 0.5 s.

UR - https://www.scopus.com/pages/publications/0027887666

UR - https://www.scopus.com/pages/publications/0027887666#tab=citedBy

U2 - 10.1109/70.265922

DO - 10.1109/70.265922

M3 - Article

AN - SCOPUS:0027887666

SN - 1042-296X

VL - 9

SP - 785

EP - 800

JO - IEEE Transactions on Robotics and Automation

JF - IEEE Transactions on Robotics and Automation

IS - 6

ER -

Real-Time Vision-Based Robot Localization

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this