Real-time vision-based robot localization

Sami Aitya; Greg Hager

Real-time vision-based robot localization

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

An algorithm for robot localization using visual landmarks is described. This algorithm determines both the correspondence between observed landmarks (in this case vertical edges in the environment) and a preloaded map, and the location of the robot from 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 its fast execution. The current version of the algorithm has been implemented and tested on a mobile robot system. In several hundred trials the algorithm has not failed, and computes location accurate to within a centimeter in less than half a second.

Original language	English (US)
Title of host publication	Proceedings - IEEE International Conference on Robotics and Automation
Publisher	Publ by IEEE
Pages	639-644
Number of pages	6
ISBN (Print)	081862163X
State	Published - Jan 1 1991
Externally published	Yes
Event	Proceedings of the 1991 IEEE International Conference on Robotics and Automation - Sacramento, CA, USA Duration: Apr 9 1991 → Apr 11 1991

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation
Volume	1

Other

Other	Proceedings of the 1991 IEEE International Conference on Robotics and Automation
City	Sacramento, CA, USA
Period	4/9/91 → 4/11/91

ASJC Scopus subject areas

Software
Control and Systems Engineering
Artificial Intelligence
Electrical and Electronic Engineering

Cite this

@inproceedings{1f8f4733adae4ffb89679101aa88c699,

title = "Real-time vision-based robot localization",

abstract = "An algorithm for robot localization using visual landmarks is described. This algorithm determines both the correspondence between observed landmarks (in this case vertical edges in the environment) and a preloaded map, and the location of the robot from 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 its fast execution. The current version of the algorithm has been implemented and tested on a mobile robot system. In several hundred trials the algorithm has not failed, and computes location accurate to within a centimeter in less than half a second.",

author = "Sami Aitya and Greg Hager",

year = "1991",

month = jan,

day = "1",

language = "English (US)",

isbn = "081862163X",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

publisher = "Publ by IEEE",

pages = "639--644",

booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

note = "Proceedings of the 1991 IEEE International Conference on Robotics and Automation ; Conference date: 09-04-1991 Through 11-04-1991",

}

TY - GEN

T1 - Real-time vision-based robot localization

AU - Aitya, Sami

AU - Hager, Greg

PY - 1991/1/1

Y1 - 1991/1/1

N2 - An algorithm for robot localization using visual landmarks is described. This algorithm determines both the correspondence between observed landmarks (in this case vertical edges in the environment) and a preloaded map, and the location of the robot from 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 its fast execution. The current version of the algorithm has been implemented and tested on a mobile robot system. In several hundred trials the algorithm has not failed, and computes location accurate to within a centimeter in less than half a second.

AB - An algorithm for robot localization using visual landmarks is described. This algorithm determines both the correspondence between observed landmarks (in this case vertical edges in the environment) and a preloaded map, and the location of the robot from 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 its fast execution. The current version of the algorithm has been implemented and tested on a mobile robot system. In several hundred trials the algorithm has not failed, and computes location accurate to within a centimeter in less than half a second.

UR - http://www.scopus.com/inward/record.url?scp=0025754476&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025754476&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0025754476

SN - 081862163X

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 639

EP - 644

BT - Proceedings - IEEE International Conference on Robotics and Automation

PB - Publ by IEEE

T2 - Proceedings of the 1991 IEEE International Conference on Robotics and Automation

Y2 - 9 April 1991 through 11 April 1991

ER -

Real-time vision-based robot localization

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this