Efficient off-road localization using visually corrected odometry

Matthew Grimes, Yann LeCun

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

Abstract

We describe an efficient, low-cost, low-overhead system for robot localization in complex visual environments. Our system augments wheel odometry with visual orientation tracking to yield localization accuracy comparable with "pure" visual odometry at a fraction of the cost. Such a system is well-suited to consumer-level robots, small form-factor robots, extraterrestrial rovers, and other platforms with limited computational resources. Our system also benefits high-end multiprocessor robots by leaving ample processor time on all cameracomputer pairs to perform other critical visual tasks, such as obstacle detection. Experimental results are shown for outdoor, off-road loops on the order of 200 meters. Comparisons are made with corresponding results from a state-of-the-art pure visual odometer.

Original languageEnglish (US)
Title of host publication2009 IEEE International Conference on Robotics and Automation, ICRA '09
Pages2649-2654
Number of pages6
DOIs
StatePublished - 2009
Event2009 IEEE International Conference on Robotics and Automation, ICRA '09 - Kobe, Japan
Duration: May 12 2009May 17 2009

Other

Other2009 IEEE International Conference on Robotics and Automation, ICRA '09
CountryJapan
CityKobe
Period5/12/095/17/09

Fingerprint

Robots
Costs
Wheels

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Grimes, M., & LeCun, Y. (2009). Efficient off-road localization using visually corrected odometry. In 2009 IEEE International Conference on Robotics and Automation, ICRA '09 (pp. 2649-2654). [5152880] https://doi.org/10.1109/ROBOT.2009.5152880

Efficient off-road localization using visually corrected odometry. / Grimes, Matthew; LeCun, Yann.

2009 IEEE International Conference on Robotics and Automation, ICRA '09. 2009. p. 2649-2654 5152880.

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

Grimes, M & LeCun, Y 2009, Efficient off-road localization using visually corrected odometry. in 2009 IEEE International Conference on Robotics and Automation, ICRA '09., 5152880, pp. 2649-2654, 2009 IEEE International Conference on Robotics and Automation, ICRA '09, Kobe, Japan, 5/12/09. https://doi.org/10.1109/ROBOT.2009.5152880
Grimes M, LeCun Y. Efficient off-road localization using visually corrected odometry. In 2009 IEEE International Conference on Robotics and Automation, ICRA '09. 2009. p. 2649-2654. 5152880 https://doi.org/10.1109/ROBOT.2009.5152880
Grimes, Matthew ; LeCun, Yann. / Efficient off-road localization using visually corrected odometry. 2009 IEEE International Conference on Robotics and Automation, ICRA '09. 2009. pp. 2649-2654
@inproceedings{cd90d8543af04513ba2be1f19ee34a98,
title = "Efficient off-road localization using visually corrected odometry",
abstract = "We describe an efficient, low-cost, low-overhead system for robot localization in complex visual environments. Our system augments wheel odometry with visual orientation tracking to yield localization accuracy comparable with {"}pure{"} visual odometry at a fraction of the cost. Such a system is well-suited to consumer-level robots, small form-factor robots, extraterrestrial rovers, and other platforms with limited computational resources. Our system also benefits high-end multiprocessor robots by leaving ample processor time on all cameracomputer pairs to perform other critical visual tasks, such as obstacle detection. Experimental results are shown for outdoor, off-road loops on the order of 200 meters. Comparisons are made with corresponding results from a state-of-the-art pure visual odometer.",
author = "Matthew Grimes and Yann LeCun",
year = "2009",
doi = "10.1109/ROBOT.2009.5152880",
language = "English (US)",
isbn = "9781424427895",
pages = "2649--2654",
booktitle = "2009 IEEE International Conference on Robotics and Automation, ICRA '09",

}

TY - GEN

T1 - Efficient off-road localization using visually corrected odometry

AU - Grimes, Matthew

AU - LeCun, Yann

PY - 2009

Y1 - 2009

N2 - We describe an efficient, low-cost, low-overhead system for robot localization in complex visual environments. Our system augments wheel odometry with visual orientation tracking to yield localization accuracy comparable with "pure" visual odometry at a fraction of the cost. Such a system is well-suited to consumer-level robots, small form-factor robots, extraterrestrial rovers, and other platforms with limited computational resources. Our system also benefits high-end multiprocessor robots by leaving ample processor time on all cameracomputer pairs to perform other critical visual tasks, such as obstacle detection. Experimental results are shown for outdoor, off-road loops on the order of 200 meters. Comparisons are made with corresponding results from a state-of-the-art pure visual odometer.

AB - We describe an efficient, low-cost, low-overhead system for robot localization in complex visual environments. Our system augments wheel odometry with visual orientation tracking to yield localization accuracy comparable with "pure" visual odometry at a fraction of the cost. Such a system is well-suited to consumer-level robots, small form-factor robots, extraterrestrial rovers, and other platforms with limited computational resources. Our system also benefits high-end multiprocessor robots by leaving ample processor time on all cameracomputer pairs to perform other critical visual tasks, such as obstacle detection. Experimental results are shown for outdoor, off-road loops on the order of 200 meters. Comparisons are made with corresponding results from a state-of-the-art pure visual odometer.

UR - http://www.scopus.com/inward/record.url?scp=70350417114&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350417114&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.2009.5152880

DO - 10.1109/ROBOT.2009.5152880

M3 - Conference contribution

AN - SCOPUS:70350417114

SN - 9781424427895

SP - 2649

EP - 2654

BT - 2009 IEEE International Conference on Robotics and Automation, ICRA '09

ER -