W. Burgard, D. Fox, and S. Thrun
Active Mobile Robot Localization
Proc. of the Fifteenth International JointConference
on Artificial Intelligence (IJCAI'97)
Abstract
Localization is the problem of determining the position of a mobile robot
from sensor data. Most existing localization approaches are passive, i.e.,
they do not exploit the opportunity to control the robot's effectors during
localization. This paper proposes an active localization approach.
The approach provides rational criteria for (1) setting the robot's motion
direction (exploration),and (2) determining the pointing direction of the
sensors so as to most efficiently localize the robot. Furthermore,
it isable to deal with noisy sensors and approximative world models.
The appropriatenessof our approach is demonstrated empirically using an RWI
B21 mobile robotin a structured office environment.
An updated and extended version of this paper can be found in:
ActiveMarkov Localization for Mobile Robots.
Download
Full paper
[.ps.gz](190 kb, 7 pages)
Bibtex
@INPROCEEDINGS{Bur97Act,
AUTHOR = {Burgard, W. and Fox, D. and Thrun, S.},
TITLE = {Active Mobile Robot Localization},
BOOKTITLE = {Proc.~of the International JointConference on Artificial
Intelligence},
YEAR = {1997}
}