D. Fox, W. Burgard, S. Thrun, and A.B. Cremers
Position Estimation for Mobile
Robots in Dynamic Environments
Proc. of the Fifteenth National Conference on Artificial
Intelligence (AAAI-98)
Abstract
For mobile robots to be successful, they have to navigate safely in
populatedand dynamic environments. While recent research has led to
a variety oflocalization methods that can track robots well in {\em
static} environments,we still lack methods that can robustly localize
mobile robots in dynamicenvironments, where, for example, people may
block the robot's sensors forextensive periods of time. This
paper proposes a family of probabilistic algorithms that can localize
mobile robots even in densely populated environments.These algorithms
are based on Markov localization, which estimates the locationof a
robot probabilistically. A novel entropy-based filter is employed for
determining the "believability" of a sensor reading, thereby filtering
outsensor readings that are corrupted by humans or unexpected changes
in theenvironment. The technique was recently implemented and
applied as partof an installation, in which a mobile robot gave interactive
tours to visitorsof the ``Deutsches Museum Bonn.'' Extensive empirical
tests involving datasetsrecorded during peak traffic hours in the museum
demonstrate that this approachis able to accurately estimate the robot's
position in more than 99 % ofthe cases even in such highly dynamic
environments.
Download
Full paper
[.ps.gz](1046 kb, 6 pages)
Bibtex
@INPROCEEDINGS{Fox98Pos,
AUTHOR = {Fox, D. and Burgard, W. and Thrun, S. and
Cremers, A.B.},
TITLE = {Position Estimation for Mobile Robots in Dynamic
Environments},
YEAR = {1998},
BOOKTITLE = {Proc.~of the National Conferenceon Artificial Intelligence}
}