W. Burgard, D. Fox, H. Jans, C. Matenar, and S. Thrun
Sonar-Based Mapping with Mobile
Robots Using EM
Proc. of the 16th International Conference on Machine
Learning (ICML'99)
Abstract
In this paper we present a method for learning maps with mobile robots equipped
with range finders. Our method builds on an approach previously developed
by the authors, which uses EM to solve the concurrent mapping and localization
problem (constrained maximum likelihood estimation). In contrast to other
techniques which either relied on predefined landmarks or used highly accurate
sensors, our approach is able to fully exploit the rich nature of range data
and to deal with noisy information coming,for example, from ultrasound sensors.
During EM it uses a layered representationof maps. It operates in two stages:
first, small, local maps are learned under the assumption that odometry is
locally correct. EM is then applied to to estimate the positions of these
local maps. Finally, the local mapsare integrated into one global map using
Bayes rule. Experimental results demonstrate that our approach is well suited
for constructing large mapsof typical indoor environments using sensors as
inaccurate as sonars.
Download
Full paper
[.ps.gz](1023 kb)
Bibtex
@INPROCEEDINGS{Bur99Son,
AUTHOR = {Burgard,W. andFox, D. and Jans, H. and Matenar,
C. and Thrun, S.},
TITLE = {Sonar-Based Mapping with Mobile Robots Using
{EM}},
YEAR = {1999},
BOOKTITLE = Proc.~of the InternationalConferenceon Machine Learning
}