D. Fox, W. Burgard, and S. Thrun
Probabilistic Methods for Mobile
Robot Mapping
Proc. of the IJCAI-99 Workshop on Adaptive SpatialRepresentations
of Dynamic Environments
Abstract
The problem of map building is the problem of determining the location
of entities-of-interest in a global frame of reference. Over the last years,
probabilistic methods have shown to be well suited for dealing with theuncertainties
involved in mobile robot map building. In this paper we introducea general
probabilistic approach to concurrent mapping and localization.This method
poses the mapping problem as a statistical maximum likelihoodproblem, and
devises an efficient algorithm for search in likelihood space. We furthermore
address the problem of using occupancy grid maps for pathplanning in highly
dynamic environments. The approaches have been testedextensively and several
experimental results are given in the paper.
Download
Full paper
[.ps.gz](1241 kb, 10 pages)
Bibtex
@TECHREPORT{Fox99Mul,
AUTHOR = {Fox, D. and Burgard, W. and Thrun, S.},
TITLE = {Probabilistic Methods for Mobile Robot Mapping},
YEAR = {1999},
BOOKTITLE = {Proc.~of the IJCAI-99 Workshopon Adaptive Spatial Representations
of Dynamic Environments},
NOTE = {Invited presentation}
}