A. Rottmann, O. Martinez Mozos, C. Stachniss and W. Burgard
Semantic Place Classification of Indoor Environments with Mobile Robots using Boosting
Proc. of the National
Conference on Artificial Intelligence (AAAI)
Abstract
Indoor environments can typically be divided into places with
different functionalities like kitchens, offices, or seminar rooms. We believe
that such semantic information enables a mobile robot to more efficiently
accomplish a variety of tasks such as human-robot interaction, path-planning,
or localization. This paper presents a supervised learning approach to label
different locations using boosting. We train a classifier using features
extracted from vision and laser range data. Furthermore, we apply a Hidden
Markov Model to increase the robustness of the final classification. Our
technique has been implemented and tested on real robots as well as in
simulation. The experiments demonstrate that our approach can be utilized to
robustly classify places into semantic categories. We also present an example
of localization using semantic labeling.
Download
Full paper [.pdf]
(940 KB)
Bibtex
@string{aaai = "Proc.~of the National Conference on Artificial Intelligence"}
@InProceedings{rottmann05aaai,
TITLE = {Place Classification of Indoor Environments with Mobile Robots using Boosting},
AUTHOR = {Rottmann, A. and Mart\'{i}nez Mozos, O. and Stachniss, C. and Burgard, W.},
BOOKTITLE = aaai,
YEAR = {2005},
ADDRESS = {Pittsburgh, PA, USA},
}