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.
Paper: [pdf: 920k]
Bibtex
@InProceedings{rottmann05aaai,
title = {Semantic Place Classification of Indoor Environments with Mobile Robots using Boosting.},
author = {Axel Rottmann and Oscar Martinez Mozos and Cyrill Stachniss and Wolfram Burgard},
booktitle = {Proceedings of the National Conference on Artificial Intelligence},
year = {2005},
address = {Pittsburgh, PA, USA},
pages = {1306--1311},
url = {http://www.informatik.uni-freiburg.de/~omartine/publications/rottmann2005aaai.pdf}
}
Multimedia
Online classification with a mobile robot.
See how places are classified and colored as the robot moves.
Colors: doorway(blue),
corridor(red),
lab(magenta),
office(cyan),
kitchen(green),
seminar(yellow),
Video; [avi: 470k].