Rudolph Triebel, Óscar Martínez Mozos, Wolfram Burgard.
Relational Learning in Mobile Robotics: An Application to Semantic Labeling of Objects in 2D and 3D Environment Maps.
Studies in Classification, Data Analysis, and Knowledge Organization.
C. Preisach, H. Burkhardt, L. Schmidt-Thieme, R. Decker (Editors).
Springer-Verlag, 2008.
pp. 293--300. ISBN: 978-3-540-78239-1. e-ISBN: 978-3-540-78246-9.

Abstract

In this paper, we present an algorithm to identify types of places and objects from 2D and 3D laser range data obtained in indoor environments. Our approach is a combination of a collective classication method based on associative Markov networks together with an instance-based feature extraction using nearest neighbor. Additionally, we show how to select the best features needed to represent the objects and places, reducing the time needed for the learning and inference steps while maintaining high classication rates. Experimental results in real data demonstrate the eectiveness of our approach in indoor environments.

Draft: [pdf: 155k]

Bibtex

@Inbook{triebel2007gfkl_b,
	title = {Studies in Classification, Data Analysis, and Knowledge Organization},
	chapter   =  {Relational Learning in Mobile Robotics: An Application to Semantic Labeling of Objects in {2D} and {3D} Environment Maps},
	author  =  {Triebel, R. and Mozos, O.M. and Burgard, W.},
	editor = {C. Preisach, H. Burkhardt, L.Schmidt-Thieme, R.Decker},
	year= {2008},
	publisher = {Springer-Verlag},
	pages = {293--300}
}