Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Classifying Dynamic Objects: An Unsupervised Learning Approach

Summary: Classifying Dynamic Objects:
An Unsupervised Learning Approach
Matthias Luber Kai O. Arras Christian Plagemann Wolfram Burgard
Albert-Ludwigs-University Freiburg, Department for Computer Science, 79110 Freiburg, Germany
{luber, arras, plagem, burgard}@informatik.uni-freiburg.de
Abstract-- For robots operating in real-world envi-
ronments, the ability to deal with dynamic entities
such as humans, animals, vehicles, or other robots is
of fundamental importance. The variability of dynamic
objects, however, is large in general, which makes
it hard to manually design suitable models for their
appearance and dynamics. In this paper, we present an
unsupervised learning approach to this model-building
problem. We describe an exemplar-based model for
representing the time-varying appearance of objects
in planar laser scans as well as a clustering procedure
that builds a set of object classes from given training
sequences. Extensive experiments in real environments
demonstrate that our system is able to autonomously
learn useful models for, e.g., pedestrians, skaters, or


Source: Arras, Kai O. - Institut für Informatik, Albert-Ludwigs-Universität Freiburg


Collections: Computer Technologies and Information Sciences