Robotics: Science and Systems IV

Classifying Dynamic Objects: An Unsupervised Learning Approach

Matthias Luber, Kai Arras, Christian Plagemann, Wolfram Burgard

Abstract: For robots operating in real-world environments, 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 a non-parametric 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 learn and classify models for, e.g., pedestrians, skaters, or cyclists, without any a priori information.

Download:

Bibtex:

@INPROCEEDINGS{Luber-RSS08,
    AUTHOR    = {Matthias Luber, Kai O. Arras, Christian Plagemann, Wolfram Burgard},
    TITLE     = {Classifying Dynamic Objects: An Unsupervised Learning Approach},
    BOOKTITLE = {Proceedings of Robotics: Science and Systems IV},
    YEAR      = {2008},
    ADDRESS   = {Zurich, Switzerland},
    MONTH     = {June},
    DOI       = {10.15607/RSS.2008.IV.035} 
}