Let it Learn - A Curious Vision System for Autonomous Object Learning

Pramod Chandrashekhariah, Gabriele Spina, Jochen Triesch

2013

Abstract

We present a “curious” active vision system for a humanoid robot that autonomously explores its environment and learns object representations without any human assistance. Similar to an infant, who is intrinsically motivated to seek out new information, our system is endowed with an attention and learning mechanism designed to search for new information that has not been learned yet. Our method can deal with dynamic changes of object appearance which are incorporated into the object models. Our experiments demonstrate improved learning speed and accuracy through curiosity-driven learning.

Paper Citation

in Harvard Style

Chandrashekhariah P., Spina G. and Triesch J. (2013). Let it Learn - A Curious Vision System for Autonomous Object Learning . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-48-8, pages 169-176. DOI: 10.5220/0004294101690176

in Bibtex Style

@conference{visapp13,
author={Pramod Chandrashekhariah and Gabriele Spina and Jochen Triesch},
title={Let it Learn - A Curious Vision System for Autonomous Object Learning},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={169-176},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004294101690176},
isbn={978-989-8565-48-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)
TI - Let it Learn - A Curious Vision System for Autonomous Object Learning
SN - 978-989-8565-48-8
AU - Chandrashekhariah P.
AU - Spina G.
AU - Triesch J.
PY - 2013
SP - 169
EP - 176
DO - 10.5220/0004294101690176