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.

References

  1. Agarwal, S. and Roth, D. (2002). Learning a sparse representation for object detection. In Proceedings of the 7th European Conference on Computer VisionPart IV, ECCV 7802, pages 113-130, London, UK, UK. Springer-Verlag.
  2. Baldassarre, G. (2011). What are intrinsic motivations? a biological perspective. In Development and Learning (ICDL), 2011 IEEE International Conference on, volume 2, pages 1 -8.
  3. Ballard, D. H. (1987). Readings in computer vision: issues, problems, principles, and paradigms. chapter Generalizing the hough transform to detect arbitrary shapes, pages 714-725. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA.
  4. Baranes, A. and Oudeyer, P.-Y. (2009). R-iac: Robust intrinsically motivated exploration and active learning. Autonomous Mental Development, IEEE Transactions on, 1(3):155 -169.
  5. Begum, M. and Karray, F. (2011). Visual attention for robotic cognition: A survey. Autonomous Mental Development, IEEE Transactions on, 3(1):92 -105.
  6. Figueira, D., Lopes, M., Ventura, R., and Ruesch, J. (2009). From pixels to objects: Enabling a spatial model for humanoid social robots. In Robotics and Automation, 2009. ICRA 2009. IEEE International Conference on, pages 3049 -3054.
  7. Gatsoulis, Y., Burbridge, C., and Mcginnity, T. (2011). Online unsupervised cumulative learning for life-long robot operation. In Robotics and Biomimetics (ROBIO), 2011 IEEE International Conference on, pages 2486 -2490.
  8. Harris, C. and Stephens, M. (1988). A combined corner and edge detector. In In Proc. of Fourth Alvey Vision Conference, pages 147-151.
  9. Itti, L. and Koch, C. (2001). Computational modelling of visual attention. Nature Reviews Neuroscience, 2(3):194-203.
  10. Jones, J. and Palmer, L. (1987). An evaluation of the two-dimensional gabor filter model of simple receptive fields in cat striate cortex. J. of Neurophysiology, 58(6):1233 -58.
  11. Kim, H., Murphy-Chutorian, E., and Triesch, J. (2006). Semi-autonomous learning of objects. In Computer Vision and Pattern Recognition Workshop, 2006. CVPRW 7806. Conference on, page 145.
  12. Metta, G., Sandini, G., Vernon, D., Natale, L., and Nori, F. (2008). The icub humanoid robot: an open platform for research in embodied cognition. In Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems, PerMIS 7808, pages 50-56, New York, NY, USA. ACM.
  13. Murphy-Chutorian, E. and Triesch, J. (2005). Shared features for scalable appearance-based object recognition. In Application of Computer Vision, 2005. WACV/MOTIONS 7805 Volume 1. Seventh IEEE Workshops on, volume 1, pages 16 -21.
  14. Schmidhuber, J. (2010). Formal theory of creativity, fun, and intrinsic motivation (1990-2010). Autonomous Mental Development, IEEE Transactions on, 2(3):230 -247.
  15. Triesch, J. and Malsburg, C. V. D. (2001). Democratic integration: Self-organized integration of adaptive cues.
  16. Wang, Q., Chandrashekhariah, P., and Spina, G. (2011). Familiarity-to-novelty shift driven by learning: A conceptual and computational model. In Development and Learning (ICDL), 2011 IEEE International Conference on, volume 2, pages 1 -6.
  17. Wersing, H., Kirstein, S., Gtting, M., Brandl, H., Dunn, M., Mikhailova, I., Goerick, C., Steil, J., Ritter, H., and Krner, E. (2007). Online learning of objects in a biologically motivated visual architecture.
  18. Wiskott, L., Fellous, J.-M., Kuiger, N., and von der Malsburg, C. (1997). Face recognition by elastic bunch graph matching. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 19(7):775 -779.
Download


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