Advertisement

Action-Driven Perception for a Humanoid

  • Jens Kleesiek
  • Stephanie Badde
  • Stefan Wermter
  • Andreas K. Engel
Part of the Communications in Computer and Information Science book series (CCIS, volume 358)

Abstract

We present active object categorization experiments with a real humanoid robot. For this purpose, the training algorithm of a recurrent neural network with parametric bias has been extended with adaptive learning rates. This modification leads to an increase in training speed. Using this new training algorithm we conducted three experiments aiming at object categorization. While holding different objects in its hand, the robot executes a motor sequence that induces multi-modal sensory changes. During learning, these high-dimensional perceptions are ‘engraved’ in the network. Simultaneously, low-dimensional PB values emerge unsupervised. The geometrical relation of these PB vectors can then be exploited to infer relations between the original high dimensional time series characterizing different objects. Even sensations belonging to unknown objects can be discriminated from known (learned) ones and kept apart from each other reliably. Additionally, we show that the network tolerates noisy sensory signals very well.

Keywords

Active Perception RNNPB Humanoid Robot 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    O’Regan, J.K., Noë, A.: A sensorimotor account of vision and visual consciousness. Behav. Brain Sci. 24(5) (October 2001); 939–73; discussion 973–1031Google Scholar
  2. 2.
    Dill, M., Wolf, R., Heisenberg, M.: Visual pattern recognition in drosophila involves retinotopic matching. Nature 365(6448), 751–753 (1993)CrossRefGoogle Scholar
  3. 3.
    Franceschini, N.: Combined optical, neuroanatomical, electrophysiological and behavioral studies on signal processing in the fly compound eye. In: Taddei-Ferretti, C. (ed.) Biocybernetics of Vision: Integrative Mechanisms and Cognitive Processes: Proceedings of the International School of Biocybernetics, Casamicciola, Napoli, Italy, October 16-22, 1994, vol. 2, World Scientific, Singapore (1997)Google Scholar
  4. 4.
    Steinman, S.B., Steinman, B.A., Garzia, R.P.: Foundations of binocular vision: a clinical perspective. McGraw-Hill, New York (2000)Google Scholar
  5. 5.
    Pfeifer, R., Lungarella, M., Iida, F.: Self-organization, embodiment, and biologically inspired robotics. Science 318(5853), 1088–1093 (2007)CrossRefGoogle Scholar
  6. 6.
    Tani, J., Ito, M.: Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment. IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans 33(4), 481–488 (2003)CrossRefGoogle Scholar
  7. 7.
    Tani, J., Ito, M., Sugita, Y.: Self-organization of distributedly represented multiple behavior schemata in a mirror system: reviews of robot experiments using RNNPB. Neural Netw. 17(8-9), 1273–1289 (2004)CrossRefGoogle Scholar
  8. 8.
    Cuijpers, R.H., Stuijt, F., Sprinkhuizen-Kuyper, I.G.: Generalisation of action sequences in RNNPB networks with mirror properties. In: Proceedings of the 17th European symposium on Artifical Neural Networks (ESANN), pp. 251–256 (2009)Google Scholar
  9. 9.
    Kolen, J.F., Kremer, S.C.: A field guide to dynamical recurrent networks. IEEE Press, New York (2001)Google Scholar
  10. 10.
    Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In: IEEE International Conference on Neural Networks, vol. 1, pp. 586–591 (1993)Google Scholar
  11. 11.
    LeCun, Y.A., Bottou, L., Orr, G.B., Müller, K.-R.: Efficient BackProp. In: Orr, G.B., Müller, K.-R. (eds.) NIPS-WS 1996. LNCS, vol. 1524, pp. 9–50. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  12. 12.
    Bradski, G.: The OpenCV Library. Dr. Dobb’s Journal of Software Tools (2000)Google Scholar
  13. 13.
    Suzuki, S., Be, K.: Topological structural analysis of digitized binary images by border following. Computer Vision, Graphics, and Image Processing 30(1), 32–46 (1985)zbMATHCrossRefGoogle Scholar
  14. 14.
    Hu, M.K.: Visual pattern recognition by moment invariants. IRE Transactions on Information Theory 8(2), 179–187 (1962)zbMATHCrossRefGoogle Scholar
  15. 15.
    Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2, 27:1–27:27 (2011)CrossRefGoogle Scholar
  16. 16.
    Kleesiek, J., Badde, S., Wermter, S., Engel, A.K.: What do Objects Feel Like? Active Perception for a Humanoid Robot. In: Proceedings of the 4th International Conference on Agents and Artificial Intelligence (ICAART), vol. 1, pp. 64–73 (2012)Google Scholar
  17. 17.
    Meltzoff, A.N., Meltzoff, A.N., Moore, M.K.: Explaining facial imitation: a theoretical model. Early Development and Parenting 6, 179–192 (1997)CrossRefGoogle Scholar
  18. 18.
    Gibson, J.J.: The theory of affordances. In: Shaw, R., Bransford, J. (eds.) Perceiving, Acting, and Knowing: Toward an Ecological Psychology, pp. 67–82. Erlbaum, Hillsdale (1977)Google Scholar
  19. 19.
    Ogata, T., Ohba, H., Tani, J., Komatani, K., Okuno, H.G.: Extracting multi-modal dynamics of objects using RNNPB. In: Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, Edmonton, pp. 160–165 (2005)Google Scholar
  20. 20.
    Körding, K.P., Wolpert, D.M.: Bayesian integration in sensorimotor learning. Nature 427(6971), 244–247 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Jens Kleesiek
    • 1
    • 3
  • Stephanie Badde
    • 2
  • Stefan Wermter
    • 3
  • Andreas K. Engel
    • 1
  1. 1.Department of Neurophysiology and PathophysiologyUniversity Medical Center Hamburg-EppendorfHamburgGermany
  2. 2.Department of Biological Psychology and NeuropsychologyUniversity of HamburgHamburgGermany
  3. 3.Department of Informatics, Knowledge TechnologyUniversity of HamburgHamburgGermany

Personalised recommendations