Advertisement

Speeding-Up the Learning of Saccade Control

  • Marco Antonelli
  • Angel J. Duran
  • Eris Chinellato
  • Angel P. Del Pobil
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8064)

Abstract

A saccade is a ballistic eye movement that allows the visual system to bring the target in the center of the visual field. For artificial vision systems, as in humanoid robotics, performing such a movement requires to know the intrinsic parameters of the camera. Parameters can be encoded in a bio-inspired fashion by a non-parametric model, that is trained during the movement of the camera. In this work, we propose a novel algorithm to speed-up the learning of saccade control in a goal-directed manner. During training, the algorithm computes the covariance matrix of the transformation and uses it to choose the most informative visual feature to gaze next. Results on a simulated model and on a real setup show that the proposed technique allows for a very efficient learning of goal-oriented saccade control.

Keywords

Ground Truth Root Mean Square Exploration Behavior Humanoid Robot Radial Basis Function Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Antonelli, M., Grzyb, B., Castelló, V., del Pobil, A.: Augmenting the reachable space in the nao humanoid robot. In: Workshops at the Twenty-Sixth AAAI Conference on Artificial Intelligence (2012)Google Scholar
  2. 2.
    Antonelli, M., Chinellato, E., Del Pobil, A.P.: On-line learning of the visuomotor transformations on a humanoid robot. In: Lee, S., Cho, H., Yoon, K.-J., Lee, J. (eds.) Intelligent Autonomous Systems 12. AISC, vol. 193, pp. 853–861. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  3. 3.
    Castet, E., Masson, G.S.: Motion perception during saccadic eye movements. Nature Neuroscience 3(2), 177–183 (2000)CrossRefGoogle Scholar
  4. 4.
    Chao, F., Lee, M., Lee, J.: A developmental algorithm for ocular-motor coordination. Robotics and Autonomous Systems 58(3), 239–248 (2010)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Chen-Harris, H., Joiner, W., Ethier, V., Zee, D., Shadmehr, R.: Adaptive control of saccades via internal feedback. The Journal of Neuroscience 28(11), 2804 (2008)CrossRefGoogle Scholar
  6. 6.
    Chinellato, E., Antonelli, M., Grzyb, B., del Pobil, A.: Implicit sensorimotor mapping of the peripersonal space by gazing and reaching. IEEE Transactions on Autonomous Mental Development 3, 45–53 (2011)CrossRefGoogle Scholar
  7. 7.
    Chinellato, E., Antontelli, M., del Pobil, A.P.: A pilot study on saccadic adaptation experiments with robots. In: Prescott, T.J., Lepora, N.F., Mura, A., Verschure, P.F.M.J. (eds.) Living Machines 2012. LNCS, vol. 7375, pp. 83–94. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  8. 8.
    Chinellato, E., Grzyb, B.J., Marzocchi, N., Bosco, A., Fattori, P., del Pobil, A.P.: The dorso-medial visual stream: From neural activation to sensorimotor interaction. Neurocomputing 74(8), 1203–1212 (2011)CrossRefGoogle Scholar
  9. 9.
    Collins, T., Doré-Mazars, K., Lappe, M.: Motor space structures perceptual space: Evidence from human saccadic adaptation. Brain Research 1172, 32–39 (2007)CrossRefGoogle Scholar
  10. 10.
    Deubel, H.: Separate adaptive mechanisms for the control of reactive and volitional saccadic eye movements. Vision Research 35(23-24), 3529–3540 (1995)CrossRefGoogle Scholar
  11. 11.
    Fiser, J., Berkes, P., Orbán, G., Lengyel, M.: Statistically optimal perception and learning: from behavior to neural representations: Perceptual learning, motor learning, and automaticity. Trends in Cognitive Sciences 14(3), 119 (2010)CrossRefGoogle Scholar
  12. 12.
    Forssén, P.: Learning saccadic gaze control via motion prediciton. In: Fourth Canadian Conference on Computer and Robot Vision (CRV), pp. 44–54 (2007)Google Scholar
  13. 13.
    Haykin, S.S., et al.: Kalman filtering and neural networks. Wiley Online Library (2001)Google Scholar
  14. 14.
    Hoffmann, H., Schenck, W., Möller, R.: Learning visuomotor transformations for gaze-control and grasping. Biological Cybernetics 93(2), 119–130 (2005)zbMATHCrossRefGoogle Scholar
  15. 15.
    Jordan, M., Rumelhart, D.: Forward models: Supervised learning with a distal teacher. Cognitive Science: A Multidisciplinary Journal 16(3), 307–354 (1992)CrossRefGoogle Scholar
  16. 16.
    Kawato, M.: Feedback-error-learning neural network for supervised motor learning. Advanced Neural Computers 6(3), 365–372 (1990)Google Scholar
  17. 17.
    Marjanovic, M., Scassellati, B., Williamson, M.: Self-taught visually guided pointing for a humanoid robot. In: From Animals to Animats 4: Proc. Fourth Intl. Conf. Simulation of Adaptive Behavior, pp. 35–44 (1996)Google Scholar
  18. 18.
    McLaughlin, S.: Parametric adjustment in saccadic eye movements. Attention, Perception, & Psychophysics 2(8), 359–362 (1967)CrossRefGoogle Scholar
  19. 19.
    Park, J., Sandberg, I.W.: Universal approximation using radial-basis-function networks. Neural Computation 3(2), 246–257 (1991)CrossRefGoogle Scholar
  20. 20.
    Pouget, A., Sejnowski, T.J.: Spatial transformations in the parietal cortex using basis functions. Journal of Cognitive Neuroscience 9(2), 222–237 (1997)CrossRefGoogle Scholar
  21. 21.
    Pouget, A., Snyder, L.: Computational approaches to sensorimotor transformations. Nature Neuroscience 3, 1192–1198 (2000)CrossRefGoogle Scholar
  22. 22.
    Quigley, M., et al.: Ros: an open-source robot operating system. In: ICRA Workshop on Open Source Software (2009)Google Scholar
  23. 23.
    Schenck, W., Möller, R.: Learning strategies for saccade control. Künstliche Intelligenz (3/06), 19–22 (2006)Google Scholar
  24. 24.
    Schnier, F., Zimmermann, E., Lappe, M.: Adaptation and mislocalization fields for saccadic outward adaptation in humans. Journal of Eye Movement Research 3(3), 1–18 (2010)Google Scholar
  25. 25.
    Shibata, T., Vijayakumar, S., Conradt, J., Schaal, S.: Biomimetic oculomotor control. Adapt. Behav. 9(3-4), 189–207 (2001)CrossRefGoogle Scholar
  26. 26.
    Sun, G., Scassellati, B.: A fast and efficient model for learning to reach. International Journal of Humanoid Robotics 2(4), 391–414 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Marco Antonelli
    • 1
  • Angel J. Duran
    • 1
  • Eris Chinellato
    • 2
  • Angel P. Del Pobil
    • 1
  1. 1.Robotic Intelligence LabUniversitat Jaume ISpain
  2. 2.Imperial College LondonUK

Personalised recommendations