Internal Simulations for Behaviour Selection and Recognition

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7559)


In this paper, we present internal simulations as a methodology for human behaviour recognition and understanding. The internal simulations consist of pairs of inverse forward models representing sensorimotor actions. The main advantage of this method is that it both serves for action selection and prediction as well as recognition. We present several human-robot interaction experiments where the robot can recognize the behaviour of the human reaching for objects.


behaviour recognition internal simulation human-robot interaction internal models 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Akgün, B., Tunaöglu, D., Sahin, E.: Action recognition through an action generation mechanism. In: International Conference on Epigenetic Robotics (EPIROB) (2010)Google Scholar
  2. 2.
    Baron-Cohen, S.: Mindblindness: An Essay on Autism and Theory of Mind. MIT Press (2001)Google Scholar
  3. 3.
    Barsalou, L.W.: Grounded cognition. Annual Reviews Psychology 59, 617–645 (2008)CrossRefGoogle Scholar
  4. 4.
    Blakemore, S.J., Wolpert, D., Frith, C.: Why can’t you tickle yourself? Neuroreport 11, 11–16 (2000)CrossRefGoogle Scholar
  5. 5.
    Blakemore, S.J., Goodbody, S.J., Wolpert, D.M.: Predicting the consequences of our own actions: The role of sensorimotor context estimation. The Journal of Neuroscience 18(18), 7511–7518 (1998)Google Scholar
  6. 6.
    Dearden, A.: Developmental learning of internal models for robotics. Ph.D. thesis, Imperial College London (2008)Google Scholar
  7. 7.
    Demiris, Y., Simmons, G.: Perceiving the unusual: Temporal properties of hierarchical motor representations for action perception. Neural Networks pp. 272–284 (2006)Google Scholar
  8. 8.
    Frith, C.D.: The Cognitive Neuropsychology of Schizophrenia. Erlbaum Associates (1992)Google Scholar
  9. 9.
    Gallese, V.: Before and below theory of mind: embodied simulation and the neural correlates of social cognition. Phil. Trans. of the Royal Society B 362(1480), 659–669 (2007)CrossRefGoogle Scholar
  10. 10.
    Hafner, V.V., Bachmann, F.: Human-humanoid walking gait recognition. In: Proceedings of Humanoids 2008, 8th IEEE-RAS International Conference on Humanoid Robots, pp. 598–602 (2008)Google Scholar
  11. 11.
    Haruno, M., Wolpert, D.M., Kawato, M.: Mosaic model for sensorimotor learning and control. Neural Computation 13, 2201–2220 (2001)zbMATHCrossRefGoogle Scholar
  12. 12.
    Jordan, M.I., Rumelhart, D.E.: Forward models: Supervised learning with a distal teacher. Cognitive Science 16, 307–354 (1992), CrossRefGoogle Scholar
  13. 13.
    Lara, B., Rendon, J.M., Capistran, M.: Prediction of multi-modal sensory situations, a forward model approach. In: Proceedings of the 4th IEEE Latin America Robotics Symposium, vol. 1 (2007)Google Scholar
  14. 14.
    Möller, R., Schenck, W.: Bootstrapping cognition from behavior–a computerized thought experiment. Cognitive Science 32(3), 504–542 (2008), CrossRefGoogle Scholar
  15. 15.
    Prinz, W.: Perception and action planning. European Journal of Cognitive Psychology 9(2), 129–154 (1997)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Schillaci, G., Hafner, V.V.: Random movement strategies in self-exploration for a humanoid robot. In: Proc. of the Intern. Conf. on Human-Robot Interaction 2011, pp. 245–246 (2011)Google Scholar
  17. 17.
    Schillaci, G., Hafner, V.V.: Prerequisites for intuitive interaction - on the example of humanoid motor babbling. In: HRI 2011 Workshop on Expectations in intuitive human-robot interaction, Laussane, Switzerland (March 2011)Google Scholar
  18. 18.
    Schillaci, G., Hafner, V.V., Lara, B.: Coupled inverse-forward models for action execution leading to tool-use in a humanoid robot. In: Proceedings of the 7th ACM/IEEE International Conference on Human-Robot Interaction, Boston (2012)Google Scholar
  19. 19.
    Schillaci, G., Lara, B., Hafner, V.V.: Internal simulation of the sensorimotor loop in action execution and recognition. In: Proceedings of the 5th International Conference on Cognitive Systems (CogSys 2012), Vienna, Austria (2012)Google Scholar
  20. 20.
    Troje, N.F.: Decomposing biological motion: A framework for analysis and synthesis of human gait patterns. Journal of Vision 2(5), 371–387 (2002)CrossRefGoogle Scholar
  21. 21.
    van der Wel, R., Sebanz, N., Knoblich, G.: Action perception from a common coding perspective. In: Johnson, K., Shiffrar, M. (eds.) People Watching: Social, Perceptual, and Neurophysiological Studies of Body Perception (in press)Google Scholar
  22. 22.
    Wilson, M., Knoblich, G.: The case for motor for motor involvement in perceiving conspecifics. Psychological Bulletin 131, 460–473 (2005)CrossRefGoogle Scholar
  23. 23.
    Wolpert, D.M., Kawato, M.: Multiple paired forward and inverse models for motor control. Neural Netw. 11(7-8), 1317–1329 (1998)CrossRefGoogle Scholar
  24. 24.
    Wolpert, D.M., Doya, K., Kawato, M.: A unifying computational framework for motor control and social interaction. Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences 358(1431), 593–602 (2003), CrossRefGoogle Scholar
  25. 25.
    Wolpert, D.M., Flanagan, J.R.: Motor prediction. Current Biology 11(18), R729–R732 (2001), CrossRefGoogle Scholar
  26. 26.
    Wolpert, D.M., Ghahramani, Z.: Computational principles of movement neuroscience. Nature Neuroscience 3(suppl.), 1212–1217 (2000), CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Cognitive Robotics Group, Department of Computer ScienceHumboldt-Universität zu BerlinGermany
  2. 2.Cognitive Robotics Group, Faculty of ScienceUniversidad Autonoma del Estado de MorelosCuernavacaMexico

Personalised recommendations