Proprioception and Imitation: On the Road to Agent Individuation

  • M. Lagarde
  • P. Andry
  • P. Gaussier
  • S. Boucenna
  • L. Hafemeister

Abstract

In this paper, we will show that different kinds of interactive behaviors can emerge according to the kind of proprioceptive function available in a given sensori-motor system. We will study three different examples. In the first one, an internal proprioceptive signal is available for the learning of the visuo-motor coordination between an arm and a camera. An imitation behavior can emerge when the robot’s eye focuses on the hand of the experimenter instead of its own hand. The imitative behavior results from the error minimization between the visual signal and the proprioceptive signal. In the second example, we will show that similar modifications of the robot’s initial dynamics allows to learn some of the space-time properties of more complex behaviors under the form of a sequence of sensori-motor associations. In the third example, a robot head has to recognize the facial expression of the human caregiver. Yet, the robot has no visual feedback of its own facial expression. The human expressive resonance will allow the robot to select the visual features relevant for a particular facial expression. As a result, after few minutes of interactions, the robot can imitates the facial expression of the human partner. We will show that the different proprioceptive signals used in the examples can be seen as bootstrap mechanisms for more complex interactions. Applied as a crude model of the human, we will propose that these mechanisms play an important role in the process of individuation.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Braitenberg, V.: Vehicles : Experiments in Synthetic Psychology. MIT Press, Bradford Books, Cambridge (1984)Google Scholar
  2. 2.
    Pfeifer, R., Scheier, C.: Understanding intelligence. MIT Press, Cambridge (1999)Google Scholar
  3. 3.
    Michel, F., Ferber, J., Drogoul, A.: Multi-Agent Systems and Simulation: a Survey From the Agents Community’s Perspective in Multi-Agent Systems: Simulation and Applications. CRC Press - Taylor and Francis (2009)Google Scholar
  4. 4.
    Breazeal, C.: Regulation and entrainment for human-robot interaction. International Journal of Experimental Robotics 10-11(21), 883–902 (2003)Google Scholar
  5. 5.
    Kozima, H., Nakagawa, C., Yano, H.: Can a robot empathize with people? Artificial Life and Robotics 8(1), 83–88 (2004)CrossRefGoogle Scholar
  6. 6.
    Masahiro, M.: On the uncanny valley. In: Proceedings of the Humanoids 2005 workshop: Views of the Uncanny Valley, Tsukuba, Japan (December 2005)Google Scholar
  7. 7.
    Meltzoff, N., Moore, M.K.: Imitation of facial and manual gestures by humans neonates. Science 198, 75–82 (1977)CrossRefGoogle Scholar
  8. 8.
    Nadel, J., Croué, S., Mattlinger, M., Canet, P., Hudelot, C., Lecuyer, C., Martini, M.: Do autistic children have expectancies about the social behaviour of unfamiliar people?: A pilot study with the still face paradigm. Autism 2, 133–145 (2000)CrossRefGoogle Scholar
  9. 9.
    Meltzoff, A., Decety, J.: What imitation tells us about social cognition: a rapprochementbetween developmental psychology and cognitive neuroscience. Phil. Trans. R. Soc. Lond. B 358, 491–500 (2003)CrossRefGoogle Scholar
  10. 10.
    Kozima, H., Nakagawa, C., Yano, H.: Attention coupling as a prerequisite for social interaction. In: 2th IEEE International Workshop on Robot and Human Interactive Communication, IEEE, October 2003, pp. 109–114. IEEE Press, Los Alamitos (2003)Google Scholar
  11. 11.
    Kozima, H., Nakagawa, C., Yano, H.: Can a robot empathize with people? Artif. Life Robotics 8, 83–88 (2004)CrossRefGoogle Scholar
  12. 12.
    Revel, A., Andry, P.: Emergence of structured interactions: From a theoretical model to pragmatic robotics. Neural Network 22, 116–125 (2009)CrossRefGoogle Scholar
  13. 13.
    Ratliff, N., Silver, D., Bagnell, J.: Learning to search: Functional gradient techniques for imitation learning. Autonomous Robots 27(1), 25–53 (2009)CrossRefGoogle Scholar
  14. 14.
    Amari, S.: Dynamic of pattern formation in lateral-inhibition type by neural fields. Biological Cybernetics 27, 77–87 (1977)MATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Schöner, G., Dose, M., Engels, C.: Dynamics of behavior: theory and applications for autonomous robot architectures. Robotic and Autonomous System 16(2-4), 213–245 (1995)CrossRefGoogle Scholar
  16. 16.
    Andry, P., Gaussier, P., Hirsbrunner, B., Nadel, J.: Learning invariant sensory-motor behaviors: A developmental approach of imitation mechanisms. Adaptive behavior 12(2) (2004)Google Scholar
  17. 17.
    Gaussier, P., Moga, S., Quoy, M., Banquet, J.: From perception-action loops to imitation processes: a bottom-up approach of learning by imitation. Applied Artificial Intelligence 12(7-8), 701–727 (1998)CrossRefGoogle Scholar
  18. 18.
    Nielsen, T.: Volition: A new experimental approach. Scandinavian Journal of Psychology 4, 225–230 (1963)CrossRefGoogle Scholar
  19. 19.
    Fourneret, P., Jeannerod, M.: Limited conscious monitoring of motor performance in normal subjects. Neuropsychologia 36, 1133–1140 (1998)CrossRefGoogle Scholar
  20. 20.
    Jeannerod, M.: To act or not to act. perspectives on the representation of actions. Quaterly Journal of Experimental Psychology 52A, 1–29 (1999)CrossRefGoogle Scholar
  21. 21.
    Andry, P., Gaussier, P., Nadel, J.: From sensorimotor coordination to low level imitation. In: Second international workshop on epigenetic robotics, pp. 7–15 (2002)Google Scholar
  22. 22.
    Gaussier, P.: Toward a cognitive system algebra: A perception/action perspective. In: European Workshop on Learning Robots (EWRL), pp. 88–100 (2001)Google Scholar
  23. 23.
    Gaussier, P., Prepin, K., Nadel, J.: Toward a cognitive system algebra: Application to facial expression learning and imitation. In: Iida, F., Pfeifer, R., Steels, L., Kuniyoshi, Y. (eds.) Embodied Artificial Intelligence. LNCS (LNAI), vol. 3139, pp. 243–258. Springer, Heidelberg (2004)Google Scholar
  24. 24.
    Nadel, J., Simon, M., Canet, P., Soussignan, R., Blancard, P., Canamero, L., Gaussier, P.: Human responses to an expressive robot. In: Epirob 2006 (2006)Google Scholar
  25. 25.
    Banquet, J., Gaussier, P., Dreher, J.C., Joulain, C., Revel, A., Günther, W.: Space-time, order, and hierarchy in fronto-hippocampal system: A neural basis of personality. In: Matthews, G. (ed.) Cognitive Science Perspectives on Personality and Emotion, vol. 124, pp. 123–189. North Holland, Amsterdam (1997)CrossRefGoogle Scholar
  26. 26.
    Zipser, D.: A computational model of hippocampal place fields. Behavioral Neuroscience 99(5), 1006–1018 (1985)CrossRefGoogle Scholar
  27. 27.
    Wiener, S., Berthoz, A., Zugaro, M.: Multisensory processing in the elaboration of place and head direction responses by limbic system neurons. Cognitive Brain Research 14, 75–90 (2002)CrossRefGoogle Scholar
  28. 28.
    O’Keefe, J.: The hippocampal cognitive map and navigational strategies. Oxford University Press, Oxford (1991)Google Scholar
  29. 29.
    Grossberg, S., Merrill, J.: A neural network model of adaptively timed reinforcement learning and hippocampal dynamics. Cognitive Brain Research 1, 3–38 (1992)CrossRefGoogle Scholar
  30. 30.
    Gaussier, P., Moga, S., Banquet, J.P., Quoy, M.: From perception-action loops to imitation processes. Applied Artificial Intelligence (AAI) 1(7), 701–727 (1998)Google Scholar
  31. 31.
    Moga, S., Gaussier, P.: A neuronal structure for learning by imitation. In: Floreano, D., Mondada, F. (eds.) ECAL 1999. LNCS, vol. 1674, pp. 314–318. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  32. 32.
    Andry, P., Gaussier, P., Moga, S., Banquet, J., Nadel, J.: Learning and communication in imitation: An autonomous robot perspective. IEEE transactions on Systems, Man and Cybernetics, Part A 31(5), 431–444 (2001)CrossRefGoogle Scholar
  33. 33.
    Andry, P., Gaussier, P., Nadel, J.: Autonomous learning and reproduction of complex sequence: a multimodal architecture for bootstrapping imitation games. In: Lund University Cognitive Studies (ed.) Proceedings of the Fith Internationnal Workshop on Epigenetic Robotics, Modeling Cognitive development in robotic Systems, EPIROB 2005, July 2005, pp. 97–100 (2005)Google Scholar
  34. 34.
    Lagarde, M., Andry, P., Gaussier, P.: The role of internal oscillators for the one-shot learning of complex temporal sequences. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D.P. (eds.) ICANN 2007. LNCS, vol. 4668, pp. 934–943. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  35. 35.
    Rumelhart, D.E., Mcclelland, J.L.: Parallel distributed processing: explorations in the microstructure of cognition. psychological and biological models, vol. 2 (1986)Google Scholar
  36. 36.
    Molter, C., Salihoglu, U., Bersini, H.: Learning cycles brings chaos in continuous hopfield networks. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN) conference (2005)Google Scholar
  37. 37.
    Daucé, E., Quoy, M., Doyon, B.: Resonant spatio-temporal learning in large random neural networks. Biological Cybernetics 87, 185–198 (2002)MATHCrossRefGoogle Scholar
  38. 38.
    Jaeger, H.: Short term memory in echo state networks. Technical Report GMD Report 152, German National Research Center for Information Technology (2001)Google Scholar
  39. 39.
    Jaeger, H.: The ”echo state” approach to analysing and training recurrent neural networks. Technical Report GMD Report 148, German National Research Center for Information Technology (2001)Google Scholar
  40. 40.
    Lopes, M., Melo, F., Montesano, L., Santos-Victor, J.: Abstraction Levels for Robotic Imitation: Overview and Computational Approaches. In: Sigaud, O., Peters, J. (eds.) From Motor Learning to Interaction Learning in Robots. SCI, vol. 264, pp. 313–355. Springer, Heidelberg (2010)Google Scholar
  41. 41.
    Chalodhorn, R., Rao, R.: Learning to imitate human actions through eigen- poses. In: Sigaud, O., Peters, J. (eds.) From Motor Learning to Interaction Learning in Robots. SCI, vol. 264, pp. 357–381. Springer, Heidelberg (2010)Google Scholar
  42. 42.
    Ijspeert, A.J., Nakanishi, J., Shibata, T., Schaal, S.: Nonlinear dynamical systems for imitation with humanoid robots. In: Proceedings of the IEEE/RAS International Conference on Humanoids Robots (Humanoids 2001), pp. 219–226 (2001)Google Scholar
  43. 43.
    Calinon, S., Billard, A.: Learning of Gestures by Imitation in a Humanoid Robot. In: Dautenhahn, K., Nehaniv, C.L. (eds.). Cambridge University Press, Cambridge (2006)Google Scholar
  44. 44.
    Hersch, M., Billard, A.: A biologically-inspired model of reaching movements. In: Proceedings of the 2006 IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, Pisa (2006)Google Scholar
  45. 45.
    Bullock, D., Grossberg, S.: Neural dynamics of planned arm movements: Emergent invariants and speed-accuracy properties during trajectory formation. Psychological Review 95, 49–90 (1988)CrossRefGoogle Scholar
  46. 46.
    Ans, B., Coiton, Y., Gilhodes, J.C., Velay, J.L.: A neural network model for temporal sequence learning and motor programming. Neural Networks 7(9), 1461–1476 (1994)CrossRefGoogle Scholar
  47. 47.
    Beer, R.: On the dynamics of small continuous–time recurrent networks. Technical Report CES–94–18, Cleveland, OH (1994)Google Scholar
  48. 48.
    Lagarde, M., Andry, P., Gaussier, P., Giovannangeli, C.: Learning new behaviors: Toward a control architecture merging spatial and temporal modalities. In: Workshop on Interactive Robot Learning - International Conference on Robotics: Science and Systems (RSS 2008) (June 2008) (to appear)Google Scholar
  49. 49.
    Cheng, G., Kuniyoshi, Y.: Complex continuous meaningful humanoid interaction: A multi sensory-cue based approach. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA 2000), April 2000, pp. 2235–2242 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • M. Lagarde
    • 2
  • P. Andry
    • 2
  • P. Gaussier
    • 1
  • S. Boucenna
    • 2
  • L. Hafemeister
    • 2
  1. 1.IUF 
  2. 2.ETIS, ENSEAUniv Cergy-pontoise, CNRS UMR 8051Cergy-Pontoise

Personalised recommendations