The European Physical Journal B

, Volume 63, Issue 3, pp 329–339 | Cite as

Predictive information and explorative behavior of autonomous robots

  • N. Ay
  • N. Bertschinger
  • R. Der
  • F. Güttler
  • E. Olbrich
Open Access
Topical issue dedicated to ECCS2007 - Dresden

Abstract.

Measures of complexity are of immediate interest for the field of autonomous robots both as a means to classify the behavior and as an objective function for the autonomous development of robot behavior. In the present paper we consider predictive information in sensor space as a measure for the behavioral complexity of a two-wheel embodied robot moving in a rectangular arena with several obstacles. The mutual information (MI) between past and future sensor values is found empirically to have a maximum for a behavior which is both explorative and sensitive to the environment. This makes predictive information a prospective candidate as an objective function for the autonomous development of such behaviors. We derive theoretical expressions for the MI in order to obtain an explicit update rule for the gradient ascent dynamics. Interestingly, in the case of a linear or linearized model of the sensorimotor dynamics the structure of the learning rule derived depends only on the dynamical properties while the value of the MI influences only the learning rate. In this way the problem of the prohibitively large sampling times for information theoretic measures can be circumvented. This result can be generalized and may help to derive explicit learning rules from complexity theoretic measures.

PACS.

89.70.Cf Entropy and other measures of information 87.19.lo Information theory 87.85.St Robotics 

References

  1. W. Bialek, I. Nemenman, N. Tishby, Neural Comput. 13, 2409 (2001) MATHCrossRefGoogle Scholar
  2. G. Box, G.M. Jenkins, G.C. Reinsel, Time Series Analysis: Forecasting and Control (Prentice Hall, 1994) Google Scholar
  3. T.M. Cover, J.A. Thomas, Elements of Information Theory Wiley series in telecommunications (Wiley, New York, 1991) Google Scholar
  4. J.P. Crutchfield, K. Young, Phys. Rev. Lett. 63, 105 (1989) CrossRefADSMathSciNetGoogle Scholar
  5. R. Der, Theory in Biosciences 120, 179 (2001) Google Scholar
  6. R. Der, F. Hesse, G. Martius, J. Adaptive Behavior 14, 105 (2005) CrossRefGoogle Scholar
  7. R. Der, R. Liebscher, True autonomy from self-organized adaptivity, in Proc. Workshop Biologically Inspired Robotics. The Legacy of Grey Walter 14-16 August 2002, Bristol Labs (Bristol, 2002) Google Scholar
  8. R. Der, G. Martius, From motor babbling to purposive actions: Emerging self-exploration in a dynamical systems approach to early robot development, in From Animals to Animats, Vol. 4095 of Lecture Notes in Computer Science, edited by S. Nolfi (Springer, 2006), p. 406 Google Scholar
  9. R. Der, G. Martius, F. Hesse, Let it roll – emerging sensorimotor coordination in a spherical robot, in Artificial Life X, edited by L.M. Rocha (MIT Press, 2006), p. 192 Google Scholar
  10. R. Der, U. Steinmetz, F. Pasemann, Homeokinesis - a new principle to back up evolution with learning, in Computational Intelligence for Modelling, Control, and Automation, Vol. 55 of Concurrent Systems Engineering Series (IOS Press, Amsterdam, 1999), p. 43 Google Scholar
  11. P. Grassberger, Int. J. Theor. Phys. 25(9) 907 (1986) Google Scholar
  12. G. Jumary, Relative Information, Vol. 47 of Springer Series in Synergetics (Springer-Verlag, Berlin Heidelberg, 1990) Google Scholar
  13. A.S. Klyubin, D. Polani, C.L. Nehaniv, Empowerment: A universal agent-centric measure of control, in Proc. CEC. IEEE, 2005 Google Scholar
  14. A.S. Klyubin, D. Polani, C.L. Nehaniv, Neural Comput. 19, 2387, 2007 Google Scholar
  15. M. Lungarella, G. Metta, R. Pfeifer, G. Sandini, Connect. Sci. 15(4), 151 (2003) CrossRefGoogle Scholar
  16. M. Lungarella, T. Pegors, D. Bulwinkle, O. Sporns, Neuroinformatics 3(3) 243 (2005) Google Scholar
  17. M. Lungarella, O. Sporns, Comput. Biol. 2(10), e144 (2006) Google Scholar
  18. G. Martius, R. Der, lpzrobots – simulation tool for autonomous robots, http://robot.informatik.uni-leipzig.de/, 2007 Google Scholar
  19. P.-Y. Oudeyer, F. Kaplan, V.V. Hafner, A. Whyte, The playground experiment: Task-independent development of a curious robot, in Proceedings of the AAAI Spring Symposium on Developmental Robotics, edited by D. Bank, L. Meeden (Stanford, California, 2005), p. 42 Google Scholar
  20. H. Risken, The Fokker-Planck Equation (Springer, 1989) Google Scholar
  21. J. Schmidhuber, Completely self-referential optimal reinforcement learners, in ICANN (2), pp. 223–233 (2005) Google Scholar
  22. R. Smith, Open dynamics engine, http://ode.org/, 2005 Google Scholar
  23. S. Still, Statistical mechanics approach to interactive learning arXiv:0709.1948v1 [physics.data-an], 2007. submitted Google Scholar
  24. A. Stout, G. Konidaris, A. Barto, Iintrinsically motivated reinforcement learning: A promising framework for developmental robotics, in The AAAI Spring Symposium on Developmental Robotics, 2005 Google Scholar
  25. J. Weng, J. McClelland, A. Pentland, O. Sporns, I. Stockman, M. Sur, E. Thelen, Science 291, 599 (2001) CrossRefGoogle Scholar

Copyright information

© The Author(s) 2008

Open Access This article is distributed under the terms of the Creative Commons Attribution License which permits any use, distribution and reproduction in any medium, provided the original author(s) and source are credited.

Authors and Affiliations

  • N. Ay
    • 1
    • 2
  • N. Bertschinger
    • 1
  • R. Der
    • 1
  • F. Güttler
    • 3
  • E. Olbrich
    • 1
  1. 1.Max-Planck Institute for Mathematics in the Sciences LeipzigLeipzigGermany
  2. 2.Santa Fe InstituteSanta FeUSA
  3. 3.University LeipzigLeipzigGermany

Personalised recommendations