Taming the Beast: Guided Self-organization of Behavior in Autonomous Robots

  • Georg Martius
  • J. Michael Herrmann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6226)


Self-organizing processes are crucial for the development of living beings. Practical applications in robots may benefit from the self-organization of behavior, e.g. for the increased fault tolerance and enhanced flexibility provided that external goals can also be achieved. We present several methods for the guidance of self-organizing control by externally prescribed criteria. We show that the degree of self-organized explorativity of the robot can be regulated and that problem-specific error functions, hints, or abstract symbolic descriptions of a goal can be reconciled with the continuous robot dynamics.


Controller Parameter Autonomous Robot Teaching Signal Imitation Learning Wheel Velocity 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Der, R., Hesse, F., Martius, G.: Rocking stamper and jumping snake from a dynamical system approach to artificial life. Adapt. Beh. 14, 105–115 (2006)CrossRefGoogle Scholar
  2. 2.
    Hesse, F., Martius, G., Der, R., Herrmann, J.M.: A sensor-based learning algorithm for the self-organization of robot behavior. Algorithms 2(1), 398–409 (2009)CrossRefGoogle Scholar
  3. 3.
    Stefano, N.: Behaviour as a complex adaptive system: On the role of self-organization in the development of individual and collective behaviour. ComplexUs 2(3-4), 195–203 (2006)Google Scholar
  4. 4.
    Tani, J.: Learning to generate articulated behavior through the bottom-up and the top-down interaction processes. Neural Networks 16(1), 11–23 (2003)CrossRefGoogle Scholar
  5. 5.
    Martius, G., Herrmann, J.M., Der, R.: Guided self-organisation for autonomous robot development. In: Almeida e Costa, F., Rocha, L.M., Costa, E., Harvey, I., Coutinho, A. (eds.) ECAL 2007. LNCS (LNAI), vol. 4648, pp. 766–775. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  6. 6.
    Prokopenko, M.: Guided self-organization. HFSP Journal 3(5), 287–289 (2009)CrossRefGoogle Scholar
  7. 7.
    Der, R.: Self-organized acquisition of situated behavior. Theory in Biosciences 120, 179–187 (2001)Google Scholar
  8. 8.
    Jordan, M.I., Rumelhart, D.E.: Forward models: Supervised learning with a distal teacher. Cognitive Science 16(3), 307–354 (1992)CrossRefGoogle Scholar
  9. 9.
    Nolfi, S., Floreano, D.: Learning and evolution. Auton. Robots 7(1), 89–113 (1999)CrossRefGoogle Scholar
  10. 10.
    Di Paolo, E.: Organismically-inspired robotics: Homeostatic adaptation and natural teleology beyond the closed sensorimotor loop. In: Murase, K., Asakura, T. (eds.) Dyn. Systems Approach to Embodiment and Sociality, pp. 19–42 (2003)Google Scholar
  11. 11.
    Williams, H.: Homeostatic plasticity in recurrent neural networks. In: Schaal, S., Ispeert, A. (eds.) From Animals to Animats: Proc. 8th Intl. Conf. on Simulation of Adaptive Behavior, vol. 8. MIT Press, Cambridge (2004)Google Scholar
  12. 12.
    Der, R., Martius, G.: From motor babbling to purposive actions: Emerging self-exploration in a dynamical systems approach to early robot development. In: Nolfi, S., Baldassarre, G., Calabretta, R., Hallam, J.C.T., Marocco, D., Meyer, J.-A., Miglino, O., Parisi, D. (eds.) SAB 2006. LNCS (LNAI), vol. 4095, pp. 406–421. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  13. 13.
    Der, R., Martius, G., Hesse, F., Güttler, F.: Videos of self-organized behavior in autonomous robots (2009),
  14. 14.
    Prokopenko, M., Zeman, A., Li, R.: Homeotaxis: Coordination with persistent time-loops. In: Asada, M., Hallam, J.C.T., Meyer, J.-A., Tani, J. (eds.) SAB 2008. LNCS (LNAI), vol. 5040, pp. 403–414. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  15. 15.
    Martius, G., Hesse, F., Güttler, F., Der, R.: LpzRobots: A free and powerful robot simulator (2009),
  16. 16.
    Nolfi, S., Floreano, D.: Evolutionary Robotics. In: The Biology, Intelligence, and Technology of Self-organizing Machines. MIT Press, Cambridge (2001); 1st Print (2000), 2nd Print (2001)Google Scholar
  17. 17.
    Sutton, R.S., Barto, A.G.: Reinforcement learning: Past, present and future. In: SEAL, pp. 195–197 (1998)Google Scholar
  18. 18.
    de Margerie, E., Mouret, J.B., Doncieux, S., Meyer, J.A.: Artificial evolution of the morphology and kinematics in a flapping-wing mini UAV. Bioinspiration and Biomimetics 2, 65–82 (2007)CrossRefGoogle Scholar
  19. 19.
    Ijspeert, A.J., Hallam, J., Willshaw, D.: Evolving Swimming Controllers for a Simulated Lamprey with Inspiration from Neurobiology. Adaptive Behavior 7(2), 151–172 (1999)CrossRefGoogle Scholar
  20. 20.
    Mazzapioda, M.G., Nolfi, S.: Synchronization and gait adaptation in evolving hexapod robots. In: Nolfi, S., Baldassarre, G., Calabretta, R., Hallam, J.C.T., Marocco, D., Meyer, J.-A., Miglino, O., Parisi, D. (eds.) SAB 2006. LNCS (LNAI), vol. 4095, pp. 113–125. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  21. 21.
    Peters, J., Vijayakumar, S., Schaal, S.: Natural Actor-Critic. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol. 3720, pp. 280–291. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  22. 22.
    Peters, J., Schaal, S.: Natural Actor-Critic. Neurocomputing 71(7-9), 1180–1190 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Georg Martius
    • 1
    • 2
    • 3
  • J. Michael Herrmann
    • 1
    • 2
    • 4
  1. 1.Bernstein Center for Computational Neuroscience GöttingenGöttingenGermany
  2. 2.Institute for Nonlinear DynamicsUniversity of GöttingenGöttingenGermany
  3. 3.Max Planck Institute for Dynamics and Self-OrganizationGöttingenGermany
  4. 4.School of Informatics, IPABUniversity of EdinburghEdinburghU.K.

Personalised recommendations