Advertisement

Evolving Humanoid Behaviors for Language Games

  • Frank Pasemann
  • Christian Rempis
  • Arndt von Twickel
Chapter

Abstract

Evolutionary techniques are applied to develop the neural control of humanoid robots. These robots were designed to act as agents in embodied language games. The basic ingredients needed to bring forth the desired behaviors are described: an appropriate physical simulator of the robots, an interactive evolution environment and various analysis tools. A modular approach to neural control is taken and is supported by a corresponding evolutionary algorithm, such that complete neural control networks are composed of specific functional units, the so called neuro-modules. Examples of such modules are described and their use is demonstrated by means of two developed networks for a walking and a gesture behavior.

Key words

evolutionary robotics recurrent neural networks neuro-modules, sensorimotor loops humanoid robots 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Floreano D, Husbands P, Nolfi S (2008) Evolutionary Robotics. In: Siciliano B, Khatib O (eds) Springer Handbook of Robotics, Springer, pp 1423–1451Google Scholar
  2. Goldberg D (1989) Genetic algorithms in search, optimization, and machine learning. Addison-wesleyGoogle Scholar
  3. Hagglund T (1995) PID Controllers: Theory, Design and Tuning. IsaGoogle Scholar
  4. Hild M, Siedel T, Benckendorff C, Kubisch M, Thiele C (2011) Myon: Concepts and design of a modular humanoid robot which can be reassembled during runtime. Proceedings of the 14th International Conference on Climbing andWalking Robots and the Support Technologies for Mobile Machines (CLAWAR 2011)Google Scholar
  5. Hild M, Siedel T, Benckendorff C, Thiele C, Spranger M (2012) Myon, a New Humanoid. In: Steels L, Hild M (eds) Language Grounding in Robots, Springer, New YorkGoogle Scholar
  6. Hulse M, Pasemann F (2002) Dynamical neural Schmitt trigger for robot control. In:Google Scholar
  7. Dorronsoro J (ed) Artificial Neural Networks - ICANN 2002, International Conference, Madrid, Spain, August 28-30, 2002. Proceedings. LNCS 2415, Springer Verlag, Berlin, pp 783–788Google Scholar
  8. Kitano H, Asada M, Kuniyoshi Y, Noda I, Osawa E (1997) Robocup: The robot world cup initiative. In: Proceedings of the first international conference on Autonomous agents, ACM, pp 340–347Google Scholar
  9. Nolfi S, Floreano D (2000) Evolutionary Robotics. ISBN-13: 978-0-262-14070-6, MIT PressGoogle Scholar
  10. Nusse H, Yorke J, Hunt B, Kostelich E (1998) Dynamics: numerical explorations. SpringerGoogle Scholar
  11. Pasemann F, Hild M, Zahedi K (2003) SO(2)-Networks as neural oscillators. Computational Methods in Neural Modeling 2686/2003:144–151CrossRefGoogle Scholar
  12. Peterka RJ (2009) Comparison of human and humanoid robot control of upright stance. Journal of Physiology-Paris 103(3–5):149–158CrossRefGoogle Scholar
  13. RempisCW, Pasemann F (2010) Search space restriction of neuro-evolution through constrained modularization of neural networks. In: Mandai K (ed) Proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent InformationGoogle Scholar
  14. Processing (ANNIIP), in Conjunction with ICINCO 2010., SciTePress, Madeira, Portugal, pp 13–22Google Scholar
  15. Rempis CW, Thomas V, Bachmann F, Pasemann F (2010) NERD - Neurodynamics and Evolutionary Robotics Development Kit. In: et al NA (ed) SIMPAR 2010, Springer, Heidelberg, Lecture Notes in Artificial Intelligence, vol 6472, pp 121– 132Google Scholar
  16. Smith R (2001) The Open Dynamics Engine (ODE) http://www.ode.org. URL http://www.ode.org
  17. von Twickel A, Buschges A, Pasemann F (2011a) Deriving neural network controllers from neuro-biological data – implementation of a single-leg stick insect controller. Biological Cybernetics 104(1 2):95–119 von Twickel A, Hild M, Siedel T, Patel V, Pasemann F (2011b) Neural control of a modular multi-legged walking machine: Simulation and hardware. Robotics and Autonomous Systems In press, doi:10.1016/j.robot.2011.10.006Google Scholar
  18. von Twickel A, Pasemann F (2007) Reflex-oscillations in evolved single leg neurocontrollers for walking machines. Natural Computing 6(3):311–337MathSciNetzbMATHCrossRefGoogle Scholar
  19. Yang JF, Lamont EV, Pang MYC (2005) Split-belt treadmill stepping in infants suggests autonomous pattern generators for the left and right leg in humans. The Journal of Neuroscience 25(29):6869–6876CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Frank Pasemann
    • 1
  • Christian Rempis
    • 1
  • Arndt von Twickel
    • 1
  1. 1.Institute of Cognitive ScienceUniversity of OsnabrueckOsnabrückGermany

Personalised recommendations