Evolutionary Learning of Neural Structures for Visuo-Motor Control

  • Nils T. Siebel
  • Gerald Sommer
  • Yohannes Kassahun

Evolutionary Learning of Neural Structures for Visuo-Motor Control Artificial neural networks are computing tools, modeled after the human brain in order to make its vast learning and data processing potential available to computers. These networks are known to be powerful tools with natural learning capabilities. However, learning the structure and synaptic weights of an artificial neural network to solve a complex problem can be a very difficult task. With a growing size of the required network the dimension of the search space can make it next to impossible to find a globally optimal solution. We apply a relatively new method called EANT to develop a network that moves a robot arm in a visuo-motor control scenario with the goal to align its hand with an object. EANT starts from a simple initial network and gradually develops it further using an evolutionary method. On a larger scale new neural structures are added to a current generation of networks. On a smaller scale the current individuals (structures) are optimised by changing their parameters. Using a simulation to evaluate the individuals a reinforcement learning procedure for neural topologies has been realised. We present results from experiments with two types of optimisation strategies for the parameter optimisation.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Peter J Angeline, Gregory M Saunders, and Jordan B Pollack. An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks, 5:54–65, 1994.CrossRefGoogle Scholar
  2. 2.
    Wolfgang Banzhaf, Peter Nordin, Robert E Keller, and Frank D Francone. Genetic Programming: An Introduction on the Automatic Evolution of Computer Programs and Its Applications. Morgan Kaufmann, San Francisco, USA, 1998.MATHGoogle Scholar
  3. 3.
    Richard Ernest Bellman. Adaptive Control Processes. Princeton University Press, Princeton, USA, 1961.Google Scholar
  4. 4.
    Andrea Beltratti, Sergio Margarita, and Pietro Terna. Neural Networks for Economic and Financial Modelling. International Thomson Computer Press, London, UK, 1996.Google Scholar
  5. 5.
    Chris C Bissell. Control Engineering. Number 15 in Tutorial Guides in Electronic Engineering. CRC Press, Boca Raton, USA, 2nd edition, 1996.Google Scholar
  6. 6.
    Wolfram Blase, Josef Pauli, and Jörg Bruske. Vision-based manipulator navigation using mixtures of RBF neural networks. In International Conference on Neural Network and Brain, pages 531–534, Bejing, China, April 1998.Google Scholar
  7. 7.
    Ágoston E Eiben and James E Smith. Introduction to Evolutionary Computing. Springer Verlag, Berlin, Germany, 2003.MATHGoogle Scholar
  8. 8.
    Scott E Fahlman and Christian Lebiere. The cascade-correlation learning architecture. Technical Report CMU-CS-90-100, Carnegie Mellon University, Pittsburgh, USA, August 1991.Google Scholar
  9. 9.
    Roger Fletcher. Practical Methods of Optimization. John Wiley & Sons, New York, Chichester, 2nd edition, 1987.MATHGoogle Scholar
  10. 10.
    Nikolaus Hansen and Andreas Ostermeier. Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation, 9(2):159–195, 2001.CrossRefGoogle Scholar
  11. 11.
    Koichi Hashimoto, editor. Visual Servoing: Real-Time Control of Robot Manipulators Based on Visual Sensory Feedback, volume 7 of Series in Robotics and Automated Systems. World Scientific Publishing Co., Singapore, 1994.Google Scholar
  12. 12.
    Gilles Hermann, Patrice Wira, and Jean-Philippe Urban. Neural networks organizations to learn complex robotic functions. In Proceedings of the 11th European Symposium on Artificial Neural Networks (ESANN 2003), pages 33–38, Bruges, Belgium, April 2005.Google Scholar
  13. 13.
    Kurt Hornik, Maxwell B Stinchcombe, and Halbert White. Multilayer feedforward networks are universal approximators. Neural Networks, 2:359–366, 1989.CrossRefGoogle Scholar
  14. 14.
    Seth Hutchinson, Greg Hager, and Peter Corke. A tutorial on visual servo control. Tutorial notes, Yale University, New Haven, USA, May 1996.Google Scholar
  15. 15.
    William R Hutchison and Kenneth R Stephens. The airline marketing tactician (AMT): A commercial application of adaptive networking. In Proceedings of the 1st IEEE International Conference on Neural Networks, San Diego, USA, volume 2, pages 753–756, 1987.Google Scholar
  16. 16.
    Martin Jägersand. Visual servoing using trust region methods and estimation of the full coupled visual-motor Jacobian. In Proceedings of the IASTED Applications of Control and Robotics, Orlando, USA, pages 105–108, January 1996.Google Scholar
  17. 17.
    Jae-Yoon Jung and James A Reggia. A descriptive encoding language for evolving modular neural networks. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), pages 519–530. Springer Verlag, 2004.Google Scholar
  18. 18.
    Yohannes Kassahun and Gerald Sommer. Automatic neural robot controller design using evolutionary acquisition of neural topologies. In 19. Fachgespräch Autonome Mobile Systeme (AMS 2005), pages 259–266, Stuttgart, Germany, December 2005.Google Scholar
  19. 19.
    Yohannes Kassahun and Gerald Sommer. Efficient reinforcement learning through evolutionary acquisition of neural topologies. In Proceedings of the 13th European Symposium on Artificial Neural Networks (ESANN 2005), pages 259–266, Bruges, Belgium, April 2005.Google Scholar
  20. 20.
    Scott Kirkpatrick, Charles Daniel Gelatt, and Mario P Vecchi. Optimization by simulated annealing. Science, 220(4598):671–680, May 1983.CrossRefMathSciNetGoogle Scholar
  21. 21.
    James W Melody. On universal approximation using neural networks. Report from project ECE 480, Decision and Control Laboratory, University of Illinois, Urbana, USA, June 1999.Google Scholar
  22. 22.
    Tom M Mitchell. Machine Learning. McGraw-Hill, London, UK, 1997.MATHGoogle Scholar
  23. 23.
    David E Moriarty and Risto Miikkulainen. Evolving obstacle avoidance behavior in a robot arm. In Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, Cape Cod, USA, 1996.Google Scholar
  24. 24.
    Arnold Neumaier. Complete search in continuous global optimization and constraint satisfaction. Acta Numerica, 13:271–369, June 2004.MathSciNetGoogle Scholar
  25. 25.
    Apostolos-Paul Refenes, editor. Neural Networks in the Capital Markets. John Wiley & Sons, New York, Chichester, USA, 1995.Google Scholar
  26. 26.
    Claude Robert, Charles-Daniel Arreto, Jean Azerad, and Jean-François Gaudy. Bibliometric overview of the utilization of artificial neural networks in medicine and biology. Scientometrics, 59(1):117–130, 2004.CrossRefGoogle Scholar
  27. 27.
    Raúl Rojas. Neural Networks - A Systematic Introduction. Springer Verlag, Berlin, Germany, 1996.MATHGoogle Scholar
  28. 28.
    James C Spall. Introduction to Stochastic Search and Optimization: Estimation, Simulation, and Control. John Wiley & Sons, Hoboken, USA, 2003.MATHCrossRefGoogle Scholar
  29. 29.
    Kenneth O Stanley and Risto Miikkulainen. Evolving neural networks through augmenting topologies. Evolutionary Computation, 10(2):99–127, 2002.CrossRefGoogle Scholar
  30. 30.
    Robert R Trippi and Efraim Turban, editors. Neural Networks in Finance and Investing. Probus Publishing Co., Chicago, USA, 1993.Google Scholar
  31. 31.
    Jean-Philippe Urban, Jean-Luc Buessler, and Julien Gresser. Neural networks for visual servoing in robotics. Technical Report EEA-TROP-TR-97-05, Université de Haute-Alsace, Mulhouse-Colmar, France, November 1997.Google Scholar
  32. 32.
    Lee E Weiss, Arthur C Sanderson, and Charles P Neuman. Dynamic sensor-based control of robots with visual feedback. IEEE Journal of Robotics and Automation, 3(5):404–417, October 1987.CrossRefGoogle Scholar
  33. 33.
    Xin Yao. Evolving artificial neural networks. Proceedings of the IEEE, 87(9):1423–1447, September 1999.CrossRefGoogle Scholar
  34. 34.
    Xin Yao and Yong Liu. A new evolutionary system for evolving artificial neural networks. IEEE Transactions on Neural Networks, 8(3):694–713, May 1997.CrossRefMathSciNetGoogle Scholar
  35. 35.
    Michael Zeller, Kenneth R Wallace, and Klaus Schulten. Biological visuo-motor control of a pneumatic robot arm. In Cihan Hayreddin Dagli, Metin Akay, C L Philip Chen, Benito R Fernandez, and Joydeep Ghosh, editors, Intelligent Engineering Systems Through Artificial Neural Networks. Proceedings of the Artificial Neural Networks in Engineering Conference, New York, volume 5, pages 645–650. American Society of Mechanical Engineers, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Nils T. Siebel
    • 1
  • Gerald Sommer
    • 1
  • Yohannes Kassahun
    • 2
  1. 1.Cognitive Systems Group, Institute of Computer ScienceChristian-Albrechts-University of KielGermany
  2. 2.Group for Robotics, DFKI Lab BremenUniversity of BremenGermany

Personalised recommendations