Advertisement

Tacit Learning for Emergence of Task-Related Behaviour through Signal Accumulation

  • Vincent Berenz
  • Fady Alnajjar
  • Mitsuhiro Hayashibe
  • Shingo Shimoda
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 316)

Abstract

Control of robotic joints movements requires the generation of appropriate torque and force patterns, coordinating the kinematically and dynamically complex multijoints systems. Control theory coupled with inverse and forward internal models are commonly used to map a desired endpoint trajectory into suitable force patterns. In this paper, we propose the use of tacit learning to successfully achieve similar tasks without using any kinematic model of the robotic system to be controlled. Our objective is to design a new control strategy that can achieve levels of adaptability similar to those observed in living organisms and be plausible from a neural control viewpoint. If the neural mechanisms used for mapping goals expressed in the task-space into control-space related command without using internal models remain largely unknown, many neural systems rely on data accumulation. The presented controller does not use any internal model and incorporates knowledge expressed in the task space using only the accumulation of data. Tested on a simulated two-link robot system, the controller showed flexibility by developing and updating its parameters through learning. This controller reduces the gap between reflexive motion based on simple accumulation of data and execution of voluntarily planned actions in a simple manner that does not require complex analysis of the dynamics of the system.

Keywords

Robotic System Internal Model Mapping Goal Task Space Stability Line 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Minsky, M.L., Papert, S.A.: Perceptron. MIT Press, Cambridge (1969)Google Scholar
  2. 2.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by backpropagating errors. Nature 323(6088), 533–536 (1986)CrossRefGoogle Scholar
  3. 3.
    Kuniyoshi, Y., Yorozu, Y., Suzuki, S., Sangawa, S., Ohmura, Y., Terada, K., Nagakubo, A.: Emergence and development of embodied cognition: A constructivist approach using robots. Prog. Brain Res. 164, 425–445 (2007)CrossRefGoogle Scholar
  4. 4.
    Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuron-like adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst., Man, Cybern. SMC-13(5), 834–846 (1983)CrossRefGoogle Scholar
  5. 5.
    Doya, K.: Reinforcement learning in continuous time and space. Neural Comput. 12(1), 219–245 (2000)CrossRefGoogle Scholar
  6. 6.
    Tedrake, R., Zhang, T.W., Seung, H.S.: Stochastic policy gradient reinforcement learning on a simple 3D biped. In: Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., pp. 2849–2854 (2004)Google Scholar
  7. 7.
    Astrom, K.J., Wittenmark, B.: Adaptive Control. Addison-Wesley, Reading (1989)Google Scholar
  8. 8.
    Slotin, J.E., Li, W.: Applied Nonlinear Control. Prentice-Hall, Englewood Cliffs (1991)Google Scholar
  9. 9.
    Zadeh, L.A.: Outline of a new approach to the analysis of complex systems and decision processes. IEEE Trans. Syst. Man, Cybern. SMC-3(1), 28–44 (1973)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Juang, J.G.: Fuzzy neural network control CMAC of a biped walking robot. IEEE Trans. Syst., Man, Cybern. B, Cybern. 30(4), 594–601 (2000)CrossRefGoogle Scholar
  11. 11.
    Shimoda, S., Kimura, H.: Bio-mimetic Approach to Tacit Learning based on Compound Control. IEEE Transactions on Systems, Man, and Cybernetics- Part B 40(1), 77–90 (2010)CrossRefGoogle Scholar
  12. 12.
    Shimoda, S., Kimura, H.: Adaptability of tacit learning in bipedal locomotion. IEEE Transactions on Autonomous Mental Development 5(2), 152–161 (2013)CrossRefGoogle Scholar
  13. 13.
    Hayashibe, M., Shimoda, S.: Emergence of Motor Synergy in Vertical Reaching Task via Tacit Learning. In: International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 4985–4988 (2013)Google Scholar
  14. 14.
    Cheah, C.C., Hirano, M., Kawamura, S., Arimoto, S.: Approximate Jacobian control for robots with uncertain kinematics and dynamics. IEEE Transactions on Robotics and Automation 19(4), 692–702 (2003)CrossRefGoogle Scholar
  15. 15.
    Dixon, W.E.: Adaptive regulation of amplitude limited robot manipulators with uncertain kinematics and dynamics. IEEE Transactions on Automatic Control 52(3), 488–493 (2007)CrossRefGoogle Scholar
  16. 16.
    Ozawa, R., Oobayashi, Y.: Adaptive task space PD control via implicit use of visual information. In: Int. Sym. Robot Control, pp. 209–214 (2009)Google Scholar
  17. 17.
    Smith, R.: Open Dynamics Engine, http://www.ode.org/
  18. 18.
    Shimoda, S., Yoshihara, Y., Fujimoto, K., Yamamoto, T., Maeda, I., Kimura, H.: Stability analysis of tacit learning based on environmental signal accumulation. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, October 7-12 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Vincent Berenz
    • 1
  • Fady Alnajjar
    • 1
  • Mitsuhiro Hayashibe
    • 2
  • Shingo Shimoda
    • 1
  1. 1.BSI-Toyota Collaboration Center, RIKENNagoyaJapan
  2. 2.INRIA DEMAR Project and LIRMM, UMR5506CNRS University of MontpellierMontpellierFrance

Personalised recommendations