ICANN 98 pp 419-424 | Cite as

A biologically inspired adaptive control architecture based on neural networks for a four-legged walking machine

  • W. Ilg
  • J. Albiez
  • H. Jedele
Part of the Perspectives in Neural Computing book series (PERSPECT.NEURAL)


This paper presents a biologically inspired adaptive control architecture for a four-legged walking machine. In this architecture neural networks are used in two different aspects. First, simple recurrent neural networks are used as coupled neuro-oscillators to represent elementary periodic movements. Second, Radial Basis Functions are employed as state space representation for a Reinforcement Learning component, with which superimposing and coordination of elementary movements are learned. In the development of the presented architecture some results of research on mammalian locomotion are included. The architecture is used to model intralimb coordination of the four-legged walking machine BISAM


Periodic Movement Elementary Movement State Space Representation Limb Segment Uneven Terrain 
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]
    A.G. Barto, R. S. Sutton, and Ch.W. Anderson. Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Transactions on Systems, Man and Cybernetics, SMC-13:834–846, 1983.CrossRefGoogle Scholar
  2. [2]
    T. G. Brown. On the nature of the fundemantal activity of the nervous centers. Journal of Physiologie, 1914.Google Scholar
  3. [3]
    M. Fischer and H. Witte. The functional morphology of the three-segmented limb of mammals and its specialities in small and medium-sized mammals. In European Mechanics Colloquium: Biology and Technology of Walking. Euromech 375, 1998.Google Scholar
  4. [4]
    R. Full. Opening lecture of the 1st Congress on Biomechanics Jena, Germany. BIONA Report, 1998.Google Scholar
  5. [5]
    W. Ilg, K. Berns, H. Jedele, J. Albiez, R. Dillmann, M. Fischer, H. Witte, J. Biltzinger, R. Lehmann, and N. Schilling. From small mammals to quadrupedal animats: Biologically inspired construction and control architecture for a four-legged walking machine. In From animals to animates: Fifth International Conference of the Society for adaptive Behaviour, 1998.Google Scholar
  6. [6]
    W. Ilg, Th. Mühlfriedel, K. Berns, and R. Dillmann. Hybrid Learning Concepts based on Self-organising Neural Networks for Adaptive Control of Walking Machines. Robotics and Autonomous Systems, 22(3):317–329, december 1997. Special Issue: Robot Learning — The new Wave.CrossRefGoogle Scholar
  7. [7]
    K. Matsuoka. Mechanisms of frequency and pattern control in the neural rhythm generators. Biological Cybernetics, 56:345–353, 1987.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 1998

Authors and Affiliations

  • W. Ilg
    • 1
  • J. Albiez
    • 1
  • H. Jedele
    • 1
  1. 1.Interactive Diagnosis- and ServicesystemsForschungszentrum Informatik KarlsruheKarlsruheGermany

Personalised recommendations