Localized Neural Network Control of Spring Actuated Leg

  • Tom Wadden
  • Örjan Ekeberg


For any animal to move about in an unstructured and dynamic environment it must have an adaptable locomotor control system. In legged vertebrates much of this control is handled by local circuits in the spinal cord [3]. The object of a neural controller is to lead the mechanical system through the proper motion pattern. This system must strive to be energy efficient, a task which is enabled through the use of springs in the form of muscle tendons [1]. Our simulated model incorporates local circuitry, series elasticity, sensory feedback and higher level control.


Stance Phase Sensory Feedback Step Cycle Control Neuron Neural Controller 
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]
    Alexander, R. M. (1988). Elastic mechanisms in animal movement. Cambridge: Cambridge University Press.Google Scholar
  2. [2]
    Ekeberg, Ö. (1993). A combined neuronal and mechanical model offish swimming. Biol. Cybern. 69: 363–374.Google Scholar
  3. [3]
    Grillner, S. (1996). Neural networks for vertebrate locomotion. Scientific American 274: 64–69.PubMedCrossRefGoogle Scholar
  4. [4]
    Tax, A. A. M. and Denier van Der Gon, J. J. (1991). A model for neural control of gradation of muscle force. Biol. Cybern. 65: 227–234.PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1997

Authors and Affiliations

  • Tom Wadden
    • 1
  • Örjan Ekeberg
    • 1
  1. 1.SANS—Studies of Artificial Neural Networks NADA—Department of Numerical Analysis and Computing ScienceRoyal Institute of TechnologyStockholmSweden

Personalised recommendations