Medical and Biological Engineering and Computing

, Volume 32, Issue 6, pp 610–614 | Cite as

Application of an artificial neural network to the control of an active external orthosis of the lower limb

  • D. Guiraud
Computing and Data Processing

Abstract

The object of this paper is to present a real-time application of an artificial neural network (ANN). The application for which this network is demonstrated is a motorised orthosis with six degrees-of-freedom for use by a paraplegic; a ‘walking machine’. Theoretical networks and training methods need modification to function correctly with a real application. Several complex phenomena that are very diffucult to model have to be accommodated; the starting threshold of the activators, nonlinearity, noise, and the non-biunivocity between successive system states (position, velocity, actuator controls). The modifications made to the network and the associated training method partially alleviate these difficulties.

Keywords

Active external orthosis Feedback control Gait restoration Neural network 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Abbas, J. J., andChizec, H. J. (1991): ‘A neural controller for functional neuromuscular stimulation systems’,Proc. IEEE Eng. Med. Biol. Soc.,13, pp. 1456–1457Google Scholar
  2. Beckmann, J., Daunicht, W. J., andHömberg, V. (1992): ‘Control of a paraplegic patient’. Proc. ICANN 92, Brighton, UK 4–7 SeptemberGoogle Scholar
  3. Bleuler, H., Diez, D., Lauber, G., Meyer, U., andZlatnik, D. (1990): ‘Non-linear neural network control with application example’. Proc. INNC 90, Paris, France,1, pp. 201–204Google Scholar
  4. Colombano, P., Compton, M., andBualat, M. (1991): ‘Goal directed model inversion: adaptation to unexpected model changes’. Proc. Neuro-Nîmes, Nîmes, France, 4–8 November, pp. 269–278Google Scholar
  5. Hornik, K., Stinchcombe, M., andWhite, H. (1990): ‘Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks’,Neural Netw.,3, pp. 551–560CrossRefGoogle Scholar
  6. Jacobs, R. A. (1988): ‘Increased rates of convergence through learning rate adaptation’,,1, pp. 295–307CrossRefGoogle Scholar
  7. Phillips, C. A., andHendershot, D. M. (1991): ‘A system approach to medically prescribed functional electrical stimulation. Ambulation after spinal cord injury’,Paraplegia,29, pp. 505–513Google Scholar
  8. Rabischong, E., Sgarbi, F., Rabischong, P., Detriche, J. M., Pinguet, N., andRiwan, A. (1990): ‘Control and command of a six degrees of freedom active electrical orthosis for paraplegic patient’. Proc. IEEE Int. Workshop on Intelligent robots and systems, pp. 987–991Google Scholar
  9. Rose, G. K. (Ed.) (1986): ‘Orthotics, principles and practice’ (William Heinemann Medical Books, London, UK) pp. 176–189Google Scholar
  10. Rumelhart, D. E., andMacClelland, C. L. (Eds.) (1986): ‘Parallel distributed processing, exploration in the microstructure of cognition’ (PDP Research Group, MIT Press, Cambridge, Massachusetts, USA) Vol. 1Google Scholar
  11. Tollenaere, T. (1990): ‘SuperSAB: fast adaptative back propagation with good scaling properties’,Neural Netw.,3, pp. 561–573CrossRefGoogle Scholar

Copyright information

© IFMBE 1994

Authors and Affiliations

  • D. Guiraud
    • 1
    • 2
  1. 1.Institut National de la Santé et de la Recherche Médicale, U103Appareil Moteur et HandicapMontpellierFrance
  2. 2.MXM S.A., Quartier Croix RougeAntibesFrance

Personalised recommendations