Skip to main content

Estimation of dynamic joint torques and trajectory formation from surface electromyography signals using a neural network model

Abstract

In this study, human arm movement was re-constructed from electromyography (EMG) signals using a forward dynamics model acquired by an artificial neural network within a modular architecture. Dynamic joint torques at the elbow and shoulder were estimated for movements in the horizontal plane from the surface EMG signals of 10 flexor and extensor muscles. Using only the initial conditions of the arm and the EMG time course as input, the network reliably reconstructed a variety of movement trajectories. The results demonstrate that posture maintenance and multijoint movements, entailing complex via-point specification and co-contraction of muscles, can be accurately computed from multiple surface EMG signals. In addition to the model's empirical uses, such as calculation of arm stiffness during motion, it allows evaluation of hypothesized computational mechanisms of the central nervous system such as virtual trajectory control and optimal trajectory planning.

This is a preview of subscription content, access via your institution.

References

  1. Akazawa K, Takizawa H, Hayashi Y, Fujii K (1988) Development of control system and myoelectric signal processor for bio-mimetic prosthetic hand. Biomechanism 9:43–53

    Google Scholar 

  2. Basmajian JV, De Luca CJ (1985) Muscles alive. Williams & Wilkins, Baltimore

    Google Scholar 

  3. Bawa P, Stein R (1976) Frequency response of human soleus muscle. J Neurophysiol 39:788–793

    Google Scholar 

  4. Bennett D (1993) Electromyographic responses to constant position errors imposed during voluntary elbow joint movement in human. Exp Brain Res 95:499–508

    Google Scholar 

  5. Brown S, Cooke J (1990) Movement related phasic muscle activation. I. Changes with temporal profile of movement. J Neurophysiol 63:455–464

    Google Scholar 

  6. Clancy EA, Hogan N (1991) Estimation of joint torque from the surface EMG. Annual International Conference of the IEEE Engineering in Medicine and Biology Society 13:0877–0878

    Google Scholar 

  7. Dornay M, Uno Y, Kawato M, Suzuki R (1992) Simulation of optimal movements using the minimum-muscle tension-change model. In: Moody JM, Hanson SJ, Lippmann RP (eds) Advances in neural information processing systems 4. Morgan Kaufmann, San Mateo, pp 627–634

    Google Scholar 

  8. Gottlieb GL, Corcos DM, Agarwal GC (1989) Organizing principles for single-joint movements. I. A speed-insensitive strategy. J Neurophysiol 62:342–357

    Google Scholar 

  9. Jacobs R, Jordan M (1991) A competitive modular connectionist architecture. In: Moody JM, Hanson SJ, Lippmann RP (eds) Advances in neural information processing systems 3. Morgan Kaufmann, San Mateo, pp 767–773

    Google Scholar 

  10. Karst GM, Hasan Z (1991) Timing and magnitude of electromyographic activity for two-joint arm movements in different directions. J Neurophysiol 66:1594–1604

    Google Scholar 

  11. Katayama M, Kawato M (1993) Virtual trajectory and stiffness ellipse during multijoint arm movement predicted by neural inverse models. Biol Cybern 69:353–362

    Google Scholar 

  12. Kawato M (1992) Optimization and learning in neural networks for formation and control of coordinated movement. In: Meyer D, Kornblum S (eds) Attention and performance, XIV. MIT Press, Cambridge, Mass.

    Google Scholar 

  13. Koike Y, Kawato M (1993) Virtual trajectories predicted from surface EMG signals. Soc Neurosci Abstr 19:543

    Google Scholar 

  14. Koike Y, Kawato M (1994a) Estimation of arm posture in 3D-space from surface EMG signals using a neural network model. IEICE Trans Fundamentals D-II(4):368–375

    Google Scholar 

  15. Koike Y, Kawato M (1994b) Trajectory formation from surface EMG signals using a neural network model. IEICE Trans (D-II) J77(1):193–203 (in Japanese)

    Google Scholar 

  16. Koike Y, Honda K, Hirayama M, Gomi H, Bateson E-V, Kawato M (1992) Dynamical model of arm using physiological data. Tech Rep IEICE NC91-146, pp107–114 (in Japanese)

  17. Koike Y, Honda K, Hirayama M, Gomi H, Bateson E-V, Kawato M (1993) Estimation of isometric torques from surface electromyography using a neural network model. IEICE Trans (D-II) (6):1270–1279 (in Japanese)

  18. Mannard A, Stein R (1973) Determination of the frequency response of isometric soleus muscle in the cat using random nerve stimulation. J Physiol 229:275–296

    Google Scholar 

  19. Mori D, Tsuji T, Ito K (1992) Motion discrimination method from EMG signals using statistically structured neural networks. Tech Rep IEICE NC91-143, pp 83–90 (in Japanese)

  20. Nowlan S, Hinton G (1991) Evaluation of adaptive mixtures of competing experts. In: Moody JM, Hanson SJ, Lippmann RP (eds) Advances in neural information processing systems 3. Morgan Kaufmann, San Mateo, pp 774–780

    Google Scholar 

  21. Ochiai K, Usui S (1994) Kick-out learning algorithm to reduce the oscillation of weights. Neural Networks 7:797–807

    Google Scholar 

  22. Rack P, Westbury D (1969) The effects of length and stimulus rate on tension in the isometric cat soleus muscle. J Physiol 217:419–444

    Google Scholar 

  23. Rumelhart D, Hinton G, Williams R (1986) Learning representations by backpropagating errors. Nature 323:533–536

    Google Scholar 

  24. Soechting J, Roberts W (1975) Transfer characteristics between EMG activity and muscle tension under isometric conditions in man. J Physiol 70:779–793

    Google Scholar 

  25. Suzuki R, Suematsu T (1969) Pattern recognition of multi-channel myoelectric signals by learning method. Jpn J Med Electron Biol Eng 7:47–48 (in Japanese)

    Google Scholar 

  26. Uno Y, Kawato M, Suzuki R (1989a) Formation and control of optimal trajectory in human multijoint arm movement: minimum torque-change model. Biol Cybern 61:89–101

    Google Scholar 

  27. Uno Y, Suzuki R, Kawato M (1989b) Minimum-muscle-tension-change model which reproduces human arm movement. Proceedings of the 4th Symposium on Biological and Physiological Engineering, pp 299–302 (in Japanese)

  28. Wada Y, Kawato M (1992) A new information criterion combined with cross-validation method to estimate generalization capability. Syst Comput Jpn 23:92–104

    Google Scholar 

  29. Winters JM (1990) Hill-based muscle models: a systems engineering perspective. In: Winters JM, Woo SL-Y (eds) Multiple muscle systems. Springer Berlin Heidelberg New York, pp 69–93

    Google Scholar 

  30. Wood J, Meek S, Jacobsen S (1989) Quantitation of human shoulder anatomy for prosthetic arm control. II. Anatomy matrices. J Biomech 22:309–325

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Yasuharu Koike.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Koike, Y., Kawato, M. Estimation of dynamic joint torques and trajectory formation from surface electromyography signals using a neural network model. Biol. Cybern. 73, 291–300 (1995). https://doi.org/10.1007/BF00199465

Download citation

Keywords

  • Extensor Muscle
  • Trajectory Planning
  • Surface Electromyography
  • Modular Architecture
  • Trajectory Control