Abstract
Human upright vertical position is unstable. A continuous activation of postural muscles is therefore required to avoid falling down. The problem is complicated by the reduced dimension of the support base (the feet) and by the articulated structure of the human skeleton. Nevertheless, upright posture is a capability, which is learnt in the first year of life. Here, the learning process is investigated by using neural networks models and the reinforcement learning paradigm. After creating a mechanically realistic digital human body, a parametric feed-back controller is defined. It outputs a set of joint torques as a function of orientation and rotational velocity of the body segments. The controller does not have any information either on the model of the human body or on the suitable set of its parameters. It learns the parameters which allow the controller to maintain the vertical position, through trial-and-error (success-fail) by using reinforcement learning. When learning is completed, the kinematics behaviour qualitatively resemble that of real experiments. The amplitude of the oscillations is larger than in the real case; this is due to the lack of any explicit penalization of the oscillations amplitude. The kinematics resembles the real one also when the body has to maintain the vertical upright position facing a tilt or displacement of the support base.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Pedotti A. A study of motor coordination and neuromuscular activities in human locomotion. Biol. Cybern., 26:53–62, 1977.
Pedotti A., Krishnan V. V., and Stark L. Optimization of muscle-force sequencing in human locomotion. Math. Biosc., 38:57–76, 1978.
A. G. Barto, R. S. Sutton, and C. W. Anderson. Neuronlike adaptive elements that can solve difficult learning problems. IEEE Trans. Syst. Man and Cybern., 13:834–846, 1983.
Ghez C. Posture. Elsevier, 1991.
de Leva P. Joint center longitudinal positions computed from a selected subset of chandler’s data. J. Biomechanics, 9:1231–1233, 1996.
Lacquaniti F., Maioli C., Borghese N. A., and Bianchi L. Posture and movement: Coordination and control. Archives Italiannes de Biologie, 135:353–367, 1997.
Massion J. Postural contol system. Curr. Opin. Neurobiol., 4:877–887, 1994.
L. P. Kaelbling, M. L. Littman, and A. W. Moore. Reinforcement learning: A survey. J. Artificial Intelligence Research, 4:237–285, 1996.
Kashima, Isurugi Y. T., and Shima M. Analysis of a muscular control system in human movements. Biol. Cybern., 82:”123–131”, 2000.
Nashner L.M. Fixed patterns of rapid postural responses among leg muscle during stance. Exp. Brain Res., 30:13–24, 1977.
Nigg B.M. and Herzog W. John Wiley and Sons, Toronto, 1999.
Bernstein N. Pergamon Press, Oxford, 1967.
Borghese N. A., Bianchi L., and Lacquaniti F. Kinematic determinants of human locomotion. J. of Physiology, 494(3):863–879, 1996.
R. Sutton T. Miller and P. Werbos, editors. MIT Press, 1990.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Borghese, N.A. (2002). Learning to Balance Upright Posture: What can be Learnt Using Adaptive NN Models?. In: Marinaro, M., Tagliaferri, R. (eds) Neural Nets. WIRN 2002. Lecture Notes in Computer Science, vol 2486. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45808-5_12
Download citation
DOI: https://doi.org/10.1007/3-540-45808-5_12
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44265-3
Online ISBN: 978-3-540-45808-1
eBook Packages: Springer Book Archive