Accurate Modeling and NN to Reproduce Human Like Motion Trajectories

  • Pietro Cerveri
  • Giuseppe Andreoni
  • Giancarlo Ferrigno
Conference paper
Part of the Advances in Soft Computing book series (AINSC, volume 18)


Due to increasingly and massive use of simulation for studying man-workplace interaction, virtual design and CAD systems will be more and more concerning with virtual actors able to emulate the real human motion, with high resemblance. In this work we present some results related to the attempt of synthetically generating human like motion trajectories to drive a model of a human arm. The problem of producing human-like trajectories of complex articulated structures has been re-framed as the issue of computing the parameters of a neural network through a large redundant data set, without involving a mathematical model of either direct or inverse kinematics. In particular, reaching and pointing motor tasks have been considered and tested on a human model. The kinematics has been described in terms of joint angles computed from a set of 3D trajectories of markers, located onto the subject and acquired by means of an opto-electronic motion analyzer. Our approach for movement simulation has been based on a multi-layer perceptron able to predict the trajectory of an arm (three sticks model) in term of joint angles by specifying only the starting and the final position (3D coordinates) of the end-effector. Results, in term of residual errors in training and extrapolation properties, show the reliability of the proposed method.


Joint Angle Inverse Kinematic Kinematic Chain Neural Network Training Virtual Actor 
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].
    N.I. Badler, “Human factors simulation research at the University of Pennsylvania. Computer graphics research quarterly progress report No. 38,” Department of Computer and Information Science. University of Pennsylvania. Fourth Quarter 1–17, 1990.Google Scholar
  2. [2].
    P. Bapu, M. Koma and J. McDaniel, “User’s guide for COMBIMAN programs (COMputerized Biomechanical MAN-model),” AFAMRLTech. Report pp. 83–97, 1983.Google Scholar
  3. [3]
    E.J. Szmrecsanyl, “CYBERMAN — An interactive computer graphics manikin for human factors analysis,” Control Data Corporation. Worldwide User Conference.Google Scholar
  4. [4].
    M. Cavazza, R. Earnshaw, N. Magnenat-Thalmann and D. Thalmann, “Motion control of virtual humans,” IEEE Computer Graphics and Applications, vol. 18, pp. 24–31, 1998.CrossRefGoogle Scholar
  5. [5].
    H. Cruse, U. Steinkühler, “Solution of the direct and inverse kinamatic problems by a common algorithm based on the mean of multiple computations,” Biol. Cybern., vol. 69, pp. 345–351, 1993.CrossRefGoogle Scholar
  6. [6].
    H. Cruse, “Constraints for joint angle control of the human arm,” Biol. Cybern., vol. 54, pp. 125–132, 1986.CrossRefGoogle Scholar
  7. T. Yoshikawa, “Manipulatability and redundancy of robotic mechanism,” Proceeding of the 1985 IEEE,Computer Society Press, Silver Spring, Md, 1004-1009.Google Scholar
  8. [8].
    T. Flash, N. Hogan, “The co-ordination of the arm movements: an experimentally confirmed mathematical model,” Journal of neuroscience, vol. 7, pp. 1688–1703, 1985.Google Scholar
  9. [9].
    Y. Uno, M. Kawato, R. Suzuki, “Formation and control of optimal trajectory in human arm movement,” Biol. Cybern., 61, pp. 89–101, 1989.CrossRefGoogle Scholar
  10. [10].
    M. Kawato, “Computational schemes and neural network models for formation and control of multijoint arm trajectory,” In: Neural Network for control ed. W.T. Miller III, R. Sutton and P. Werbos (1990), MIT Press.Google Scholar
  11. [11].
    M. Kawato, M. Isobe, Y. Uno and R. Suzuki, “Trajectory formation of arm movements by cascade neural network model based on minimum torque-change criterion,” Biol Cybern., vol. 62, pp. 275–288, 1990.CrossRefGoogle Scholar
  12. [12].
    J. C. Fiala, “A network for learning kinematics with application to human reaching models,” Proc. of the ICNN, 5, pp. 2759-2764, Orlando, FL, 1994.Google Scholar
  13. [13].
    P. Morasso and V. Sanguineti, “Self-organizing body-schema for motor planning,” J. Motor Behavior, vol. 26, pp. 131–148, 1995.Google Scholar
  14. [14].
    A. Pedotti and G. Ferrigno, “Opto-electronic based system,” in Three dimensional analysis of human movement, P. Allard, I.A.F. Stokes and J.P. Bianchi, pp. 57-77, Human Kinetics Publishers, 1995.Google Scholar
  15. [15].
    F. Lacquaniti, G. Ferrigno, A. Pedotti, J.F. Soechting and C. Terzuolo, “Changes in spatial scale in drawing and handwriting contributions by proximal and distal joints,” The journal of Neuroscience, vol. 7, no. 3, 1987.Google Scholar
  16. [16].
    Fletcher, R., and C.M. Reeves, “Function minimization by conjugate gradients,” Compute Journal, vol. 7, pp. 149–154, 1964.MATHCrossRefMathSciNetGoogle Scholar
  17. [17].
    U. Steinkühler, H Cruse, “A holistic model for an internal representation to control the movement of a manipulator with redundant degrees of freedom,” Biol. Cybern., vol. 79, pp. 457–466, 1998.CrossRefGoogle Scholar
  18. [18].
    N.A. Bernstein, “The co-ordination and regulation of movements,” Pergamon Press, New York, 1967.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Pietro Cerveri
    • 1
    • 2
  • Giuseppe Andreoni
    • 1
    • 2
  • Giancarlo Ferrigno
    • 1
    • 2
  1. 1.Dipartimento di BioingegneriaPolitecnico di MilanoMilanoItaly
  2. 2.Centro di BioingegneriaPolitecnico di Milano-Fondazione Pro Juventute Don Carlo Gnocchi ONLUSMilanoItaly

Personalised recommendations