Preprint: Linear combinations of nonlinear models

[Jim Patton]

The following paper has been accepted by Biological Cybernetics.

Preprints are available from:
<http://www.smpp.nwu.edu/~smpp_pub/PattonMussa-Ivaldi2001BiolCybern_preprint.htm>

LINEAR COMBINATIONS OF NONLINEAR MODELS FOR PREDICTING HUMAN-MACHINE
INTERFACE FORCES

James L. Patton & Ferdinando A. Mussa-Ivaldi
Sensory Motor Performance Program, Rehabilitation Institute of Chicago
Physical Medicine and Rehabilitation, Northwestern University Medical School

In press, Biological Cybernetics, May, 2001

ABSTRACT
This study presents a computational framework that capitalizes on known
human neuromechanical characteristics during limb movements in order to
predict man-machine interactions. A parallel-distributed approach, the
mixture of nonlinear models, fits the relationship between the measured
kinematics and kinetics at the handle of a robot. Each element of the
mixture represented the arm and its controller as a feedforward nonlinear
model of inverse dynamics plus a linear approximation of musculotendonous
impedance. We evaluated this approach with data from experiments where
subjects held a handle of a planar manipulandum robot and attempted to make
point-to-point reaching movements. We compared the performance to the more
conventional approach of a constrained, nonlinear optimization of the
parameters. On average, the mixture of nonlinear models accounted for 0.79 
0.11 (1 SD), and force errors were 0.73%  0.20% of the maximum exerted
force. Solutions were acquired in half the time with significantly better
fit. However, both approaches equally suffered from the simplifying
assumptions, namely, that the human neuromechanical system consisted of a
feedforward controller coupled with linear impedances and a moving state
equilibrium. Hence, predictability was best limited to the first half of the
movement. The mixture of nonlinear models may be useful in man-machine tasks
such as in telerobotics, fly-by-wire vehicles, robotic training and
rehabilitation.

______________________________________________________________________

J  A  M  E  S      P  A  T  T  O  N  ,     P  H .  D .
Research Scientist
Sensory Motor Performance Prog., Rehabilitation Institute of Chicago
Physical Med & Rehabilitation, Northwestern University Med
School
345 East Superior, Room 1406, Chicago, IL 60611
312-238-1277 (OFFICE)  -2208 (FAX)  -1232 (LAB)  -3381 (SECRETARY)
<http://www.smpp.northwestern.edu/~jim/>
<j-patton at northwestern.edu>
CELL PHONE MESSAGING (<150 char.): 8473341056 at msg.myvzw.com
______________________________________________________________________