Abstract
A planar 17 muscle model of the monkey's arm based on realistic biomechanical measurements was simulated on a Symbolics Lisp Machine. The simulator implements the equilibrium point hypothesis for the control of arm movements. Given initial and final desired positions, it generates a minimum-jerk desired trajectory of the hand and uses the backdriving algorithm to determine an appropriate sequence of motor commands to the muscles (Flash 1987; Mussa-Ivaldi et al. 1991; Dornay 1991b). These motor commands specify a temporal sequence of stable (attractive) equilibrium positions which lead to the desired hand movement.
A strong disadvantage of the simulator is that it has no memory of previous computations. Determining the desired trajectory using the minimum-jerk model is instantaneous, but the laborious backdriving algorithm is slow, and can take up to one hour for some trajectories. The complexity of the required computations makes it a poor model for biological motor control. We propose a computationally simpler and more biologically plausible method for control which achieves the benefits of the backdriving algorithm. A fast learning, tree-structured network (Sanger 1991c) was trained to remember the knowledge obtained by the backdriving algorithm. The neural network learned the nonlinear mapping from a 2-dimensional cartesian planar hand position {x, y} to a 17-dimensional motor command space {u 1, ..., u 17}. Learning 20 training trajectories, each composed of 26 sample points {{x y{,{u 1, ..., u 17} took only 20 min on a Sun-4 Spare workstation. After the learning stage, new, untrained test trajectories as well as the original trajectories of the hand were given to the neural network as input. The network calculated the required motor commands for these movements. The resulting movements were close to the desired ones for both the training and test cases.
Similar content being viewed by others
References
Bizzi E, Accornero N, Chapple W, Hogan N (1982) Arm trajectory formation in monkeys. Exp Brain Res 46:139–143
Bizzi E, Accornero N, Chapple W, Hogan N (1984) Posture control and trajectory formation during arm movements. J Neurosci 4:2738–2744
Carter RR, Crago PE, Keith M W (1990) Stiffness regulation by reflex action in the normal human hand. J Neurophysical 64:105–118
Dornay M (1990) Control of movement and the postural stability of the monkey's arm. Proc 3rd International Symposium on Bioelectronic and Molecular Electronic Devices, December 18–20, 1990, Kobe, Japan, pp 101–102
Dornay M (1991a) Control of movement, postural stability and muscle angular stiffness — A 17-muscle model of the monkey's arm. Proc IEICE Neuro-Computing Meeting, NC90-106, March 18–19, Tokyo, Japan, pp 225–230
Dornay M (1991b) Static analysis of posture and movement, using a 17-muscle model of the monkey's arm. ATR technical report TR-A-0109, pp 1–46
Dornay M (1991c) Control of movement, postural stability, and muscle angular stiffness. Proc IEEE Int Conf on Systems, Man and Cybernetics, October 13–16, Charlottesville, Virginia, USA, pp 1373–1379
Feldman AG (1966) Functional tuning of nervous system with control of movement or maintenance of a steady posture. III. mechanographic analysis of the execution by man of the simplest motor task. Biophysics 11:766–775
Feldman AG (1986) Once more on the equilibrium-point hypothesis (gamma model) for motor control. J Motor Behav 18:17–54
Feldman AG, Adamovich SV, Ostry DJ, Flanagan JR (1990) The origin of electromyograms-explanations based on the equilibrium point hypothesis. In: Winters JM, Woo SLY (eds) Multiple muscle systems: biomechanics and movement organizations. Springer Berlin Heidelberg New York, pp 195–213
Flash T (1987) The control of hand equilibrium trajectories in multi-joint arm movements. Biol Cybern 57:257–274
Flash T, Hogan N (1985) The coordination of arm movements: an experimentally confirmed mathematical model. J Neurosci 5:1688–1703
Georgopoulos A (1986) On reaching. Annual Review of Neuroscience 9:147–170
Hogan N (1984) An organizing principle for a class of voluntary movements. J Neurosci 4:2745–2754
Jordan ML (1990) Motor learning and the degrees of freedom problem. In: Jeannerod M (eds) Attention and performance XIII. Lawrence Erlbaum, Hillsdale, New Jersey, pp 796–836
Katayama M, Kawato M (1992) Virtual trajectory and stiffness ellipse during multi-joint arm movement predicted by neural inverse models. ATR technical report TR-A-0144, pp 1–32
Kawato M (1992) Optimization and learning in neural networks for formation and control of coordinated movement. In: Mayer D (eds) Attention and performance XIV. Lawrence Erlbaum, Hillsdale, New Jersey: (in press)
KlopfensteinRW, Sverdlove R (1983) Approximation by uniformly spaced gaussian functions. In: Chui CK, Schumaker LL, Ward JD (eds) Approximation Theory, vol IV. Academic Press, pp 575–580
Massone L, Bizzi E (1989) A neural network model for limb trajectory formation. Biol Cybern 61:417–425
Miller WT, Glanz FH, Kraft LG (1987) Application of a general learning algorithm to the control of robotic manipulators. Intl J Robot Res 6:84–98
Morasso P (1981) Spatial control of arm movements. Exp Brain Res 42:223–227
Mussa-Ivaldi FA, Hogan N, Bizzi E (1985) Neural, mechanical and geometric factors subserving arm posture in humans. J Neurosci 5:2732–2743
Mussa-Ivaldi FA, Morasso P, Hogan N, Bizzi E (1991) Network models of motor systems with many degrees of freedom. In: Fraser MD (eds) Advances in control networks and large scale parallel distributed processing models. Albex Publ Corp, Norwood, N. J. pp171–220
Nichols TR, Houk JC (1976) Improvement in linearity and regulation of stiffness that results from action of stretch reflex. J Neurophysiol 39:119–142
Poggio T, Girosi F (1989) A theory of networks for approximation and learning. MIT AI Memo 1140
Powell MJD (1987) Radial basis functions for multivariable interpolation. In: Mason JC, Cox MG (eds) Algorithm for approximation. Clarendon Press, Oxford, pp 143–167
Rack PMH, Westbury DR (1969) The effects of length and stimulus rate on tension in isometric cat soleus muscle. J Physiol 204:443–460
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. In: Parallel distributed processing, MIT Press, Cambridge pp 318–362
Sanger TD (1991a) A tree-structured adaptive network for function approximation in high-dimensional spaces. IEEE Trans Neural Networks 2:285–293
Sanger TD (1991b) Basis function trees as a generalization of local variable selection methods for function approximation. In: Lippmann RP, Moody JE, Touretzky DS (eds) Advances in neural information processing systems 3, Morgan Kaufmann, Proc NIPS'90, Denver Co. pp 700–706
Sanger TD (1991c) A tree-structured algorithm for reducing computation in networks with separable basis functions. Neural Computat 2:67–78
Uno Y, Kawato M, Suzuki R (1989) Formation and control of optimal trajectory in human multi joint arm movement — minium torque-change model. Biol Cybern 61:89–101
Widrow B, Hoff ME (1960) Adaptive switching circuits. In: IRE WESCON Conv Record, Part 4, pp 96–104
Zeffiro TA (1986) Motor adaptations to alterations in limb mechanics. Ph.D. Thesis, Dept of Brain and Cognitive Sciences, MIT, USA
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Dornay, M., Sanger, T.D. Equilibrium point control of a monkey arm simulator by a fast learning tree structured artificial neural network. Biol. Cybern. 68, 499–508 (1993). https://doi.org/10.1007/BF00200809
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00200809