Radial Basis Gaussian Functions for Modelling Motor Learning Process of Human Arm Movement in the Ballistic Task – Hit a Target

Mathematical tool for modelling motor learning of human arm movement in the ballistic task – hit a target is described in this paper. Proposed tool is used for quantification of the subject’s ability to learn motor control of their arm movements in the ballistic task after training. Conducted research showed that the key role in the ballistic task – hit the target had velocity profiles of the arm/joystick movement. Therefore, the velocity profiles have been an object of refined analysis and modelling performed for the purpose of determining whether motor learning of humans arm movement is possible or not. Radial Basis Gaussian Functions (RBGF) are used as a tool for analysis and modelling, because they can reveal behaviour of human’s arm movement around more local points or in the more stages of movement. The proposed tool is verified by conducted experimental analysis. The experimental analysis was performed as practice of 50 subjects in the ballistic task – hit a target.

[1]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[2]  Angel R. Martinez,et al.  Computational Statistics Handbook with MATLAB , 2001 .

[3]  E Bizzi,et al.  Motor learning through the combination of primitives. , 2000, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[4]  Reza Shadmehr,et al.  Learning the dynamics of reaching movements results in the modification of arm impedance and long-latency perturbation responses , 2001, Biological Cybernetics.

[5]  Reza Shadmehr,et al.  Learning of action through adaptive combination of motor primitives , 2000, Nature.

[6]  Jun Nakanishi,et al.  Learning Movement Primitives , 2005, ISRR.

[7]  P. R. Davidson,et al.  Motor learning and prediction in a variable environment , 2003, Current Opinion in Neurobiology.

[8]  Chris Bishop,et al.  Improving the Generalization Properties of Radial Basis Function Neural Networks , 1991, Neural Computation.

[9]  F A Mussa-Ivaldi,et al.  Adaptive representation of dynamics during learning of a motor task , 1994, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[10]  S. Schaal.  Dynamic Movement Primitives -A Framework for Motor Control in Humans and Humanoid Robotics , 2006 .

[11]  Angel R. Martinez,et al.  : Exploratory data analysis with MATLAB ® , 2007 .

[12]  A. Christopoulos,et al.  Fitting Models to Biological Data Using Linear and Nonlinear Regression: A Practical Guide to Curve Fitting , 2004 .