Transformation of human hand positions for robotic hand control

Abstract

A method for using the human hand as a multidegree-of-freedom teaching device is described. The algorithm is based on a functional analysis of the human hand and results in an algebraic transformation of human hand positions to corresponding positions in a target domain. The target domain should be of lower dimensionality (fewer degrees of freedom) than the human hand but is not constrained in any other way. The target described here is a sixteen-degree-of-freedom robotic hand, with four fingers of four joints each. The target need not, however be a handlike device but, for each use, should have a kinematic structure with poses similar in functionality to natural poses of the human hand.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>