Vectorization of robot dynamics on a pipelined vector processor

Abstract

A computational scheme for a pipelined vector processor for robot inverse dynamics is presented. Vectorization of the inverse dynamics computation is achieved while the dynamics formulation still remains within the general linear recursive framework, which is based on Newton-Euler equations and originally designed for scalar processing. Parametric studies were conducted on a commercially available pipelined vector processor. It is shown that the factor 1.82 of the speedup is achieved through vectorization for the inverse dynamics computation of a general six-degree-of-freedom robot manipulator.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>