Vectorization of robot inverse dynamics on a pipelined vector processor

This paper presents a computational scheme on a pipelined vector processor for robot inverse dynamics. Vectorization of the inverse dynamics computation is achieved while the dynamics formulation still remains within the general linear recursive framework. Parametric studies are conducted on a commercially available pipelined vector processor. The 1.82 speedup is achieved through vectorization for the inverse dynamics computation of a general six-degrees-of-freedom robot manipulator