Optimal Location of Path Following Tasks in the Workspace of a Manipulator Using Genetic Algorithms

Abstract

In this paper a method is presented, for estimating the best location, from dexterity point of view, of a path following task into the workspace of an industrial manipulator. The best location of the path is defined as the location with the higher mean value of the manipulability along the path. The optimisation problem is formulated in a procedural way and solved using Genetic Algorithms (GA). The efficiency of the method is demonstrated through experiments carried out on a planar manipulator and on a PUMA robot in a simulation environment.