A biologically inspired fitness function for robotic grasping

Abstract

This paper describes the innovative use of genetic programming (GP) to solve the grasp synthesis problem for multifingered robot hands. The goal of our algorithm is to select a grasp of an object, given some information about the object geometry and some user- defined which intuitively delineate good from bad grasp qualities. The fitness functions are used by the specially designed genetic program, which iteratively selects the grasp. This paper describes in detail the fitness function used to obtain the best grasps for multiple objects. The approach is biologically inspired in the choice of fitness functions, which adapt intuition from nature to guide the evolution process.