Hierarchical fuzzy control in robot soccer using evolving algorithms

Abstract

In this paper, an evolutionary algorithm is developed to learn a three layer hierarchical fuzzy knowledge base. This knowledge base is used in a fuzzy controller to control a micro-robot to hit the ball along the ball to goal line of sight from any configuration belonging to a grid of initial configurations. The inputs to the fuzzy controller are variables from a relative coordinate system and output change in wheel velocities. Forward and reverse facing impact with the ball and physical dimensions are included.