Neuro-Fuzzy Gait Generator for a Biped Robot

Abstract

The control of walking robots has improved dramatically over the last few years. Several methodologies have been developed for this. As one of them, in this work, we used fuzzy logic controller that generates angular of the knees in order to active a desired position of the center of mass. We present a fuzzy gait generator, FGG, that generates the angular trajectories of a biped robot. The FGG, is a neuro-fuzzy gait generator that used a classical geometric model of a 5 segments representation and replicated its comportment. The obtained controller has the same comportment of a classical geometric model and could be an alternative to it.