A fuzzy logic approach for handling imprecise measurements in robotic assembly

Abstract

The problem of part mating and assembly with close tolerances is addressed. A position sensitive compliant wrist has been used in conjunction with a fuzzy logic system for ascertaining and correcting positional error. The methodology used involves correlating sensory inputs, via a fuzzy algorithm, into an offset vector. Experimentation with this system was carried out with a peg-in-hole precision assembly scenario. It has been shown that this device along with the fuzzy logic approach gives better results than a purely deterministic model.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>