A fuzzy expert organizer for control of robotic part assembly

Abstract

A fuzzy intelligent organizing control strategy, based on a fuzzy rule-base and derived from measured force/moment data, for a robotic device performing quasi-static assembly tasks is presented. Fuzzy set theory is implemented as an expert system to constitute the organizer of a robotic system for micro tasking (part mating) purposes. A distance metric is employed to measure the uncertainty (fuzziness) as it is related to specific control actions. A learning algorithm based on the probability of a fuzzy event and a distance metric is introduced. The top organizing level determines the most appropriate n-tuple control values with minimum fuzziness and downlinks them to the lower level of the system which carries out the specified task. Experimental results show the effectiveness of the proposed approach.<>