Incorporation of negative rules into fuzzy inference systems

Abstract

This paper considers the incorporation of negative examples into fuzzy inference systems (FIS). A new method of defuzzification called dot product attenuation is presented. This is a generalization of conventional defuzzification which has the ability to incorporate negative examples into the FIS's reasoning process. The method is illustrated with an inverted pendulum controller which has a negative rule added to its rule base. The modification of the control surface due to the introduction of the negative rule is investigated. Simple control of the path of a robot in the presence of obstructions using dot product attenuation is demonstrated.