A new type reduction method for type-2 fuzzy logic controller

Abstract

In interval type-2 fuzzy logic systems (IT2-FLSs), the inference engine outputs are type-2 fuzzy sets, and type reduction (TR) is needed to convert them into a type reduced set. Recently, researchers have proposed many efficient TR algorithms to find the boundary of the type reduced set, but they don't have an effective scheme to obtain the defuzzified crisp output. In this paper, we propose an optimal TR method, which searches the optimal point from the type reduced set as a defuzzified output. In order to demonstrate the effectiveness and superiority of the proposed method, simulations and comparisons are given. Simulation results show that the designed interval type-2 fuzzy logic controller (IT2-FLC) can smoothly achieve backing up control of the mobile robot from all initial positions.