Skip to Main Content
This paper proposes evolutionary wall-following control of a mobile robot using an interval type-2 fuzzy controller (IT2FC) with species-differential-evolution-activated continuous ant colony optimization (SDE-CACO). Both the position and speed of a mobile robot are controlled by using two IT2FCs to improve noise resistance ability. A new cost function is defined to accurately evaluate the wall-following performance of an evolutionary IT2FC. A two-stage training approach is proposed that learns a position IT2FC followed by a speed IT2FC to optimize both the wall-following accuracy and the moving speed. The proposed learning approach avoids the time consuming task of the exhaustive collection of supervised input-output training pairs. All fuzzy rules are generated online using a clustering-based approach during the evolutionary learning process. All of the free parameters in an online-generated IT2FC are optimized using SDE-CACO, in which an SDE mutation operation is incorporated within a continuous ACO to improve its explorative ability. The proposed SDE-CACO is compared with various population-based optimization algorithms to demonstrate its efficiency and effectiveness in the wall-following control problem. This study also includes experiments that demonstrate wall-following control utilizing a real mobile robot.