Continuous ant optimized type-2 fuzzy controller for accurate mobile robot wall-following control

Abstract

This paper proposes the design of an interval type-2 fuzzy controller (IT2FC) using a rule-based continuous ant colony optimization (RCACO). The design approach is then applied to control a mobile robot for wall following task. The IT2FC uses interval type-2 fuzzy sets in the antecedent part. The RCACO finds solutions in a real space by using ant path selection and refinement by group-best-ant attraction operations. All of the free-parameters in an IT2FC are optimized using the RCACO to find an accurate control result. In the robot wall-following control application, a new cost function is proposed to accurately measure the wall-following performance. With the proposed cost function and the RCACO-designed IT2FC, neither a priori training data collection nor human expert knowledge is required in designing the IT2FC, which eases the design effort. Simulation results verify the effectiveness of the design approach and the noise resistance ability of the type-2 fuzzy controller.