Optimal Design and Performance Comparison of a Combined ANFIS-PID with Back Stepping Technique, Using Various Meta-Heuristic Algorithms to Solve Wheeled Mobile Robot Trajectory Tracking Problem

Abstract

The present investigation suggests a novel control technique that merge the advantage of the adaptive Neuro-Fuzzy inference system (ANFIS) with the proportional integral derivative (PID) controller, abbreviated as (ANFIS-PID), for dealing with the dynamics of the of wheeled mobile robot (WMR). A comparative study of various meta-heuristic optimization algorithms is made. The results revealed the highest efficiency of the suggested ANFIS-PID technique compared to seven designed PID controllers, in terms of settling and rise time, overshoot, and the integral square error (ISE) as a cost function. Various cases, study (circular path, diamond path, zigzag path) have highlighted the over performance of mentioned controller. Moreover, this hybrid technique is fused with backstepping approach for the kinematic control. A lemniscate and a square trajectory were performed to clarify the capability of the mentioned controller.