Neural Networks Identification and Control of Mobile Robot Using Adaptive Neuro Fuzzy Inference System

Abstract

This paper developed and investigates the performance of intelligent algorithms in order to stabilize the robot when it is tracking to the desired reference. One type of robot is a Two Wheeled Balancing Mobile Robot (TWBMR) that requires control for both balancing and maneuvering. Combination artificial intelligence, Neural Networks (NNs) and Fuzzy Logic Control (FLC) have been recognized as the main tools to improve the performance of coupling nonlinear robot system without using any mathematical model. The input-output data of TWBMR generated from closed loop control system is used to develop a neural network model. In this study, neural networks model can be trained offline and then transferred into a process where an adaptive online learning is carried out using Adaptive Network Based Fuzzy Inference System (ANFIS) to improve the system performance. The simulation results verify that the considered identification and control strategies can achieve favorable control performance. The ANFIS control design approach does not require an accurate model of the plant as classical controller. In addition, high-level knowledge of the system is not needed to build a set of rules as a fuzzy controller.