Simulation and Visualization of Intelligent MIMO-ANFIS-Based Control System in Virtual Reality using MATLAB and V-Rep

The noteworthy increase in processing power of computers with the excess of open software and hardware standards has significantly changed the landscape in the field of 3D virtual robotics simulation platforms. Employing software computing tools, such as fuzzy logic, neural networks, and genetic algorithms, encouraged researchers to design intelligent systems that mimic human behavior. Designing a Multiple-Input Multiple-Output (MIMO) control system using Adaptive Nuero-Fuzzy System (ANFIS) offers easy and reliable solutions to generate the desired outputs without the need for a complex mathematical model. This paper shows a MATLAB-based MIMO ANFIS control system for two different robotic systems: a two-wheel drive (2WD) mobile robot and a six-degree of freedom (6DOF) robotic arm. The Virtual Robot Experimentation Platform (V-Rep) has been used to test the designed systems through a direct interface with the MATLAB Simulink. The results showed an acceptable error value of 0.002% in generating the desired outputs of the 2WD robot. On the other hand, the performance of the implemented ANFIS controller for the 6DOF robotic arm showed a high error value of 30% if the proposed method is used to design MIMO-ANFIS control system.