Performance Analysis of OWMR Directional Wheels Robot Arm based on (ANFIS+PID) controller

Abstract

The main objective of this study is to design an Adaptive Neuro Fuzzy Inference System (ANFIS) algorithm to solve the problem of finding the inverse kinematics to control the movement of the modified PUMA 560 arm in robotic system.Accuracy and stability are two major issues that face designers when control system design is intended. Tuning the system to coup with the variations and changes in the environment where the system is expected to work. In this paper the mechanical design of modified PUMA 560 robotic arm with 6 DoF was revisited and implemented with new powerful features and the experimental results were tracked. The main problem is the dynamic equations which are nonlinear and time-varying in the extreme. The challenge was how to manipulate these equations in such a way leading to a better performance regarding accuracy and stability of the system. The method used to control the base of robot arm which consists of 3-wheels with 120 degrees apart was designed and implemented. After that accurate trajectory control methods which use Adaptive Neuro Fuzzy Inference System of 3-wheels omni-directional mobile robot were implemented. Thus the design of full new robot system structure was used in the validation and testing the performance of proposed methods. This included modification of the PUMA 560 arm by the addition of an omini-directinal wheeled mobile robot (OWMR) base structure to the robotic arm. This base consisted of three motors for 3-wheels which are positioned 120 degrees apart. The resulting robot was a modified PUMA 560 robotic arm with 6 axes. The results obtained showed a significant improvement in both accuracy and stability of the system proposed. Hence, objectives were met to a great extent.