Implementation of Inverse Kinematics using ANFIS in Modified PUMA 560 through Tracking Control of Omni-directional wheels

Abstract

In this paper Adaptive Neuro Inference System algorithm, implemented on microcontrollers, was utilized to obtain the solution of IK problem of PUMA 560 robot arm. The problem of accurate and precise displacement is an acute problem faced by designers and operatorsNeuro-Fuzzy systems have been developed to make a sensible merge of linguistic information processing capability of Fuzzy Inference Systems (FIS) and learning capability of neural networks to evolve systems, which have strong modeling capability as well as relatively easy interpretability from the user point of view It differentiates itself from normal fuzzy systems by the adaptive parameters, i.e., both the premise and consequent parameters are adjustable. One of the main goals of a control system is to make the system more stable by reducing the steady state error as fast as possible. There are many types of control systems that can be used such as PID, PD+I, FUZZY PD+I and Adaptive Neuro-Fuzzy Inference System ANFIS. The use of ANFIS proved to be very efficient in handling the accuracy precision problem. Results obtained in this paper showed that error could be decreased to as low as 0.21% using this system. Stability in performance which is another dominant factor was acceptable to a great extent without any serious overshooting or unacceptable delay.