Solving inverse kinematics of delta robot using ANFIS

Abstract

The paper propose a methodology using the ability of ANFIS (Adaptive Neuro-Fuzzy Inference System) to solve inverse kinematics problem of Delta parallel robot. A five layer neural network of ANFIS is used to adjust input and output parameters of membership function in a fuzzy logic controller. The hybrid algorithm is used for training this network. In this algorithm, the least square estimation method is applied for the tuning of linear output membership function parameters and the error backpropagation method is used to tune the nonlinear input membership function parameters, it is possible to predict position end-effector exactly against inverse kinematics and reduce mathematical representation of the system. Virtual Reality (VR) is used to simulation trajectory of robot. Computer simulations with Matlab ver. 2013b conducted on 3DOF robot Delta shows the effectiveness of the approach.