An Improved Inverse Kinematics Solution for a Robot Arm Trajectory Using Multiple Adaptive Neuro-Fuzzy Inference Systems

Abstract

Inverse kinematics of robots is a critical topic in the robotics field. Although there are conventional ways of solving inverse kinematics, soft computing is an important technology that has lately gained prominence due to its ability to reduce the complexity of the inverse kinematics problem. This paper presents an inverse kinematics solution using multiple adaptive neuro-fuzzy inference systems (MANFIS). Different models were established by employing various methods of identification. Subtractive Clustering (SCM), Fuzzy C-Means Clustering (FCM), and Grid Partitioning (GP) are the three methods used in this study. This work is being carried out on a 5-DOF articulated robot arm, which is commonly used in industry. A mathematical model is built based on the Denavit-Hartenberg (DH) approach. Following confirmation that the kinematic findings of the mathematical model match the actual observed values of the robot arm, two types of data sets are generated: a random data set and a systematic data set based on a trajectory. The data sets are then utilized to train and evaluate ANFIS models and choose the optimal models to develop MANFIS model. Thus, the prediction and experimental data are compared to assess the performance of the MANFIS model.