A Hybrid Inverse Kinematic Solution for Trajectory Tracking of Industrial Robot Manipulator.

This paper introduces a novel method based on Adaptive Neuro-Fuzzy Inference System (ANFIS) and Optimization technique for calculating the Inverse Kinematics (IK) of a six Degree of Freedom (DoF) industrial robotic manipulator, ABB IRB 1200. The effect of different membership function in single ANFIS application is studied and best-fitted network is selected for ANFIS evaluation, which guaranteed a significant reduction in convergence time. This network predicts the best-suited joint angles and the predicted angles act as the initial condition to start optimization search in order to get the optimum values. The experimental studies carried out illustrate the effectiveness of proposed approach while tracking a given trajectory without violating the mechanical joint limit constraints. This method is highly accurate, efficient in terms of computation time and is applicable to any serial robot having higher DoF as it requires only direct kinematic equations. [ABSTRACT FROM AUTHOR]