Forward Kinematic Analysis of 6-R Industrial Robot Using Active Sampled Neural Network Regressor

Abstract

This paper describes the estimation of robotic forward kinematics using Neural Network (NN). The quality of training data is highly essential for better accuracy of NN models. So, in this contribution, clustering-based refined training data selection is performed to improve the representativeness of the selected data. The k-means clustering algorithm is adopted to find the most distinct and informative training data. The 6-R MTAB Aristo-XT robot is selected as a case study to generate the experimental training and testing data for validation of ML techniques. Standard performance measures such as deviation error, Mean Square Error (MSE) are evaluated and graphical illustrations are presented for fair comparison of the results. Experimental results reveal that, instead of random sampling, the clustering-based active sampled training data selection is strongly suggested to improve the accuracy of NN regressor, and also it greatly reduces the time complexity to train the model.