Modeling of Elastic Robotic Arm using a Soft-Computing Algorithm

Abstract

This paper proposes the use of the least square support vector machine (LS-SVM) algorithm to model an elastic robotic arm. Dynamic system modeling is important as the first step in obtaining a suitable controller for any system. Acquiring an accurate model of elastic robotic based on input-output measurements using the LS-SVM algorithm requires less knowledge about the physical-laws of the system. The LS-SVM algorithm achieves global, unique solution, and requires less training time compared with other soft computing algorithms. In this paper, a successful use of the LS-SVM algorithm to model the elastic robotic arm as multi-input multi-output system is demonstrated. The simulation results illustrate the efficiency and high performance of the proposed approach.