EJONS INTERNATIONAL JOURNAL ON MATHEMATICS, ENGINEERING & NATURAL SCIENCES ISSN 2602 - 4136

Quick Access


Bu Dergi DOI ve Crosscheck üyesidir


ARTIFICIAL NEURAL NETWORK APPLICATION FOR INVERSE KINEMATIC SOLUTION OF A 5-DOF ROBOTIC ARM
(ARTIFICIAL NEURAL NETWORK APPLICATION FOR INVERSE KINEMATIC SOLUTION OF A 5-DOF ROBOTIC ARM )

Author : Aysun Eğrisöğüt Tiryaki    
Type :
Printing Year : 2020
Number : 16
Page : 965-977
Cite : Aysun Eğrisöğüt Tiryaki , (2020). ARTIFICIAL NEURAL NETWORK APPLICATION FOR INVERSE KINEMATIC SOLUTION OF A 5-DOF ROBOTIC ARM. EJONS INTERNATIONAL JOURNAL ON MATHEMATICS, ENGINEERING - NATURAL SCIENCES, 16, p. 965-977. Doi: 10.38063/ejons.362.
    


Summary

The inverse kinematic solution is one of the major problems for real time application of robot control. The conventional solution methods such as geometric, algebraic and numerical iterative are insufficient and slow in the inverse kinematic solution. Recently, different solution methods based on artificial intelligence techniques have been developed in order to solve inverse kinematics of especially redundant robots and to reduce the solution time. In this study, an Artificial Neural Network (ANN) model was designed to solve the inverse kinematics of the 5 degrees of freedom (DOF) robotic arm. Network was trained using database obtained from the experimental setup and ANN model was validated by experimental works. The Neural Network (NN) calculated the joint angles with high accuracy with respect to the given (x, y, z) Cartesian coordinates. The comparison results show that the proposed NN has a high correlation (R=0.9988) and superior performance for solving inverse kinematics of the robotic arm.



Keywords
Inverse kinematics, Robotic arm, Artificial neural network

Abstract

The inverse kinematic solution is one of the major problems for real time application of robot control. The conventional solution methods such as geometric, algebraic and numerical iterative are insufficient and slow in the inverse kinematic solution. Recently, different solution methods based on artificial intelligence techniques have been developed in order to solve inverse kinematics of especially redundant robots and to reduce the solution time. In this study, an Artificial Neural Network (ANN) model was designed to solve the inverse kinematics of the 5 degrees of freedom (DOF) robotic arm. Network was trained using database obtained from the experimental setup and ANN model was validated by experimental works. The Neural Network (NN) calculated the joint angles with high accuracy with respect to the given (x, y, z) Cartesian coordinates. The comparison results show that the proposed NN has a high correlation (R=0.9988) and superior performance for solving inverse kinematics of the robotic arm.



Keywords
Inverse kinematics, Robotic arm, Artificial neural network

Advanced Search


Announcements

    EYLÜL Sayısı

    VERBİS'E KAYIT S�RELERİ HAKKINDA DUYURU | Kırklareli Ticaret ve ...

    EYLÜL ayında yayınlanacak Sayımız için  20 AĞUSTOSTarihine kadar çalişmanızı Yükleyebilirsiniz



Address :Kazakh National Women's Pedagogical University, Almatı, Kazakhistan
Telephone :+7 778 921 0336 - 0 534 349 92 73 Fax :
Email :ejonsjournal@gmail.com

Web Yazılım & Programlama Han Yazılım Bilişim Hizmetleri