Solving Inverse Kinematics for 3R Manipulator Using Artificial Neural Networks

Muhammad Esmat; Mohammed Abdel-Nasser; Abdul Wahid A. Saif

doi:10.1109/SSD58187.2023.10411151

Solving Inverse Kinematics for 3R Manipulator Using Artificial Neural Networks

Muhammad Esmat^*, Mohammed Abdel-Nasser, Abdul Wahid A. Saif^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Manipulator robots are one of the widely famous robotics types. One of the major problems that appear when preparing these robots is the Inverse Kinematic Problem (IKP). Overcoming the IKP in some cases requires solving complex equations, time-consuming, and can lead to singularity solutions. In this paper, a modeling of the forward kinematics for a 3-R manipulator robot was carried out to generate a dataset for supervised learning. Furthermore, a training model for solving the inverse kinematics of this robot with avoiding the singularity points based on Artificial Neural Networks (ANN) is proposed. The reliability of the method was validated by trajectory tracking. The results demonstrate the effectiveness of the robot to track the referenced path successfully with maximum mean absolute error in the X, Y, and Z axes around 1.375 mm.

Original language	English
Title of host publication	2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	116-120
Number of pages	5
ISBN (Electronic)	9798350332568
DOIs	https://doi.org/10.1109/SSD58187.2023.10411151
State	Published - 2023
Event	20th International Multi-Conference on Systems, Signals and Devices, SSD 2023 - Mahdia, Tunisia Duration: 20 Feb 2023 → 23 Feb 2023

Publication series

Name	2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023

Conference

Conference	20th International Multi-Conference on Systems, Signals and Devices, SSD 2023
Country/Territory	Tunisia
City	Mahdia
Period	20/02/23 → 23/02/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

3-R robotic manipulator
inverse kinematics
neural networks
supervised learning

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Computer Networks and Communications
Information Systems
Signal Processing
Health Informatics
Instrumentation

Access to Document

10.1109/SSD58187.2023.10411151

Cite this

Esmat, M., Abdel-Nasser, M., & Saif, A. W. A. (2023). Solving Inverse Kinematics for 3R Manipulator Using Artificial Neural Networks. In 2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023 (pp. 116-120). (2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSD58187.2023.10411151

Esmat, Muhammad ; Abdel-Nasser, Mohammed ; Saif, Abdul Wahid A. / Solving Inverse Kinematics for 3R Manipulator Using Artificial Neural Networks. 2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 116-120 (2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023).

@inproceedings{ad8f135cb38c4ee3b04f46809b3af262,

title = "Solving Inverse Kinematics for 3R Manipulator Using Artificial Neural Networks",

abstract = "Manipulator robots are one of the widely famous robotics types. One of the major problems that appear when preparing these robots is the Inverse Kinematic Problem (IKP). Overcoming the IKP in some cases requires solving complex equations, time-consuming, and can lead to singularity solutions. In this paper, a modeling of the forward kinematics for a 3-R manipulator robot was carried out to generate a dataset for supervised learning. Furthermore, a training model for solving the inverse kinematics of this robot with avoiding the singularity points based on Artificial Neural Networks (ANN) is proposed. The reliability of the method was validated by trajectory tracking. The results demonstrate the effectiveness of the robot to track the referenced path successfully with maximum mean absolute error in the X, Y, and Z axes around 1.375 mm.",

keywords = "3-R robotic manipulator, inverse kinematics, neural networks, supervised learning",

author = "Muhammad Esmat and Mohammed Abdel-Nasser and Saif, \{Abdul Wahid A.\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023 ; Conference date: 20-02-2023 Through 23-02-2023",

year = "2023",

doi = "10.1109/SSD58187.2023.10411151",

language = "English",

series = "2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "116--120",

booktitle = "2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023",

address = "United States",

}

Esmat, M, Abdel-Nasser, M & Saif, AWA 2023, Solving Inverse Kinematics for 3R Manipulator Using Artificial Neural Networks. in 2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023. 2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023, Institute of Electrical and Electronics Engineers Inc., pp. 116-120, 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023, Mahdia, Tunisia, 20/02/23. https://doi.org/10.1109/SSD58187.2023.10411151

Solving Inverse Kinematics for 3R Manipulator Using Artificial Neural Networks. / Esmat, Muhammad; Abdel-Nasser, Mohammed; Saif, Abdul Wahid A.
2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 116-120 (2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Solving Inverse Kinematics for 3R Manipulator Using Artificial Neural Networks

AU - Esmat, Muhammad

AU - Abdel-Nasser, Mohammed

AU - Saif, Abdul Wahid A.

PY - 2023

Y1 - 2023

N2 - Manipulator robots are one of the widely famous robotics types. One of the major problems that appear when preparing these robots is the Inverse Kinematic Problem (IKP). Overcoming the IKP in some cases requires solving complex equations, time-consuming, and can lead to singularity solutions. In this paper, a modeling of the forward kinematics for a 3-R manipulator robot was carried out to generate a dataset for supervised learning. Furthermore, a training model for solving the inverse kinematics of this robot with avoiding the singularity points based on Artificial Neural Networks (ANN) is proposed. The reliability of the method was validated by trajectory tracking. The results demonstrate the effectiveness of the robot to track the referenced path successfully with maximum mean absolute error in the X, Y, and Z axes around 1.375 mm.

AB - Manipulator robots are one of the widely famous robotics types. One of the major problems that appear when preparing these robots is the Inverse Kinematic Problem (IKP). Overcoming the IKP in some cases requires solving complex equations, time-consuming, and can lead to singularity solutions. In this paper, a modeling of the forward kinematics for a 3-R manipulator robot was carried out to generate a dataset for supervised learning. Furthermore, a training model for solving the inverse kinematics of this robot with avoiding the singularity points based on Artificial Neural Networks (ANN) is proposed. The reliability of the method was validated by trajectory tracking. The results demonstrate the effectiveness of the robot to track the referenced path successfully with maximum mean absolute error in the X, Y, and Z axes around 1.375 mm.

KW - 3-R robotic manipulator

KW - inverse kinematics

KW - neural networks

KW - supervised learning

UR - https://www.scopus.com/pages/publications/85185845317

U2 - 10.1109/SSD58187.2023.10411151

DO - 10.1109/SSD58187.2023.10411151

M3 - Conference contribution

AN - SCOPUS:85185845317

T3 - 2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023

SP - 116

EP - 120

BT - 2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023

Y2 - 20 February 2023 through 23 February 2023

ER -

Esmat M, Abdel-Nasser M, Saif AWA. Solving Inverse Kinematics for 3R Manipulator Using Artificial Neural Networks. In 2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 116-120. (2023 20th International Multi-Conference on Systems, Signals and Devices, SSD 2023). doi: 10.1109/SSD58187.2023.10411151

Solving Inverse Kinematics for 3R Manipulator Using Artificial Neural Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this