Investigating Feed-Forward Back-Propagation Neural Network with Different Hyperparameters for Inverse Kinematics of a 2-DoF Robotic Manipulator: A Comparative Study

Inverse kinematics is a significant challenge in robotic manipulators, and finding practical solutions plays a crucial role in achieving precise control. This paper presents a study on solving inverse kinematics problems using the Feed-Forward Back-Propagation Neural Network (FFBP-NN) and examines i...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Chaos theory and applications Ročník 6; číslo 2; s. 90 - 110
Hlavní autori: Bouzid, Rania, Gritli, Hassène, Narayan, Jyotindra
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Akif AKGUL 30.06.2024
Predmet:
artifical neural network
bayesian regularization algorithm
different datasets
feed-forward backpropagation
hyperparameters
inverse kinematics
levenberg-marquardt algorithm
mean squared error
r-value
robotic manipulator
scaled conjugate gradient algorithm
ISSN:2687-4539, 2687-4539
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Inverse kinematics is a significant challenge in robotic manipulators, and finding practical solutions plays a crucial role in achieving precise control. This paper presents a study on solving inverse kinematics problems using the Feed-Forward Back-Propagation Neural Network (FFBP-NN) and examines its performance with different hyperparameters. By utilizing the FFBP-NN, our primary objective is to ascertain the joint angles required to attain precise Cartesian coordinates for the end-effector of the manipulator. To accomplish this, we first formed three input-output datasets (a fixed-step-size dataset, a random-step-size dataset, and a sinusoidal-signal-based dataset) of joint positions and their respective Cartesian coordinates using direct geometrical formulations of a two-degree-of-freedom (2-DoF) manipulator. Thereafter, we train the FFBP-NN with the generated datasets using the MATLAB Neural Network Toolbox and investigate its potential by altering the hyperparameters (e.g., number of hidden neurons, number of hidden layers, and training optimizer). Three different training optimizers are considered, namely the Levenberg-Marquardt (LM) algorithm, the Bayesian Regularization (BR) algorithm, and the Scaled Conjugate Gradient (SCG) algorithm. The Mean Squared Error is used as the main performance metric to evaluate the training accuracy of the FFBP-NN. The comparative outcomes offer valuable insights into the capabilities of various network architectures in addressing inverse kinematics challenges. Therefore, this study explores the application of the FFBP-NNs in tackling the inverse kinematics, and facilitating the choice of the most appropriate network design by achieving a portfolio of various experimental results by considering and varying different hyperparameters of the FFBP-NN.
AbstractList Inverse kinematics is a significant challenge in robotic manipulators, and finding practical solutions plays a crucial role in achieving precise control. This paper presents a study on solving inverse kinematics problems using the Feed-Forward Back-Propagation Neural Network (FFBP-NN) and examines its performance with different hyperparameters. By utilizing the FFBP-NN, our primary objective is to ascertain the joint angles required to attain precise Cartesian coordinates for the end-effector of the manipulator. To accomplish this, we first formed three input-output datasets (a fixed-step-size dataset, a random-step-size dataset, and a sinusoidal-signal-based dataset) of joint positions and their respective Cartesian coordinates using direct geometrical formulations of a two-degree-of-freedom (2-DoF) manipulator. Thereafter, we train the FFBP-NN with the generated datasets using the MATLAB Neural Network Toolbox and investigate its potential by altering the hyperparameters (e.g., number of hidden neurons, number of hidden layers, and training optimizer). Three different training optimizers are considered, namely the Levenberg-Marquardt (LM) algorithm, the Bayesian Regularization (BR) algorithm, and the Scaled Conjugate Gradient (SCG) algorithm. The Mean Squared Error is used as the main performance metric to evaluate the training accuracy of the FFBP-NN. The comparative outcomes offer valuable insights into the capabilities of various network architectures in addressing inverse kinematics challenges. Therefore, this study explores the application of the FFBP-NNs in tackling the inverse kinematics, and facilitating the choice of the most appropriate network design by achieving a portfolio of various experimental results by considering and varying different hyperparameters of the FFBP-NN.
Author Narayan, Jyotindra
Gritli, Hassène
Bouzid, Rania
Author_xml – sequence: 1
  givenname: Rania
  orcidid: 0009-0003-9641-1380
  surname: Bouzid
  fullname: Bouzid, Rania
– sequence: 2
  givenname: Hassène
  orcidid: 0000-0002-5643-134X
  surname: Gritli
  fullname: Gritli, Hassène
– sequence: 3
  givenname: Jyotindra
  orcidid: 0000-0002-2499-6039
  surname: Narayan
  fullname: Narayan, Jyotindra
BookMark eNp1kd1uEzEQhVeoSJTSW679Aht2vWt7l7uSEhrRAuLn2hrb49TtZh2NnUZ5Hx6UTVokVImrM5rR-TQz53VxMsYRi-JtXc1ELRr1zt5CTLO6UaKT8kVxymWnylY0_ck_9aviPKW7qqp439eSq9Pi93J8wJTDCnIYV2yB6MpFpB2QYx_A3pffKG7gMI0j-4JbgmGSvIt0z3Yh37LL4D0Sjpld7TdIGyBYY0ZKzEdiBzolZJ_DiOsJYhOLngHj5WVcsO_RxKnHbmAMm-0AOdJ7dsHmcX3A5PCA7Efeuv2b4qWHIeH5k54VvxYff86vyuuvn5bzi-vSTvfIsuXOGVtB23OlRGWt5MIKLwWYzjjT2MpxoVorDSioa6Ow6dH41mOvjHC-OSuWj1wX4U5vKKyB9jpC0MdGpJUGmhYeUHuphOmFktA0LULdgRUSVNMpZ7jxfGK1jyxLMSVCr23IxzdmgjDoutLH4PQxOP0U3GSbPbP9XeM_hj-xeqGX
CitedBy_id crossref_primary_10_2478_acss_2024_0004
Cites_doi 10.1088/1742-6596/366/1/012013
10.51537/chaos.1213070
10.1016/S0893-6080(05)80056-5
10.3390/app12199512
10.1109/ICIEV.2018.8640958
10.1007/978-3-030-84205-5_26
10.3390/mca21020020
10.1007/978-3-031-51224-7_4
10.1007/s10015-019-00552-y
10.1007/s11370-023-00477-3
10.1088/1742-6596/1969/1/012010
10.1007/s11012-016-0369-3
10.2339/politeknik.1092642
10.1007/s12652-020-01815-4
10.1109/TII.2018.2792002
10.1016/j.chaos.2022.112769
10.51537/chaos.1116084
10.1016/j.engappai.2023.106301
10.1117/1.OE.53.5.055102
10.1016/j.engappai.2023.107175
10.3844/ajeassp.2017.394.411
10.51537/chaos.1184952
10.1109/ICCUBEA47591.2019.9128742
10.1109/ICOIACT.2018.8350676
10.1109/3ICT60104.2023.10391576
10.1115/1.4011045
10.1109/ISPCC.2017.8269676
10.1016/j.robot.2004.09.010
10.1007/978-3-030-01424-7_77
10.1007/s10846-017-0502-0
10.1016/j.procs.2018.07.069
10.1109/IATMSI60426.2024.10503452
10.1016/j.actaastro.2017.06.015
10.1109/ICPC2T60072.2024.10474947
10.1108/01439910810893626
10.1016/0167-8655(84)90007-2
10.1007/s12652-014-0244-9
10.1007/s00170-018-1785-4
10.51537/chaos.1249532
10.1109/ICETSIS61505.2024.10459544
10.3390/machines11100952
10.1088/0266-5611/14/3/003
10.1016/j.rcim.2018.05.008
10.5772/64047
10.1007/s10846-016-0449-6
10.1007/s12652-011-0056-0
10.1080/0951192X.2017.1305507
10.1177/0954411918781418
10.1007/s41870-017-0002-2
10.1155/2022/1713657
10.1016/j.protcy.2013.12.451
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.51537/chaos.1375866
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
EISSN 2687-4539
EndPage 110
ExternalDocumentID oai_doaj_org_article_f675b9576a334ea18ac56a7387db2bf2
10_51537_chaos_1375866
GroupedDBID AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
IAO
ITC
ID FETCH-LOGICAL-c2996-42ddbc0a4927750cc625c5f65ab8bdb3c0d2574c6ba7a11b7e39ebf4fe97b5df3
IEDL.DBID DOA
ISSN 2687-4539
IngestDate Fri Oct 03 12:50:32 EDT 2025
Sat Nov 29 03:40:14 EST 2025
Tue Nov 18 22:43:42 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2996-42ddbc0a4927750cc625c5f65ab8bdb3c0d2574c6ba7a11b7e39ebf4fe97b5df3
ORCID 0000-0002-5643-134X
0000-0002-2499-6039
0009-0003-9641-1380
OpenAccessLink https://doaj.org/article/f675b9576a334ea18ac56a7387db2bf2
PageCount 21
ParticipantIDs doaj_primary_oai_doaj_org_article_f675b9576a334ea18ac56a7387db2bf2
crossref_citationtrail_10_51537_chaos_1375866
crossref_primary_10_51537_chaos_1375866
PublicationCentury 2000
PublicationDate 2024-06-30
PublicationDateYYYYMMDD 2024-06-30
PublicationDate_xml – month: 06
  year: 2024
  text: 2024-06-30
  day: 30
PublicationDecade 2020
PublicationTitle Chaos theory and applications
PublicationYear 2024
Publisher Akif AKGUL
Publisher_xml – name: Akif AKGUL
References ref13
ref57
ref12
ref56
ref15
ref59
ref14
ref58
ref53
ref52
ref11
ref55
ref10
ref54
ref17
ref16
ref19
ref18
ref51
ref50
ref46
ref45
ref48
ref47
ref42
ref41
ref44
ref43
ref49
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref40
ref35
ref34
ref37
ref36
ref31
ref30
ref33
ref32
ref2
ref1
ref39
ref38
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
ref60
ref61
References_xml – ident: ref18
  doi: 10.1088/1742-6596/366/1/012013
– ident: ref33
  doi: 10.51537/chaos.1213070
– ident: ref20
– ident: ref43
  doi: 10.1016/S0893-6080(05)80056-5
– ident: ref29
  doi: 10.3390/app12199512
– ident: ref26
  doi: 10.1109/ICIEV.2018.8640958
– ident: ref45
  doi: 10.1007/978-3-030-84205-5_26
– ident: ref32
  doi: 10.3390/mca21020020
– ident: ref10
  doi: 10.1007/978-3-031-51224-7_4
– ident: ref27
– ident: ref56
  doi: 10.1007/s10015-019-00552-y
– ident: ref44
  doi: 10.1007/s11370-023-00477-3
– ident: ref2
  doi: 10.1088/1742-6596/1969/1/012010
– ident: ref34
  doi: 10.1007/s11012-016-0369-3
– ident: ref3
  doi: 10.2339/politeknik.1092642
– ident: ref11
– ident: ref13
– ident: ref23
  doi: 10.1007/s12652-020-01815-4
– ident: ref54
  doi: 10.1109/TII.2018.2792002
– ident: ref49
  doi: 10.1016/j.chaos.2022.112769
– ident: ref42
  doi: 10.51537/chaos.1116084
– ident: ref58
  doi: 10.1016/j.engappai.2023.106301
– ident: ref59
  doi: 10.1117/1.OE.53.5.055102
– ident: ref12
  doi: 10.1016/j.engappai.2023.107175
– ident: ref50
  doi: 10.3844/ajeassp.2017.394.411
– ident: ref30
  doi: 10.51537/chaos.1184952
– ident: ref1
  doi: 10.1109/ICCUBEA47591.2019.9128742
– ident: ref37
  doi: 10.1109/ICOIACT.2018.8350676
– ident: ref6
  doi: 10.1109/3ICT60104.2023.10391576
– ident: ref40
– ident: ref17
  doi: 10.1115/1.4011045
– ident: ref47
– ident: ref46
  doi: 10.1109/ISPCC.2017.8269676
– ident: ref35
  doi: 10.1016/j.robot.2004.09.010
– ident: ref57
  doi: 10.1007/978-3-030-01424-7_77
– ident: ref22
  doi: 10.1007/s10846-017-0502-0
– ident: ref36
  doi: 10.1016/j.procs.2018.07.069
– ident: ref8
  doi: 10.1109/IATMSI60426.2024.10503452
– ident: ref60
  doi: 10.1016/j.actaastro.2017.06.015
– ident: ref9
  doi: 10.1109/ICPC2T60072.2024.10474947
– ident: ref28
  doi: 10.1108/01439910810893626
– ident: ref21
  doi: 10.1016/0167-8655(84)90007-2
– ident: ref5
  doi: 10.1007/s12652-014-0244-9
– ident: ref61
  doi: 10.1007/s00170-018-1785-4
– ident: ref25
– ident: ref31
  doi: 10.51537/chaos.1249532
– ident: ref51
– ident: ref7
  doi: 10.1109/ICETSIS61505.2024.10459544
– ident: ref24
  doi: 10.3390/machines11100952
– ident: ref55
  doi: 10.1088/0266-5611/14/3/003
– ident: ref38
  doi: 10.1016/j.rcim.2018.05.008
– ident: ref16
  doi: 10.5772/64047
– ident: ref15
– ident: ref39
  doi: 10.1007/s10846-016-0449-6
– ident: ref4
  doi: 10.1007/s12652-011-0056-0
– ident: ref53
  doi: 10.1080/0951192X.2017.1305507
– ident: ref52
– ident: ref48
  doi: 10.1177/0954411918781418
– ident: ref41
  doi: 10.1007/s41870-017-0002-2
– ident: ref14
  doi: 10.1155/2022/1713657
– ident: ref19
  doi: 10.1016/j.protcy.2013.12.451
SSID ssj0002991627
Score 2.3189788
Snippet Inverse kinematics is a significant challenge in robotic manipulators, and finding practical solutions plays a crucial role in achieving precise control. This...
SourceID doaj
crossref
SourceType Open Website
Enrichment Source
Index Database
StartPage 90
SubjectTerms artifical neural network
bayesian regularization algorithm
different datasets
feed-forward backpropagation
hyperparameters
inverse kinematics
levenberg-marquardt algorithm
mean squared error
r-value
robotic manipulator
scaled conjugate gradient algorithm
Title Investigating Feed-Forward Back-Propagation Neural Network with Different Hyperparameters for Inverse Kinematics of a 2-DoF Robotic Manipulator: A Comparative Study
URI https://doaj.org/article/f675b9576a334ea18ac56a7387db2bf2
Volume 6
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2687-4539
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002991627
  issn: 2687-4539
  databaseCode: DOA
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Na9ZAEF6k9OBFlCrWL-ZQ8LQ22U2y73rrVyiIL0UUegsz-1GLmpTkVfD_-EOd3cT2vYgXr5thCDOTnWfCwzNCHOhGYyDjJTlbyEoVTpKlUrpQRF87wgaLvGzCrNery0t7sbXqK3HCZnngOXCHkREtWUbFqHUVsFyhqxs0emU8KYr59mXUszVMpTtYJdijzKzSyC1bm0P3GYfpTakZIGdJxLsutCXWn7tK-1A8WOAgHM2v8UjcC_2e-LUlftFfQcsNRrbDmPitcIzui7wYedS9yjGFpK7BHtYznRvSf1U4XbaebOCcx8wxyXt_S7SXCRiiQvI-TgHeMcDMgq0TDBEQlDwdWvgw0MBn8B7767zbaxjfwhGc3KmEQ-Ie_nwsPrVnH0_O5bJNQTqVmMaV8p5cgZVVhmGCczz5uDo2NdKKPGlXeP58K9cQGixLMkHbQLGKwRqqfdRPxE4_9OGpgBC91Qz8-FmojKoQURtFqrBFbCLRvpB_otu5RWo8bbz42vHIkbPR5Wx0Szb2xetb-5tZZOOvlscpWbdWSRw7H3DJdEvJdP8qmWf_w8lzcV8xvpmpgy_Ezmb8Hl6KXfdjcz2Nr3I1_gZuM-pk
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Investigating+Feed-Forward+Back-Propagation+Neural+Network+with+Different+Hyperparameters+for+Inverse+Kinematics+of+a+2-DoF+Robotic+Manipulator%3A+A+Comparative+Study&rft.jtitle=Chaos+theory+and+applications&rft.au=Rania+Bouzid&rft.au=Jyotindra+Narayan&rft.au=Hass%C3%A8ne+Gritli&rft.date=2024-06-30&rft.pub=Akif+AKGUL&rft.eissn=2687-4539&rft.volume=6&rft.issue=2&rft.spage=90&rft.epage=110&rft_id=info:doi/10.51537%2Fchaos.1375866&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_f675b9576a334ea18ac56a7387db2bf2
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2687-4539&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2687-4539&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2687-4539&client=summon