A Learning-Based Assembly Sequence Planning Method Using Neural Combinatorial Optimization With Satisfactory Generalization Ability

This paper proposes a specific and effective real-time sequence planning method using robot manipulators to complete complex assembly tasks. Many previous studies developed different traversal methods to obtain the optimal assembly sequence. Besides, a number of algorithms were proposed to enhance f...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on automation science and engineering Jg. 22; S. 8952 - 8964
Hauptverfasser: Hou, Ruiming, Xu, Sheng, Yang, Chenguang, Duan, Jianghua, Wu, Xinyu, Xu, Tiantian
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 01.01.2025
Schlagworte:
ISSN:1545-5955, 1558-3783
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract This paper proposes a specific and effective real-time sequence planning method using robot manipulators to complete complex assembly tasks. Many previous studies developed different traversal methods to obtain the optimal assembly sequence. Besides, a number of algorithms were proposed to enhance flexibility when the conditions or rules were changed in various sequence optimization problems. However, these state-of-the-art (STOA) methods necessarily require modifications when task details are changed. Consequently, to further improve the generalization ability and improve the performance of the sequence optimization, a neural combinatorial optimization algorithm combined with a self-learning strategy is proposed for assembly sequence planning. In addition, obstacle avoidance and the non-collision constraints between workpieces in the assembly process are considered. According to the experiment results, the new method is superior to the STOA methods in terms of optimization efficiency. More importantly, the proposed method has satisfactory generalization ability for different assembly tasks.Note to Practitioners-This paper studies assembly sequence planning problems for different real-world applications in industrial and home service fields. Many assembly sequence planning solutions have been widely utilized before. However, the generalization ability of the previous methods is not satisfactory since the re-adjust process is required when the workpiece number or collision condition changes in different tasks.Motivated by the above reasons, this paper develops a learning-based assembly sequence planning solution to resolve complex assembly problems without parameter re-adjustment processes. Users can directly apply the developed workpiece identification and localization method to obtain the sensing information. Then, the newly designed collision-free cost function should be programmed as the core of the assembly sequence optimization. Next, the proposed neural combinatorial optimization (NCO) with the sensing information and target configuration as inputs can provide the optimal assembly sequence by self-learning. The learned NCO-based method can be directly applied to diverse planning tasks, even with different workpiece numbers. Users can also refer to the experimental examples in this paper for the extension of the proposed method to their own applications.
AbstractList This paper proposes a specific and effective real-time sequence planning method using robot manipulators to complete complex assembly tasks. Many previous studies developed different traversal methods to obtain the optimal assembly sequence. Besides, a number of algorithms were proposed to enhance flexibility when the conditions or rules were changed in various sequence optimization problems. However, these state-of-the-art (STOA) methods necessarily require modifications when task details are changed. Consequently, to further improve the generalization ability and improve the performance of the sequence optimization, a neural combinatorial optimization algorithm combined with a self-learning strategy is proposed for assembly sequence planning. In addition, obstacle avoidance and the non-collision constraints between workpieces in the assembly process are considered. According to the experiment results, the new method is superior to the STOA methods in terms of optimization efficiency. More importantly, the proposed method has satisfactory generalization ability for different assembly tasks.Note to Practitioners-This paper studies assembly sequence planning problems for different real-world applications in industrial and home service fields. Many assembly sequence planning solutions have been widely utilized before. However, the generalization ability of the previous methods is not satisfactory since the re-adjust process is required when the workpiece number or collision condition changes in different tasks.Motivated by the above reasons, this paper develops a learning-based assembly sequence planning solution to resolve complex assembly problems without parameter re-adjustment processes. Users can directly apply the developed workpiece identification and localization method to obtain the sensing information. Then, the newly designed collision-free cost function should be programmed as the core of the assembly sequence optimization. Next, the proposed neural combinatorial optimization (NCO) with the sensing information and target configuration as inputs can provide the optimal assembly sequence by self-learning. The learned NCO-based method can be directly applied to diverse planning tasks, even with different workpiece numbers. Users can also refer to the experimental examples in this paper for the extension of the proposed method to their own applications.
Author Xu, Tiantian
Hou, Ruiming
Duan, Jianghua
Yang, Chenguang
Wu, Xinyu
Xu, Sheng
Author_xml – sequence: 1
  givenname: Ruiming
  surname: Hou
  fullname: Hou, Ruiming
  organization: Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
– sequence: 2
  givenname: Sheng
  orcidid: 0000-0002-5086-4152
  surname: Xu
  fullname: Xu, Sheng
  email: sheng.xu@siat.ac.cn
  organization: Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
– sequence: 3
  givenname: Chenguang
  orcidid: 0000-0001-5255-5559
  surname: Yang
  fullname: Yang, Chenguang
  organization: Department of Computer Science, University of Liverpool, Liverpool, U.K
– sequence: 4
  givenname: Jianghua
  orcidid: 0009-0005-2271-8253
  surname: Duan
  fullname: Duan, Jianghua
  organization: HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute, Shenzhen, Futian, China
– sequence: 5
  givenname: Xinyu
  orcidid: 0000-0001-6130-7821
  surname: Wu
  fullname: Wu, Xinyu
  organization: Guangdong Provincial Key Laboratory of Robotics and Intelligent System, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
– sequence: 6
  givenname: Tiantian
  orcidid: 0000-0001-8974-4572
  surname: Xu
  fullname: Xu, Tiantian
  organization: Engineering Research Center of Digital Community, Ministry of Education, Beijing University of Technology, Beijing, China
BookMark eNpNkEFLwzAYhoNMcJv-AMFD_kBn0jRpeqxjTmE6YRseS5p-cZE2nU13qFf_uC2b4Ol7X3je7_BM0MjVDhC6pWRGKUnut-lmMQtJGM1YlDBB4ws0ppzLgMWSjYYc8YAnnF-hifefpCdlQsboJ8UrUI2z7iN4UB4KnHoPVV52eANfR3Aa8Fup3ADgF2j3dYF3fiivcGxUied1lVun2rqxfVsfWlvZb9Xa2uF32-7xps_eKN0DHV6Cg370B6S5LW3bXaNLo0oPN-c7RbvHxXb-FKzWy-d5ugp0SGUbcB4XWkaC6sjoXBlR0FyY2GhVGMkMqFiAFKYgXFKgXDAj8jyHhCiiYyETNkX09Fc3tfcNmOzQ2Eo1XUZJNljMBovZYDE7W-w3d6eNBYB_fMxDkjD2CyvNdEs
CODEN ITASC7
Cites_doi 10.1109/tase.2024.3421889
10.1214/ss/1177011077
10.1109/MCI.2023.3277768
10.1109/TASE.2023.3236805
10.1109/TASE.2022.3213730
10.1007/s00170-013-4799-y
10.1109/TSMC.2020.3013904
10.1109/LRA.2023.3330611
10.1007/bf01473902
10.1109/TRO.2022.3197013
10.1109/TASE.2014.2345569
10.23940/ijpe.21.03.p4.289298
10.3390/sym14051013
10.1109/TASE.2021.3136006
10.1109/TIE.2018.2886798
10.1109/TRO.2022.3157147
10.1016/j.jairtraman.2013.06.001
10.1016/j.cirpj.2022.11.003
10.1109/TASE.2012.2232652
10.1007/s00170-006-0438-1
10.1016/j.jmsy.2021.01.004
10.1016/j.sysconle.2004.08.007
10.1177/0954408918764459
10.1007/bf01179417
10.1109/TASE.2018.2791665
10.1007/s00170-015-7565-5
10.1109/CoASE.2015.7294142
10.1177/0954406215584633
10.1177/0954406219842908
10.1109/ICACI.2018.8377505
10.1109/TSMC.2023.3317390
10.1109/TCYB.2021.3121080
10.1109/LRA.2023.3280816
10.1007/s00170-003-1952-z
10.1016/j.advengsoft.2016.01.008
10.1080/00207543.2021.1937748
10.1109/TASE.2016.2622253
10.1016/j.birob.2021.100001
10.1109/TRO.2022.3198020
10.1007/s11465-020-0613-3
10.1016/j.advengsoft.2013.12.007
10.1109/TNNLS.2021.3105937
10.1109/21.87086
10.1109/RCAR58764.2023.10249862
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/TASE.2024.3493617
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-3783
EndPage 8964
ExternalDocumentID 10_1109_TASE_2024_3493617
10752093
Genre orig-research
GrantInformation_xml – fundername: Basic and Applied Basic Research Foundation of Guangdong Province; Guangdong Basic and Applied Basic Research Foundation
  grantid: 2022B1515120010
  funderid: 10.13039/501100021171
– fundername: Shenzhen Science and Technology Program
  grantid: KCXFZ20211020165003005; JCYJ20220818101611025; RCJC20231211085926038
– fundername: National Key Research and Development Project
  grantid: 2023YFB4705300
  funderid: 10.13039/501100012166
– fundername: National Natural Science Foundation of China
  grantid: 62273327; U22A2064
  funderid: 10.13039/501100001809
– fundername: Shenzhen Institutes of Advanced Technology and Chinese University of Hong Kong (SIAT-CUHK) Joint Laboratory of Robotics and Intelligent Systems.
  funderid: 10.13039/501100011443
– fundername: Project of Hetao Shenzhen-Hong Kong Science and Technology Innovation Cooperation Zone
  grantid: HZQB-KCZYB-2020083
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AIBXA
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
ID FETCH-LOGICAL-c218t-557dc8461c4fcbaf6d1b6f7fcadf83fea76e86fd0581e1563f6bbbe90a0c76893
IEDL.DBID RIE
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001358234900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1545-5955
IngestDate Sat Nov 29 08:05:23 EST 2025
Wed Aug 27 02:04:30 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c218t-557dc8461c4fcbaf6d1b6f7fcadf83fea76e86fd0581e1563f6bbbe90a0c76893
ORCID 0000-0001-5255-5559
0009-0005-2271-8253
0000-0001-8974-4572
0000-0001-6130-7821
0000-0002-5086-4152
PageCount 13
ParticipantIDs crossref_primary_10_1109_TASE_2024_3493617
ieee_primary_10752093
PublicationCentury 2000
PublicationDate 2025-01-01
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – month: 01
  year: 2025
  text: 2025-01-01
  day: 01
PublicationDecade 2020
PublicationTitle IEEE transactions on automation science and engineering
PublicationTitleAbbrev TASE
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref35
ref12
ref34
ref15
ref14
Wang (ref22) 2005; 25
ref36
ref11
ref33
ref10
ref32
Ying (ref25) 2021; 58
ref2
ref1
ref17
ref39
ref16
ref19
ref18
Bello (ref43) 2016
Wu (ref38) 2022; 60
ref24
ref46
ref23
ref26
ref20
ref42
Garmendia (ref45) 2022
ref41
ref21
Suszyǹski (ref37) 2022; 14
ref28
ref27
Mirjalili (ref30) 2016; 95
ref29
ref8
ref7
ref9
ref4
ref3
ref6
ref5
Mirjalili (ref31) 2014; 69
ref40
Borkar (ref44) 2005; 54
References_xml – ident: ref24
  doi: 10.1109/tase.2024.3421889
– ident: ref27
  doi: 10.1214/ss/1177011077
– ident: ref46
  doi: 10.1109/MCI.2023.3277768
– ident: ref2
  doi: 10.1109/TASE.2023.3236805
– ident: ref5
  doi: 10.1109/TASE.2022.3213730
– ident: ref12
  doi: 10.1007/s00170-013-4799-y
– ident: ref34
  doi: 10.1109/TSMC.2020.3013904
– ident: ref9
  doi: 10.1109/LRA.2023.3330611
– ident: ref18
  doi: 10.1007/bf01473902
– ident: ref35
  doi: 10.1109/TRO.2022.3197013
– ident: ref11
  doi: 10.1109/TASE.2014.2345569
– ident: ref29
  doi: 10.23940/ijpe.21.03.p4.289298
– volume: 14
  start-page: 1013
  issue: 5
  year: 2022
  ident: ref37
  article-title: Mechanical assembly sequence determination using artificial neural networks based on selected DFA rating factors
  publication-title: Symmetry
  doi: 10.3390/sym14051013
– ident: ref8
  doi: 10.1109/TASE.2021.3136006
– ident: ref32
  doi: 10.1109/TIE.2018.2886798
– ident: ref6
  doi: 10.1109/TRO.2022.3157147
– ident: ref10
  doi: 10.1016/j.jairtraman.2013.06.001
– ident: ref39
  doi: 10.1016/j.cirpj.2022.11.003
– ident: ref19
  doi: 10.1109/TASE.2012.2232652
– ident: ref20
  doi: 10.1007/s00170-006-0438-1
– volume: 58
  start-page: 452
  year: 2021
  ident: ref25
  article-title: Cyber-physical assembly system-based optimization for robotic assembly sequence planning
  publication-title: J. Manuf. Syst.
  doi: 10.1016/j.jmsy.2021.01.004
– volume: 54
  start-page: 207
  issue: 3
  year: 2005
  ident: ref44
  article-title: An actor-critic algorithm for constrained Markov decision processes
  publication-title: Syst. Control Lett.
  doi: 10.1016/j.sysconle.2004.08.007
– ident: ref14
  doi: 10.1177/0954408918764459
– ident: ref21
  doi: 10.1007/bf01179417
– ident: ref13
  doi: 10.1109/TASE.2018.2791665
– ident: ref15
  doi: 10.1007/s00170-015-7565-5
– year: 2016
  ident: ref43
  article-title: Neural combinatorial optimization with reinforcement learning
  publication-title: arXiv:1611.09940
– ident: ref17
  doi: 10.1109/CoASE.2015.7294142
– ident: ref4
  doi: 10.1177/0954406215584633
– ident: ref16
  doi: 10.1177/0954406219842908
– ident: ref42
  doi: 10.1109/ICACI.2018.8377505
– ident: ref33
  doi: 10.1109/TSMC.2023.3317390
– ident: ref36
  doi: 10.1109/TCYB.2021.3121080
– ident: ref41
  doi: 10.1109/LRA.2023.3280816
– volume: 25
  start-page: 1137
  issue: 11
  year: 2005
  ident: ref22
  article-title: A novel ant colony algorithm for assembly sequence planning
  publication-title: Int. J. Adv. Manuf. Technol.
  doi: 10.1007/s00170-003-1952-z
– volume: 95
  start-page: 51
  year: 2016
  ident: ref30
  article-title: The whale optimization algorithm
  publication-title: Adv. Eng. Softw.
  doi: 10.1016/j.advengsoft.2016.01.008
– volume: 60
  start-page: 4797
  issue: 15
  year: 2022
  ident: ref38
  article-title: A decision-making method for assembly sequence planning with dynamic resources
  publication-title: Int. J. Prod. Res.
  doi: 10.1080/00207543.2021.1937748
– ident: ref28
  doi: 10.1109/TASE.2016.2622253
– ident: ref7
  doi: 10.1016/j.birob.2021.100001
– ident: ref3
  doi: 10.1109/TRO.2022.3198020
– ident: ref23
  doi: 10.1007/s11465-020-0613-3
– volume: 69
  start-page: 46
  year: 2014
  ident: ref31
  article-title: Grey wolf optimizer
  publication-title: Adv. Eng. Softw.
  doi: 10.1016/j.advengsoft.2013.12.007
– ident: ref40
  doi: 10.1109/TNNLS.2021.3105937
– ident: ref1
  doi: 10.1109/21.87086
– year: 2022
  ident: ref45
  article-title: Neural combinatorial optimization: A new player in the field
  publication-title: arXiv:2205.01356
– ident: ref26
  doi: 10.1109/RCAR58764.2023.10249862
SSID ssj0024890
Score 2.3958652
Snippet This paper proposes a specific and effective real-time sequence planning method using robot manipulators to complete complex assembly tasks. Many previous...
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 8952
SubjectTerms Assembly
Assembly sequence planning (ASP)
contact matrix
Cost function
Costs
Manipulators
neural combinatorial optimization (NCO)
Optimization
Planning
pointer network
Production
reinforcement learning (RL)
Robot kinematics
Robots
Stability analysis
Title A Learning-Based Assembly Sequence Planning Method Using Neural Combinatorial Optimization With Satisfactory Generalization Ability
URI https://ieeexplore.ieee.org/document/10752093
Volume 22
WOSCitedRecordID wos001358234900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore
  customDbUrl:
  eissn: 1558-3783
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0024890
  issn: 1545-5955
  databaseCode: RIE
  dateStart: 20040101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxQADzyLKSx6YkFySJo7tMaBWLBSkFtEtil-ARFtUtUid-eOcHUftwsAWRVYU3dk-f76770Po2nF88TRWBEKfJGlsGBFSUpJQpZUWsemaSmyCDQZ8PBbPoVnd98IYY3zxmem4R5_L1zO1dFdlsMKZq9pIGqjBWFY1a62J9bi_UHFHAkIFpSGFGUfidpQPewAFu2knSUWSeXGydRDaUFXxQaW__8_fOUB74fSI88rdh2jLTI_Q7gan4DH6yXHgTH0jdxCiNHZ53Yn8XOFhKJvGtVIRfvT60djXDWDH0wEfhx0C0LLD4jA18RNsKZPQq4lfPxbveFj3Q8zmKxxYq-sBuS-1XbXQS783un8gQWmBKAjxC0Ip0wpOIrFKrZKlzXQsM8usKrXliTUlywzPrI4ojw0gvsRmUkojojJSgFdEcoKa09nUnCLMKWAOmRpNWZoaxqTjhlAQBcuSu6RsG93Upi--KkKNwgORSBTOT4XzUxH81EYtZ_aNgZXFz_54f452uk6f11-RXKDmYr40l2hbfYNh5ld-vvwCunfAoA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBfXgs2J95uBJSN1HstkcV2mp2FahFXtbNi8VbCulFXr2j5tkU9qLB2_LEpZlJsnky8x8HwDXluMrxaFAJvRxhENFEeOcoJgIKSQLVaRKsQna7aaDAXv2zequF0Yp5YrPVN0-uly-HIuZvSozK5zaqo14HWwQjKOgbNdaUuul7krFHgoQYYT4JGYYsNt-1msYMBjheoxZnDh5smUYWtFVcWGluffPH9oHu_78CLPS4QdgTY0Owc4Kq-AR-MmgZ019Q3cmSEloM7tD_jmHPV84DRdaRbDjFKShqxyAlqnDfNzsEQYvWzRuJid8MpvK0HdrwteP6TvsLToixpM59LzViwGZK7adV8FLs9G_byGvtYCECfJTRAiVwpxFQoG14IVOZMgTTbUopE5jrQqaqDTRMiBpqAzmi3XCOVcsKAJhEAuLj0FlNB6pEwBTYlAHx0oSirGilFt2CGHiYFGkNi1bAzcL0-dfJaVG7qBIwHLrp9z6Kfd-qoGqNfvKwNLip3-8vwJbrX6nnbcfuo9nYDuyar3uwuQcVKaTmboAm-LbGGly6ebOL-hhw-c
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=A+Learning-Based+Assembly+Sequence+Planning+Method+Using+Neural+Combinatorial+Optimization+With+Satisfactory+Generalization+Ability&rft.jtitle=IEEE+transactions+on+automation+science+and+engineering&rft.au=Hou%2C+Ruiming&rft.au=Xu%2C+Sheng&rft.au=Yang%2C+Chenguang&rft.au=Duan%2C+Jianghua&rft.date=2025-01-01&rft.issn=1545-5955&rft.eissn=1558-3783&rft.volume=22&rft.spage=8952&rft.epage=8964&rft_id=info:doi/10.1109%2FTASE.2024.3493617&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TASE_2024_3493617
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-5955&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-5955&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-5955&client=summon