CoAS-Net: Context-Aware Suction Network with a Large-Scale Domain Randomized Synthetic Dataset
Robotic grasping is one of the essential skills in robotics. From industrial to housework, robots are required to handle objects, enabling them to interact with their surroundings. Among the various tasks in robotic grasping, bin-picking is considered one of the most challenging because of the clutt...
Saved in:
Published in | IEEE robotics and automation letters Vol. 9; no. 1; pp. 1 - 8 |
---|---|
Main Authors | , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Piscataway
IEEE
01.01.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Robotic grasping is one of the essential skills in robotics. From industrial to housework, robots are required to handle objects, enabling them to interact with their surroundings. Among the various tasks in robotic grasping, bin-picking is considered one of the most challenging because of the cluttered bin filled with objects. Also, for the next-level automation, they need to handle unseen objects and discriminate target objects and outliers. This paper proposes a novel dataset generation pipeline for suction-grasping in bin-picking tasks. This pipeline consists of a series of methods that progressively transit from a single object evaluation to an entire scene evaluation and lower the dimension of the labels to the image space. We trained a suction prediction FCN (Fully Convolution Network) with our dataset generated from the pipeline and conducted bin-picking experiments. Our large-scale collision-free annotation enables the network to understand the context of a bin-picking task, where collisions between the gripper and the bin or object are a concern, and distinguishing the background is crucial. The results show that our solution excels the existing methods, and the network demonstrates its context-aware grasp on objects with loosely defined RoI (Region of Interest). Our dataset and the grasp detection model are available at https://github.com/SonYeongGwang/CoAS-Net.git. |
---|---|
AbstractList | Robotic grasping is one of the essential skills in robotics. From industrial to housework, robots are required to handle objects, enabling them to interact with their surroundings. Among the various tasks in robotic grasping, bin-picking is considered one of the most challenging because of the cluttered bin filled with objects. Also, for the next-level automation, they need to handle unseen objects and discriminate target objects and outliers. This letter proposes a novel dataset generation pipeline for suction-grasping in bin-picking tasks. This pipeline consists of a series of methods that progressively transit from a single object evaluation to an entire scene evaluation and lower the dimension of the labels to the image space. We trained a suction prediction FCN (Fully Convolution Network) with our dataset generated from the pipeline and conducted bin-picking experiments. Our large-scale collision-free annotation enables the network to understand the context of a bin-picking task, where collisions between the gripper and the bin or object are a concern, and distinguishing the background is crucial. The results show that our solution excels the existing methods, and the network demonstrates its context-aware grasp on objects with loosely defined RoI (Region of Interest). Robotic grasping is one of the essential skills in robotics. From industrial to housework, robots are required to handle objects, enabling them to interact with their surroundings. Among the various tasks in robotic grasping, bin-picking is considered one of the most challenging because of the cluttered bin filled with objects. Also, for the next-level automation, they need to handle unseen objects and discriminate target objects and outliers. This paper proposes a novel dataset generation pipeline for suction-grasping in bin-picking tasks. This pipeline consists of a series of methods that progressively transit from a single object evaluation to an entire scene evaluation and lower the dimension of the labels to the image space. We trained a suction prediction FCN (Fully Convolution Network) with our dataset generated from the pipeline and conducted bin-picking experiments. Our large-scale collision-free annotation enables the network to understand the context of a bin-picking task, where collisions between the gripper and the bin or object are a concern, and distinguishing the background is crucial. The results show that our solution excels the existing methods, and the network demonstrates its context-aware grasp on objects with loosely defined RoI (Region of Interest). Our dataset and the grasp detection model are available at https://github.com/SonYeongGwang/CoAS-Net.git. |
Author | Choi, Hyouk Ryeol Kang, Hansol Rhee, Issac Son, Yeong Gwang Hong, Juyong Kim, Chun Soo Bui, Tat Hieu Moon, Seung Jae Kim, Yong Hyeon |
Author_xml | – sequence: 1 givenname: Yeong Gwang orcidid: 0009-0007-1350-379X surname: Son fullname: Son, Yeong Gwang organization: School of Mechanical Engineering, Sungkyunkwan University, Seoburo 2066, Jangan-gu, Suwon, South Korea – sequence: 2 givenname: Tat Hieu orcidid: 0000-0002-1221-057X surname: Bui fullname: Bui, Tat Hieu organization: School of Mechanical Engineering, Sungkyunkwan University, Seoburo 2066, Jangan-gu, Suwon, South Korea – sequence: 3 givenname: Juyong surname: Hong fullname: Hong, Juyong organization: School of Mechanical Engineering, Sungkyunkwan University, Seoburo 2066, Jangan-gu, Suwon, South Korea – sequence: 4 givenname: Yong Hyeon surname: Kim fullname: Kim, Yong Hyeon organization: School of Mechanical Engineering, Sungkyunkwan University, Seoburo 2066, Jangan-gu, Suwon, South Korea – sequence: 5 givenname: Seung Jae orcidid: 0000-0001-9190-9372 surname: Moon fullname: Moon, Seung Jae organization: School of Mechanical Engineering, Sungkyunkwan University, Seoburo 2066, Jangan-gu, Suwon, South Korea – sequence: 6 givenname: Chun Soo surname: Kim fullname: Kim, Chun Soo organization: School of Mechanical Engineering, Sungkyunkwan University, Seoburo 2066, Jangan-gu, Suwon, South Korea – sequence: 7 givenname: Issac surname: Rhee fullname: Rhee, Issac organization: School of Mechanical Engineering, Sungkyunkwan University, Seoburo 2066, Jangan-gu, Suwon, South Korea – sequence: 8 givenname: Hansol surname: Kang fullname: Kang, Hansol organization: School of Mechanical Engineering, Sungkyunkwan University, Seoburo 2066, Jangan-gu, Suwon, South Korea – sequence: 9 givenname: Hyouk Ryeol orcidid: 0000-0003-2902-7453 surname: Choi fullname: Choi, Hyouk Ryeol organization: School of Mechanical Engineering, Sungkyunkwan University, Seoburo 2066, Jangan-gu, Suwon, South Korea |
BookMark | eNpNkE1PAjEQhhuDiYjcPXho4nmxH3S3622z-JUQTVi92nTLIIvQYrcE8ddbAgdmDjOTed-Z5LlEHessIHRNyYBSkt-NJ8WAEcYHnPMszdkZ6jKeZUkc0s5Jf4H6bbsghFDBMp6LLvosXVElrxDucelsgN-QFFvtAVcbExpncVxtnf_G2ybMscZj7b8gqYxeAh65lW4snmg7davmD6a42tkwh9AYPNJBtxCu0PlML1voH2sPfTw-vJfPyfjt6aUsxolhQxGSVGhteG4I1ECkAClTw-mMUcp1LWuREwMShKamBsglGBI3ciilyLKUppr30O3h7tq7nw20QS3cxtv4UrGcUB5TiKgiB5Xxrm09zNTaNyvtd4oStQepIki1B6mOIKPl5mBpAOBEzveR8X8YbW9x |
CODEN | IRALC6 |
Cites_doi | 10.1177/0278364912445831 10.1109/LRA.2021.3115406 10.1109/ICAR.2015.7251504 10.1109/CVPR.2019.01291 10.1177/0278364919868017 10.3390/app10165442 10.1109/LRA.2023.3247221 10.3389/fnbot.2022.806898 10.1007/978-3-319-14249-4_75 10.1177/0278364914549607 10.1126/scirobotics.aau4984 10.1109/ICCVW.2019.00187 10.1109/ICCV.2017.169 10.1109/ICRA46639.2022.9811599 10.1007/978-3-319-68792-6_51 10.1109/CVPR42600.2020.01146 10.1007/s43154-020-00021-6 10.1109/IROS.2017.8202237 10.1109/LRA.2023.3293314 10.1109/CASE49997.2022.9926427 10.15607/RSS.2017.XIII.058 10.1109/ICRA.2018.8463191 10.1109/IROS40897.2019.8967594 10.1109/LRA.2019.2895878 10.1109/IROS.2017.8202133 10.1109/ICRA.2018.8460875 10.1109/ICRA.2018.8460887 10.1007/978-3-030-01231-1_43 10.1007/978-3-031-19842-7_22 10.1109/IROS.2018.8593933 10.1109/LRA.2023.3240362 10.1109/CVPR.2017.106 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
DOI | 10.1109/LRA.2023.3337692 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
DatabaseTitleList | Technology Research Database |
Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
EISSN | 2377-3766 |
EndPage | 8 |
ExternalDocumentID | 10_1109_LRA_2023_3337692 10333337 |
Genre | orig-research |
GrantInformation_xml | – fundername: Ministry of Trade, Industry and Energy (MOTIE, Korea), through the Industrial Strategic Technology Development Program grantid: 20014558 |
GroupedDBID | 0R~ 97E AAJGR AASAJ ABQJQ ABVLG ACGFS AKJIK ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL RIA RIE RIG AAYXX CITATION EJD 7SC 7SP 8FD JQ2 L7M L~C L~D |
ID | FETCH-LOGICAL-c245t-65aac39c0ebe085e886c31f2113ab8b590ce8e5a1cbee98ec01138488577616a3 |
IEDL.DBID | RIE |
ISSN | 2377-3766 |
IngestDate | Thu Oct 10 20:26:29 EDT 2024 Fri Aug 23 01:04:17 EDT 2024 Wed Jun 26 19:24:17 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 1 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c245t-65aac39c0ebe085e886c31f2113ab8b590ce8e5a1cbee98ec01138488577616a3 |
ORCID | 0000-0001-9190-9372 0000-0003-2902-7453 0000-0002-1221-057X 0009-0007-1350-379X 0009-0004-2212-0561 0009-0002-5477-6587 0000-0002-8672-2359 0009-0004-9342-7544 0009-0000-3538-8453 |
PQID | 2901313155 |
PQPubID | 4437225 |
PageCount | 8 |
ParticipantIDs | ieee_primary_10333337 proquest_journals_2901313155 crossref_primary_10_1109_LRA_2023_3337692 |
PublicationCentury | 2000 |
PublicationDate | 2024-01-01 |
PublicationDateYYYYMMDD | 2024-01-01 |
PublicationDate_xml | – month: 01 year: 2024 text: 2024-01-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Piscataway |
PublicationPlace_xml | – name: Piscataway |
PublicationTitle | IEEE robotics and automation letters |
PublicationTitleAbbrev | LRA |
PublicationYear | 2024 |
Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
References | ref13 ref12 ref15 ref14 ref31 ref30 ref11 ref10 ref32 ref2 ref1 ref17 ref16 ref19 ref18 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 |
References_xml | – ident: ref30 doi: 10.1177/0278364912445831 – ident: ref21 doi: 10.1109/LRA.2021.3115406 – ident: ref29 doi: 10.1109/ICAR.2015.7251504 – ident: ref27 doi: 10.1109/CVPR.2019.01291 – ident: ref22 doi: 10.1177/0278364919868017 – ident: ref5 doi: 10.3390/app10165442 – ident: ref4 doi: 10.1109/LRA.2023.3247221 – ident: ref17 doi: 10.3389/fnbot.2022.806898 – ident: ref6 doi: 10.1007/978-3-319-14249-4_75 – ident: ref18 doi: 10.1177/0278364914549607 – ident: ref13 doi: 10.1126/scirobotics.aau4984 – ident: ref31 doi: 10.1109/ICCVW.2019.00187 – ident: ref2 doi: 10.1109/ICCV.2017.169 – ident: ref16 doi: 10.1109/ICRA46639.2022.9811599 – ident: ref9 doi: 10.1007/978-3-319-68792-6_51 – ident: ref20 doi: 10.1109/CVPR42600.2020.01146 – ident: ref8 doi: 10.1007/s43154-020-00021-6 – ident: ref19 doi: 10.1109/IROS.2017.8202237 – ident: ref15 doi: 10.1109/LRA.2023.3293314 – ident: ref23 doi: 10.1109/CASE49997.2022.9926427 – ident: ref11 doi: 10.15607/RSS.2017.XIII.058 – ident: ref10 doi: 10.1109/ICRA.2018.8463191 – ident: ref3 doi: 10.1109/IROS40897.2019.8967594 – ident: ref14 doi: 10.1109/LRA.2019.2895878 – ident: ref24 doi: 10.1109/IROS.2017.8202133 – ident: ref26 doi: 10.1109/ICRA.2018.8460875 – ident: ref12 doi: 10.1109/ICRA.2018.8460887 – ident: ref1 doi: 10.1007/978-3-030-01231-1_43 – ident: ref32 doi: 10.1007/978-3-031-19842-7_22 – ident: ref25 doi: 10.1109/IROS.2018.8593933 – ident: ref7 doi: 10.1109/LRA.2023.3240362 – ident: ref28 doi: 10.1109/CVPR.2017.106 |
SSID | ssj0001527395 |
Score | 2.2970262 |
Snippet | Robotic grasping is one of the essential skills in robotics. From industrial to housework, robots are required to handle objects, enabling them to interact... |
SourceID | proquest crossref ieee |
SourceType | Aggregation Database Publisher |
StartPage | 1 |
SubjectTerms | Annotations Collision avoidance Computer Vision for Automation Context Data Sets for Robotic Vision Datasets Deep Learning in Grasping and Manipulation Grasping Grasping (robotics) Object oriented modeling Outliers (statistics) Picking Pipelines Robotics Robots Seals Springs Suction Suction Grasping Synthetic data |
Title | CoAS-Net: Context-Aware Suction Network with a Large-Scale Domain Randomized Synthetic Dataset |
URI | https://ieeexplore.ieee.org/document/10333337 https://www.proquest.com/docview/2901313155 |
Volume | 9 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NT4MwFH9xO-nBb-N0mh68eCgCXYF6W_yIMbrDpoknSSmPxJiBmSzGHfzbfQUWp8ZEuHCg0PT32r7PXwGOVJqR3IiM-wIV7xHqPMlSwdFFtIyfAjNrKN4Ogqv73vWDfGiK1ataGESsks_QsY9VLD8tzNS6ymiGC3uFLWhFrl8Xa305VCyVmJLzUKSrTm6GfceeDu7YNoHyv2091Vkqvxbgale5XIPBvD91MsmzMy0Tx8x-UDX-u8PrsNrol6xfC8QGLGG-CSsLrINb8HhW9Ed8gOUpq7ipyPTtv-kJslHNJMsGdWo4sz5aptmNTRbnIwIT2Xkx1k85G-o8LcZPM0zZ6D0nHZL-xs51SVtiuQ33lxd3Z1e8OWaBG78nSx5IrY1QxiU8SQHDKAqM8DKyDIVOokQq12CEUnsmQVQRGloSREQTX4Zh4AVa7EA7L3LcBZYoWlwD9I1nefXCRHtZkEbKw1BJ4aPuwPEcgfilZtOIKyvEVTGhFVu04gatDmzbAV14rx7LDnTnmMXNfHuNbTRY0C3l3h_N9mGZvt6rvSddaJeTKR6QPlEmh9C6_bg4rKTpE3zjyFU |
link.rule.ids | 315,786,790,802,27955,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT4QwEJ74OKgH38b12YMXD0WgW6DeNj6y6srB1cSTpJQhMUYwysbor3cKbHzFRLhwoGnTb6bz6PQrwJ7KcpIbkXNfoOJdQp2neSY4uoiW8VNgbgPFyzjo33TPb-Vte1i9PguDiHXxGTr2s97Lz0ozsqky0nBhn3ASpsnQu2FzXOszpWLJxJQcb0a66mBw1XPs_eCObRUo_5vxqW9T-bUE13bldAHi8YiacpIHZ1Sljnn_Qdb47yEvwnzrYbJeIxJLMIHFMsx94R1cgbujsjfkMVaHrGanouC396qfkQ0bLlkWN8XhzGZpmWYDWy7OhwQnsuPyUd8X7EoXWfl4_44ZG74V5EVSb-xYV2QUq1W4OT25Purz9qIFbvyurHggtTZCGZcQJRcMoygwwsspNhQ6jVKpXIMRSu2ZFFFFaGhREBGpvgzDwAu0WIOpoixwHViqaHkN0DeeZdYLU-3lQRYpD0MlhY-6A_tjBJKnhk8jqeMQVyWEVmLRSlq0OrBqJ_TLf81cdmBrjFnSatxLYveDBb1SbvzRbBdm-teXg2RwFl9swiz11G1yKVswVT2PcJu8iyrdqWXqA3hoyng |
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=CoAS-Net%3A+Context-Aware+Suction+Network+with+a+Large-Scale+Domain+Randomized+Synthetic+Dataset&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Son%2C+Yeong+Gwang&rft.au=Bui%2C+Tat+Hieu&rft.au=Hong%2C+Juyong&rft.au=Kim%2C+Yong+Hyeon&rft.date=2024-01-01&rft.pub=IEEE&rft.eissn=2377-3766&rft.spage=1&rft.epage=8&rft_id=info:doi/10.1109%2FLRA.2023.3337692&rft.externalDocID=10333337 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2377-3766&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2377-3766&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2377-3766&client=summon |