Autonomous Robotic Pepper Harvesting: Imitation Learning in Unstructured Agricultural Environments

Automating tasks in outdoor agricultural fields poses significant challenges due to environmental variability, unstructured terrain, and diverse crop characteristics. We present a robotic system that leverages imitation learning for autonomous pepper harvesting designed to operate in these complex s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE robotics and automation letters Jg. 10; H. 4; S. 3406 - 3413
Hauptverfasser: Kim, Chung Hee, Silwal, Abhisesh, Kantor, George
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 01.04.2025
Schlagworte:
Agricultural automation
Cameras
Crops
Data collection
Faces
Grippers
Imitation learning
learning from demonstration
robotics and automation in agriculture and forestry
Robots
Robustness
Service robots
Training
ISSN:2377-3766, 2377-3766
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Automating tasks in outdoor agricultural fields poses significant challenges due to environmental variability, unstructured terrain, and diverse crop characteristics. We present a robotic system that leverages imitation learning for autonomous pepper harvesting designed to operate in these complex settings. Utilizing a custom handheld shear-gripper, we collected 300 demonstrations to train a visuomotor policy, enabling the system to adapt to varying field conditions and crop diversity. We achieved a success rate of 28.95% with a cycle time of 31.71 seconds, comparable to existing systems tested under more controlled conditions like greenhouses. Our system demonstrates the potential feasibility and effectiveness of employing imitation learning for automated harvesting in unstructured agricultural environments. This work aims to advance scalable, automated robotic solutions for agriculture in natural settings.
AbstractList Automating tasks in outdoor agricultural fields poses significant challenges due to environmental variability, unstructured terrain, and diverse crop characteristics. We present a robotic system that leverages imitation learning for autonomous pepper harvesting designed to operate in these complex settings. Utilizing a custom handheld shear-gripper, we collected 300 demonstrations to train a visuomotor policy, enabling the system to adapt to varying field conditions and crop diversity. We achieved a success rate of 28.95% with a cycle time of 31.71 seconds, comparable to existing systems tested under more controlled conditions like greenhouses. Our system demonstrates the potential feasibility and effectiveness of employing imitation learning for automated harvesting in unstructured agricultural environments. This work aims to advance scalable, automated robotic solutions for agriculture in natural settings.
Author Silwal, Abhisesh
Kim, Chung Hee
Kantor, George
Author_xml – sequence: 1
  givenname: Chung Hee
  orcidid: 0000-0001-7710-5984
  surname: Kim
  fullname: Kim, Chung Hee
  email: chunghek@andrew.cmu.edu
  organization: Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA
– sequence: 2
  givenname: Abhisesh
  orcidid: 0000-0002-1710-6704
  surname: Silwal
  fullname: Silwal, Abhisesh
  email: asilwal@andrew.cmu.edu
  organization: Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA
– sequence: 3
  givenname: George
  orcidid: 0000-0001-7088-8533
  surname: Kantor
  fullname: Kantor, George
  email: gkantor@andrew.cmu.edu
  organization: Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA
BookMark eNp9kLFqwzAQhkVJoWmavUMHvYBTWbIku5sJaRIwtIRmNrIkBxVbCpIc6NvXIRlCh05398N3x32PYGKd1QA8p2iRpqh4rXblAiNMF4RmmGB8B6aYcJ4Qztjkpn8A8xC-EUIpxZwUdAqacojOut4NAe5c46KR8FMfj9rDjfAnHaKxhze47U0U0TgLKy28HTNoLNzbEP0g4-C1guXBGzl04yA6uLIn453ttY3hCdy3ogt6fq0zsH9ffS03SfWx3i7LKpGYZTFhbYZVxmieqYJT2hZCMElZnqUZkYg2RU4VQYqLtmCSNEylmBZSa0JbpXiuyAygy17pXQhet_XRm174nzpF9VlTPWqqz5rqq6YRYX8Qef0zemG6_8CXC2i01jd38pwThMkvQRR42Q
CODEN IRALC6
CitedBy_id crossref_primary_10_1016_j_asoc_2025_113628
Cites_doi 10.1007/s41315-019-00103-5
10.1109/ICRA46639.2022.9811628
10.3390/s20092672
10.1109/LRA.2024.3386463
10.1109/IROS.2018.8594368
10.1109/LRA.2024.3357397
10.1109/ICRA57147.2024.10611327
10.3389/frobt.2024.1441312
10.3390/robotics13070098
10.1109/Humanoids53995.2022.10000171
10.1109/iros58592.2024.10802082
10.1002/rob.21889
10.1109/ACCESS.2020.3006919
10.1109/ICRA57147.2024.10610866
10.1016/j.compag.2024.109195
10.1002/rob.21973
10.1109/LRA.2020.2976314
10.1109/IROS.2016.7759122
10.1002/rob.21709
10.1007/s10846-022-01793-z
10.1109/ICRA48891.2023.10160650
10.15607/RSS.2023.XIX.026
10.1002/rob.21937
10.1109/ICRA48891.2023.10161400
10.15607/RSS.2024.XX.045
10.1109/TRO.2021.3075644
10.55417/fr.2022051
10.1109/ICRA.2016.7487394
10.1109/LRA.2017.2651952
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/LRA.2025.3542322
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 Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2377-3766
EndPage 3413
ExternalDocumentID 10_1109_LRA_2025_3542322
10887302
Genre orig-research
GrantInformation_xml – fundername: NSF
  grantid: 2138259; 2138286; 2138307; 2137603; 2138296
– fundername: NSF/USDA-NIFA AIIRA AI Research Institute
  grantid: 2021-67021-35329
– fundername: Bridges-2 at Pittsburgh Supercomputing Center through allocation
– fundername: NSF Robust Intelligence
  grantid: 1956163
GroupedDBID 0R~
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFS
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IFIPE
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
RIA
RIE
AAYXX
CITATION
ID FETCH-LOGICAL-c264t-6f42d46584d9755f9aa6c5684143c05b985d30d7af96c3b6d1259cee35fdd78d3
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001434749300013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2377-3766
IngestDate Sat Nov 29 08:08:38 EST 2025
Tue Nov 18 22:18:45 EST 2025
Wed Aug 27 01:49:28 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 4
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-c264t-6f42d46584d9755f9aa6c5684143c05b985d30d7af96c3b6d1259cee35fdd78d3
ORCID 0000-0001-7710-5984
0000-0001-7088-8533
0000-0002-1710-6704
PageCount 8
ParticipantIDs crossref_primary_10_1109_LRA_2025_3542322
ieee_primary_10887302
crossref_citationtrail_10_1109_LRA_2025_3542322
PublicationCentury 2000
PublicationDate 2025-04-01
PublicationDateYYYYMMDD 2025-04-01
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-04-01
  day: 01
PublicationDecade 2020
PublicationTitle IEEE robotics and automation letters
PublicationTitleAbbrev LRA
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref12
ref15
ref14
ref31
ref30
ref11
Ho (ref27) 2020
ref10
ref32
ref2
Ven (ref25) 2024
ref17
ref16
ref19
ref18
ref24
ref23
ref26
ref20
ref22
ref21
ref28
ref29
ref8
ref7
ref9
ref4
ref3
ref6
ref5
Cheng (ref1) 2023; 11
References_xml – ident: ref28
  doi: 10.1007/s41315-019-00103-5
– ident: ref12
  doi: 10.1109/ICRA46639.2022.9811628
– ident: ref6
  doi: 10.3390/s20092672
– start-page: 6840
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2020
  ident: ref27
  article-title: Denoising diffusion probabilistic models
– ident: ref8
  doi: 10.1109/LRA.2024.3386463
– ident: ref26
  doi: 10.1109/IROS.2018.8594368
– ident: ref31
  doi: 10.1109/LRA.2024.3357397
– ident: ref10
  doi: 10.1109/ICRA57147.2024.10611327
– ident: ref3
  doi: 10.3389/frobt.2024.1441312
– ident: ref22
  doi: 10.3390/robotics13070098
– ident: ref32
  doi: 10.1109/Humanoids53995.2022.10000171
– ident: ref16
  doi: 10.1109/iros58592.2024.10802082
– ident: ref13
  doi: 10.1002/rob.21889
– ident: ref15
  doi: 10.1109/ACCESS.2020.3006919
– ident: ref17
  doi: 10.1109/ICRA57147.2024.10610866
– ident: ref24
  doi: 10.1016/j.compag.2024.109195
– ident: ref20
  doi: 10.1002/rob.21973
– ident: ref23
  doi: 10.1109/LRA.2020.2976314
– ident: ref14
  doi: 10.1109/IROS.2016.7759122
– ident: ref19
  doi: 10.1002/rob.21709
– ident: ref2
  doi: 10.1007/s10846-022-01793-z
– ident: ref9
  doi: 10.1109/ICRA48891.2023.10160650
– volume: 11
  issue: 1
  volume-title: Machines
  year: 2023
  ident: ref1
  article-title: Recent advancements in agriculture robots: Benefits and challenges
– ident: ref5
  doi: 10.15607/RSS.2023.XIX.026
– ident: ref21
  doi: 10.1002/rob.21937
– ident: ref7
  doi: 10.1109/ICRA48891.2023.10161400
– ident: ref4
  doi: 10.15607/RSS.2024.XX.045
– ident: ref29
  doi: 10.1109/TRO.2021.3075644
– ident: ref11
  doi: 10.55417/fr.2022051
– ident: ref18
  doi: 10.1109/ICRA.2016.7487394
– ident: ref30
  doi: 10.1109/LRA.2017.2651952
– year: 2024
  ident: ref25
  article-title: DualLQR: Efficient grasping of oscillating apples using task parameterized learning from demonstration
SSID ssj0001527395
Score 2.3330443
Snippet Automating tasks in outdoor agricultural fields poses significant challenges due to environmental variability, unstructured terrain, and diverse crop...
SourceID crossref
ieee
SourceType Enrichment Source
Index Database
Publisher
StartPage 3406
SubjectTerms Agricultural automation
Cameras
Crops
Data collection
Faces
Grippers
Imitation learning
learning from demonstration
robotics and automation in agriculture and forestry
Robots
Robustness
Service robots
Training
Title Autonomous Robotic Pepper Harvesting: Imitation Learning in Unstructured Agricultural Environments
URI https://ieeexplore.ieee.org/document/10887302
Volume 10
WOSCitedRecordID wos001434749300013&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 Electronic Library (IEL)
  customDbUrl:
  eissn: 2377-3766
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001527395
  issn: 2377-3766
  databaseCode: RIE
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2377-3766
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001527395
  issn: 2377-3766
  databaseCode: M~E
  dateStart: 20160101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED7RigEGnkWUR-WBhSFtSOw4ZotQK5BKVVVU6hYlflSVIKlCy8hvx07cEgaQ2KLozkr82bo7n-87gJs7s248FztCYuXgJOAOE0o4KadYKR5yQstC4SEdjcLZjI1tsXpZCyOlLC-fya55LHP5Iudrc1Smd7jeEr6hjmxQSqtire8DFUMlxsgmFemy3nAS6QDQI12fmHSk98P01HqplKZkcPjPjziCA-szoqgC-Rh2ZHYC-zUmwVNIo_XKlCfoOB5N8jTXkmgsl0tZINP9x1BpZPN79PRmKbmR5VWdo0WGppZFdl1IgaJ5saXjQP1aGVwLpoP-y8OjY9snOFx7OSsnUNgT2HgYglFCFEs0EiQIsXaRuEtSFhLhu4ImigXcTwOhfR2mbaZPlBA0FP4ZNLM8k-eAcCi5jhu1PyCEHjRJjDILmEyxl2CXt6G3mdmY2x8xLS5e4zLGcFmssYgNFrHFog23W41lxavxh2zLwFCTqxC4-OX9JewZ9ep-zRU09RTKa9jlH6vFe9GBxvNnv1OunS-JYMQ5
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA8yBfXg58T5mYMXD926Nmkbb0M2NqxjjA12K20-xkDbUTf_fvPabNaDgrdSktDml_Dey8vv9xB6aMO6cWxiCUmURWKPW0woYSXcJ0rxgFO_IAqH_nAYzGZsZMjqBRdGSllcPpNNeCxy-SLjazgq0ztcbwkXpCN3KSFOu6RrfR-pgJgYo5tkpM1a4bijQ0CHNl0KCUnnh_GpVFMpjEnv-J-fcYKOjNeIOyXMp2hHpmfosKIleI6SznoFBAUdyeNxlmS6JR7J5VLmGOr_gJhGOn_Cg3cjyo2NsuocL1I8NTqy61wK3JnnW0EO3K0Q4epo2utOnvuWKaBgce3nrCxPEUcQ8DEE8ylVLNZYUC8g2kniNk1YQIVrCz9WzONu4gnt7TBtNV2qhPAD4V6gWpql8hJhEkiuI0ftEQihB41j6Mw8JhPixMTmDdTazGzEzY9AkYu3qIgybBZpLCLAIjJYNNDjtseyVNb4o20dYKi0KxG4-uX9PdrvT17DKBwMX67RAQxV3ra5QTU9nfIW7fHP1eIjvytW0BdBPMZP
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=Autonomous+Robotic+Pepper+Harvesting%3A+Imitation+Learning+in+Unstructured+Agricultural+Environments&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Kim%2C+Chung+Hee&rft.au=Silwal%2C+Abhisesh&rft.au=Kantor%2C+George&rft.date=2025-04-01&rft.issn=2377-3766&rft.eissn=2377-3766&rft.volume=10&rft.issue=4&rft.spage=3406&rft.epage=3413&rft_id=info:doi/10.1109%2FLRA.2025.3542322&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LRA_2025_3542322
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