Hybrid machine learning-based systems and methods for training an object picking robot with real and simulated performance data

For training an object picking robot with real and simulated grasp performance data, grasp locations on an object are assigned based on object physical properties. A simulation experiment for robot grasping is performed using a first set of assigned locations. Based on simulation data from the simul...

Full description

Saved in:
Bibliographic Details
Main Authors Fuhlbrigge, Thomas A, Choi, Sangeun, Huang, Jinmiao, Martinez, Carlos
Format Patent
LanguageEnglish
Published 13.09.2022
Subjects
CALCULATING
CHAMBERS PROVIDED WITH MANIPULATION DEVICES
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
HAND TOOLS
MANIPULATORS
PERFORMING OPERATIONS
PHYSICS
PORTABLE POWER-DRIVEN TOOLS
TRANSPORTING
Online AccessGet full text

Cover

Abstract For training an object picking robot with real and simulated grasp performance data, grasp locations on an object are assigned based on object physical properties. A simulation experiment for robot grasping is performed using a first set of assigned locations. Based on simulation data from the simulation, a simulated object grasp quality of the robot is evaluated for each of the assigned locations. A first set of candidate grasp locations on the object is determined based on data representative of simulated grasp quality from the evaluation. Based on sensor data from an actual experiment for the robot grasping using each of the candidate grasp locations, an actual object grasp quality is evaluated for each of the candidate locations.
AbstractList For training an object picking robot with real and simulated grasp performance data, grasp locations on an object are assigned based on object physical properties. A simulation experiment for robot grasping is performed using a first set of assigned locations. Based on simulation data from the simulation, a simulated object grasp quality of the robot is evaluated for each of the assigned locations. A first set of candidate grasp locations on the object is determined based on data representative of simulated grasp quality from the evaluation. Based on sensor data from an actual experiment for the robot grasping using each of the candidate grasp locations, an actual object grasp quality is evaluated for each of the candidate locations.
Author Fuhlbrigge, Thomas A
Choi, Sangeun
Martinez, Carlos
Huang, Jinmiao
Author_xml – fullname: Fuhlbrigge, Thomas A
– fullname: Choi, Sangeun
– fullname: Huang, Jinmiao
– fullname: Martinez, Carlos
BookMark eNqNjEsOgkAQRFnowt8d2gOQiLBwrdGwV9ekZ2hkdD5kuo1h5dUF4wFcVVL1Xs2TiQ-eZsm77FU0NTjUrfEEljB642-pQqYauGchx4B-QEjaUDM0IYJENCM2DBDUnbRAZ_RjbGJQQeBlpIVIaL8qG_e0KMNhR3HwHXpNUKPgMpk2aJlWv1wk69PxcihT6kJF3KEmT1Jdz1lWFJtsl--3-T_MB3UBStE
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
ExternalDocumentID US11440183B2
GroupedDBID EVB
ID FETCH-epo_espacenet_US11440183B23
IEDL.DBID EVB
IngestDate Fri Jul 19 15:05:40 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US11440183B23
Notes Application Number: US201916366700
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220913&DB=EPODOC&CC=US&NR=11440183B2
ParticipantIDs epo_espacenet_US11440183B2
PublicationCentury 2000
PublicationDate 20220913
PublicationDateYYYYMMDD 2022-09-13
PublicationDate_xml – month: 09
  year: 2022
  text: 20220913
  day: 13
PublicationDecade 2020
PublicationYear 2022
RelatedCompanies ABB Schweiz AG
RelatedCompanies_xml – name: ABB Schweiz AG
Score 3.4118173
Snippet For training an object picking robot with real and simulated grasp performance data, grasp locations on an object are assigned based on object physical...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
CHAMBERS PROVIDED WITH MANIPULATION DEVICES
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
HAND TOOLS
MANIPULATORS
PERFORMING OPERATIONS
PHYSICS
PORTABLE POWER-DRIVEN TOOLS
TRANSPORTING
Title Hybrid machine learning-based systems and methods for training an object picking robot with real and simulated performance data
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220913&DB=EPODOC&locale=&CC=US&NR=11440183B2
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB5Kfd60KlofjCC5BW0Ta3sIQpKWIPSBbaW30k12pWKT0ETEk3_dmTW1XvS6j4HdZHZmZ-f7BuBK1IVSUknTslREFxTVNIW0b0yhGqEdkoq1bMYOd3uNYGw_TG4nJXhZYWE0T-i7JkckjQpJ33N9XqfrIJavcyuzazGnpuS-M3J8o7gd1-tMc2n4rtMe9P2-Z3ieMx4avUenxo-Y9Pu6dFxvsBvNPPvtJ5dRKelvk9LZg80BSYvzfSjJuAI73qryWgW2u8WDdwW2dIZmmFFjoYXZAXwGH4yzwoVOhJRYVH54NtkkRfhNzpzhLKYhukB0huSa4qoaBHVgIjj-guk85FA5LhOR5MgxWSQn8lVPzeYLLu1FAtM1uAA5o_QQLjvtkReYtKbpzwZOx8P18q0jKMdJLI8BydWIbCkZVE5OUSsSteiu2ZjZoWTSeEudQPVvOdX_Ok9hlz8G51XUrDMo58s3eU7GOxcXete_AGCyoYg
link.rule.ids 230,309,786,891,25594,76906
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8MwDLam8Rg3GKAxXkFCvVWwtuxxqJDWbiqwl9iGdpuWNkFDrK3WIsSJv44dOsYFrklqKUkdO46_zwCX3OBSCil005QBXlBkXefCuta5rPqWjyrWsAg73O1VvbF1P7mZ5OBlhYVRPKHvihwRNcpHfU_VeR2vg1iuyq1Mrvgcm6Lb9sh2tex2bBhEc6m5Tbs16Lt9R3McezzUeo92hR4x8fdt4nG9USN2XnKdnpqESol_m5T2LmwOUFqY7kFOhEUoOKvKa0XY7mYP3kXYUhmafoKNmRYm-_DpfRDOii1UIqRgWeWHZ51MUsC-yZkTNgtxiCoQnTB0TdmqGgR2sIhT_IXFc59C5WwZ8ShlFJNl6ES-qk-T-YJKe6HAeA0uYJRRegAX7dbI8XSc0_RnAafj4Xr65iHkwygUJWDoagSWEAQqR6eoEfBKUKtXZ5YviDTelEdQ_ltO-b_Ocyh4o25n2rnrPRzDDm0M5VhUzBPIp8s3cYqGPOVnage-ABjdpHU
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%3Apatent&rft.title=Hybrid+machine+learning-based+systems+and+methods+for+training+an+object+picking+robot+with+real+and+simulated+performance+data&rft.inventor=Fuhlbrigge%2C+Thomas+A&rft.inventor=Choi%2C+Sangeun&rft.inventor=Huang%2C+Jinmiao&rft.inventor=Martinez%2C+Carlos&rft.date=2022-09-13&rft.externalDBID=B2&rft.externalDocID=US11440183B2