GP-GPIS-OPT: Grasp planning with shape uncertainty using Gaussian process implicit surfaces and Sequential Convex Programming

Computing grasps for an object is challenging when the object geometry is not known precisely. In this paper, we explore the use of Gaussian process implicit surfaces (GPISs) to represent shape uncertainty from RGBD point cloud observations of objects. We study the use of GPIS representations to sel...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings - IEEE International Conference on Robotics and Automation pp. 4919 - 4926
Main Authors: Mahler, Jeffrey, Patil, Sachin, Kehoe, Ben, van den Berg, Jur, Ciocarlie, Matei, Abbeel, Pieter, Goldberg, Ken
Format: Conference Proceeding
Language:English
Published: IEEE 01.05.2015
Subjects:
Approximation methods
Force
Grippers
Sensors
Shape
Three-dimensional displays
Uncertainty
ISSN:1050-4729
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Computing grasps for an object is challenging when the object geometry is not known precisely. In this paper, we explore the use of Gaussian process implicit surfaces (GPISs) to represent shape uncertainty from RGBD point cloud observations of objects. We study the use of GPIS representations to select grasps on previously unknown objects, measuring grasp quality by the probability of force closure. Our main contribution is GP-GPIS-OPT, an algorithm for computing grasps for parallel-jaw grippers on 2D GPIS object representations. Specifically, our method optimizes an approximation to the probability of force closure subject to antipodal constraints on the parallel jaws using Sequential Convex Programming (SCP). We also introduce GPIS-Blur, a method for visualizing 2D GPIS models based on blending shape samples from a GPIS. We test the algorithm on a set of 8 planar objects with transparency, translucency, and specularity. Our experiments suggest that GP-GPIS-OPT computes grasps with higher probability of force closure than a planner that does not consider shape uncertainty on our test objects and may converge to a grasp plan up to 5.7×faster than using Monte-Carlo integration, a common method for grasp planning under shape uncertainty. Furthermore, initial experiments on the Willow Garage PR2 robot suggest that grasps selected with GP-GPIS-OPT are up to 90% more successful than those planned assuming a deterministic shape. Our dataset, code, and videos of our experiments are available at http://rll.berkeley.edu/icra2015grasping/.
AbstractList Computing grasps for an object is challenging when the object geometry is not known precisely. In this paper, we explore the use of Gaussian process implicit surfaces (GPISs) to represent shape uncertainty from RGBD point cloud observations of objects. We study the use of GPIS representations to select grasps on previously unknown objects, measuring grasp quality by the probability of force closure. Our main contribution is GP-GPIS-OPT, an algorithm for computing grasps for parallel-jaw grippers on 2D GPIS object representations. Specifically, our method optimizes an approximation to the probability of force closure subject to antipodal constraints on the parallel jaws using Sequential Convex Programming (SCP). We also introduce GPIS-Blur, a method for visualizing 2D GPIS models based on blending shape samples from a GPIS. We test the algorithm on a set of 8 planar objects with transparency, translucency, and specularity. Our experiments suggest that GP-GPIS-OPT computes grasps with higher probability of force closure than a planner that does not consider shape uncertainty on our test objects and may converge to a grasp plan up to 5.7×faster than using Monte-Carlo integration, a common method for grasp planning under shape uncertainty. Furthermore, initial experiments on the Willow Garage PR2 robot suggest that grasps selected with GP-GPIS-OPT are up to 90% more successful than those planned assuming a deterministic shape. Our dataset, code, and videos of our experiments are available at http://rll.berkeley.edu/icra2015grasping/.
Author Patil, Sachin
van den Berg, Jur
Mahler, Jeffrey
Kehoe, Ben
Ciocarlie, Matei
Abbeel, Pieter
Goldberg, Ken
Author_xml – sequence: 1
  givenname: Jeffrey
  surname: Mahler
  fullname: Mahler, Jeffrey
  email: jmahler@berkeley.edu
  organization: Dept. of EECS, Univ. of California, Berkeley, Berkeley, CA, USA
– sequence: 2
  givenname: Sachin
  surname: Patil
  fullname: Patil, Sachin
  email: sachinpatil@berkeley.edu
  organization: Dept. of EECS, Univ. of California, Berkeley, Berkeley, CA, USA
– sequence: 3
  givenname: Ben
  surname: Kehoe
  fullname: Kehoe, Ben
  email: benk@berkeley.edu
  organization: Dept. of ME, Univ. of California, Berkeley, Berkeley, CA, USA
– sequence: 4
  givenname: Jur
  surname: van den Berg
  fullname: van den Berg, Jur
  email: jurvandenberg@gmail.com
  organization: Google Inc., CA, USA
– sequence: 5
  givenname: Matei
  surname: Ciocarlie
  fullname: Ciocarlie, Matei
  email: matei.ciocarlie@columbia.edu
  organization: Dept. of ME, Colombia Univ., NY, USA
– sequence: 6
  givenname: Pieter
  surname: Abbeel
  fullname: Abbeel, Pieter
  email: pabbeel@berkeley.edu
  organization: Dept. of EECS, Univ. of California, Berkeley, Berkeley, CA, USA
– sequence: 7
  givenname: Ken
  surname: Goldberg
  fullname: Goldberg, Ken
  email: goldberg@berkeley.edu
  organization: Dept. of EECS, Univ. of California, Berkeley, Berkeley, CA, USA
BookMark eNotkNFKwzAYRiNMcJt7APEmL9CZNE3TeDeK1sFgxc3r8dv-3SJtWpNWtwvf3Ym7-uAcOBffhIxsa5GQO87mnDP9sExfF_OQcTlXXOgkCa_ITKuER0rrWIciGpExZ5IFkQr1DZl4_8EYEyKOx-Qny4MsX26Cdb59pJkD39GuBmuN3dNv0x-oP0CHdLAFuh6M7U908H8yg8F7A5Z2ri3Qe2qarjaF6akfXAVnRMGWdIOfA9reQE3T1n7hkeau3TtomnPkllxXUHucXXZK3p6ftulLsFpny3SxCgxXsg8SBaBLQMFRyrgUJWKiAQoWRshkFUOoKilkiSWCLuKoQBZJySGJikS9cyWm5P6_axBx1znTgDvtLm-JX2RfYoU
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICRA.2015.7139882
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9781479969234
1479969230
EndPage 4926
ExternalDocumentID 7139882
Genre orig-research
GroupedDBID 29O
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i175t-87aa9dae31e556d3dee89aac024e05f6a27f535dedea9c64ce04551a84c87b173
IEDL.DBID RIE
ISICitedReferencesCount 35
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000370974904125&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1050-4729
IngestDate Wed Aug 27 02:17:02 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-87aa9dae31e556d3dee89aac024e05f6a27f535dedea9c64ce04551a84c87b173
PageCount 8
ParticipantIDs ieee_primary_7139882
PublicationCentury 2000
PublicationDate 2015-May
PublicationDateYYYYMMDD 2015-05-01
PublicationDate_xml – month: 05
  year: 2015
  text: 2015-May
PublicationDecade 2010
PublicationTitle Proceedings - IEEE International Conference on Robotics and Automation
PublicationTitleAbbrev ICRA
PublicationYear 2015
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003366
Score 1.8247038
Snippet Computing grasps for an object is challenging when the object geometry is not known precisely. In this paper, we explore the use of Gaussian process implicit...
SourceID ieee
SourceType Publisher
StartPage 4919
SubjectTerms Approximation methods
Force
Grippers
Sensors
Shape
Three-dimensional displays
Uncertainty
Title GP-GPIS-OPT: Grasp planning with shape uncertainty using Gaussian process implicit surfaces and Sequential Convex Programming
URI https://ieeexplore.ieee.org/document/7139882
WOSCitedRecordID wos000370974904125&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ3PS8MwFMfDNjzoxR-b-JscPJqtXZu18SbDzYHM4qbsNl6TVy1oV9ZO9OD_btKWqeDFW-khhATe-ybv880j5FwIDqGNNhNSSeb6bpeFOiQwrUXAAlCeKLwwj7feeOzPZiKokYu1FwYRC_gM2-azqOWrhVyZq7KOPlAJrQjrpO55XunVWkddxynqklouWMzVirGqYNqW6Iz691cG4uLtaoBfnVSKRDLY_t8Udkjr25FHg3Wu2SU1TPbI1o_HBJvkcxiwYTCasLtgekmHS8hSmlYtiai5bqXZM6RIdSIrMYD8gxrq_YkOYZUZLyVNS9cAjQvMPM5ptlpGhtmikCg6KahrHRFeaN-w6u9mRgbuetWDtMjD4Hrav2FVcwUWa8WQ6ygIIBSgYyPnPeUoRF8ASJ2z0eJRD7pexB2uUCEI2XMlavHHbfBd6Xuh7Tn7pJEsEjwg1BwZHdTKpxdZrhO6ArjwdXDohsLoO35ImmYh52n5fsa8WsOjv38fk02zVyVUeEIa-XKFp2RDvuVxtjwrNv0LK2GuAA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ3PT8IwFMcbRBP14g8w_rYHjxY21rLVmyHyIyIugoYbeVsfSqKwsGH04P9uuy2oiRdvyw5N0y3vfdv3-fYRci6lgMBGm8lQhYx7vMYCHRKY1iJgAShXpl6Yx67b63nDofQL5GLphUHEFD7DinlMa_lqFi7MUVlVb6ikVoQrZFVwXrMzt9Yy7jpOWpnUgsFiXGvGvIZpW7LaadxfGYxLVPIhfvVSSVNJc-t_k9gm5W9PHvWX2WaHFHC6SzZ_XCdYIp8tn7X8Tp_d-YNL2ppDHNEob0pEzYErjZ8hQqpTWQYCJB_UcO9PtAWL2LgpaZT5BugkBc0nCY0X87GhtihMFe2n3LWOCS-0YWj1dzMjg3e96kHK5KF5PWi0Wd5egU20Zkh0HASQCtCxUYi6chSiJwFCnbXREuM61NyxcIRChSDDOg9Ryz9hg8dDzw1s19kjxelsivuEmk2jg1r71McWdwIuQUhPh4daII3CEwekZBZyFGU3aIzyNTz8-_UZWW8Pbrujbqd3c0Q2zHfLEMNjUkzmCzwha-FbMonnp-kP8AVkn7FH
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+-+IEEE+International+Conference+on+Robotics+and+Automation&rft.atitle=GP-GPIS-OPT%3A+Grasp+planning+with+shape+uncertainty+using+Gaussian+process+implicit+surfaces+and+Sequential+Convex+Programming&rft.au=Mahler%2C+Jeffrey&rft.au=Patil%2C+Sachin&rft.au=Kehoe%2C+Ben&rft.au=van+den+Berg%2C+Jur&rft.date=2015-05-01&rft.pub=IEEE&rft.issn=1050-4729&rft.spage=4919&rft.epage=4926&rft_id=info:doi/10.1109%2FICRA.2015.7139882&rft.externalDocID=7139882
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1050-4729&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1050-4729&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1050-4729&client=summon