Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Global Search with Bernoulli Alternation Kernel for Task-oriented Grasping Informed by Simulation
KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.ORCID-id: 0000-0002-3018-2445
KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.ORCID-id: 0000-0003-2965-2953
2018 (engelsk)Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

We develop an approach that benefits from large simulated datasets and takes full advantage of the limited online data that is most relevant. We propose a variant of Bayesian optimization that alternates between using informed and uninformed kernels. With this Bernoulli Alternation Kernel we ensure that discrepancies between simulation and reality do not hinder adapting robot control policies online. The proposed approach is applied to a challenging real-world problem of task-oriented grasping with novel objects. Our further contribution is a neural network architecture and training pipeline that use experience from grasping objects in simulation to learn grasp stability scores. We learn task scores from a labeled dataset with a convolutional network, which is used to construct an informed kernel for our variant of Bayesian optimization. Experiments on an ABB Yumi robot with real sensor data demonstrate success of our approach, despite the challenge of fulfilling task requirements and high uncertainty over physical properties of objects.

sted, utgiver, år, opplag, sider
2018.
HSV kategori
Forskningsprogram
Datalogi
Identifikatorer
URN: urn:nbn:se:kth:diva-249696OAI: oai:DiVA.org:kth-249696DiVA, id: diva2:1305572
Konferanse
2nd Conference on Robot Learning, Zürich, Switzerland, Oct. 29-31 2018
Merknad

Contribution/Authorship note: Rika Antonova and Mia Kokic contributed equally

QC 20190520

Tilgjengelig fra: 2019-04-17 Laget: 2019-04-17 Sist oppdatert: 2019-05-20bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

http://proceedings.mlr.press/v87/antonova18a/antonova18a.pdf

Personposter BETA

Antonova, RikaKokic, MiaStork, Johannes A.Kragic, Danica

Søk i DiVA

Av forfatter/redaktør
Antonova, RikaKokic, MiaStork, Johannes A.Kragic, Danica
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric

urn-nbn
Totalt: 47 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf