oru.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Global Search with Bernoulli Alternation Kernel for Task-oriented Grasping Informed by Simulation
Robotics, Perception and Learning, CSC, Royal Institute of Technology, Stockholm, Sweden.
Robotics, Perception and Learning, CSC, Royal Institute of Technology, Stockholm, Sweden.
Robotics, Perception and Learning, CSC, Royal Institute of Technology, Stockholm, Sweden. (AASS)ORCID iD: 0000-0003-3958-6179
Robotics, Perception and Learning, CSC, Royal Institute of Technology, Stockholm, Sweden.
2018 (English)In: Proceedings of Machine Learning Research: Conference on Robot Learning 2018, PMLR , 2018, Vol. 87, p. 641-650Conference paper, Published paper (Refereed)
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.

Place, publisher, year, edition, pages
PMLR , 2018. Vol. 87, p. 641-650
Series
Proceedings of Machine Learning Research, ISSN 2640-3498
Keywords [en]
Bayesian optimization, Deep learning, Task-oriented grasping
National Category
Computer Sciences Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:oru:diva-71550OAI: oai:DiVA.org:oru-71550DiVA, id: diva2:1280223
Conference
The 2nd Conference on Robot Learning (CoRL), Zürich, Switzerland, October 29-31, 2018
Funder
Knut and Alice Wallenberg FoundationAvailable from: 2019-01-18 Created: 2019-01-18 Last updated: 2019-01-24Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Electronic full texthttp://proceedings.mlr.press/v87/antonova18a.html

Authority records BETA

Stork, Johannes Andreas

Search in DiVA

By author/editor
Stork, Johannes Andreas
Computer SciencesComputer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 96 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf