Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Deep kernels for optimizing locomotion controllers
KTH, School of Computer Science and Communication (CSC), Robotics, perception and learning, RPL. (Robotik, perception och lärande, RPL, Robotics, perception and learning, RPL)ORCID iD: 0000-0002-3018-2445
Robotics Institute, School of Computer Science, Carnegie Mellon University, USA.
Robotics Institute, School of Computer Science, Carnegie Mellon University, USA.
2017 (English)In: Proceedings of the 1st Annual Conference on Robot Learning, PMLR , 2017Conference paper, Published paper (Refereed)
Abstract [en]

Sample efciency is important when optimizing parameters of locomotion controllers, since hardware experiments are time consuming and expensive. Bayesian Optimization, a sample-efcient optimization framework, has recently been widely applied to address this problem, but further improvements in sample efciency are needed for practical applicability to real-world robots and highdimensional controllers. To address this, prior work has proposed using domain expertise for constructing custom distance metrics for locomotion. In this work we show how to learn such a distance metric automatically. We use a neural network to learn an informed distance metric from data obtained in high-delity simulations. We conduct experiments on two different controllers and robot architectures. First, we demonstrate improvement in sample efciency when optimizing a 5-dimensional controller on the ATRIAS robot hardware. We then conduct simulation experiments to optimize a 16-dimensional controller for a 7-link robot model and obtain signicant improvements even when optimizing in perturbed environments. This demonstrates that our approach is able to enhance sample efciency for two different controllers, hence is a tting candidate for further experiments on hardware in the future. Keywor

Place, publisher, year, edition, pages
PMLR , 2017.
Series
Proceedings of Machine Learning Research
Keywords [en]
Bayesian Optimization, Simulator-to-Robot Transfer, Bipedal Locomotion
National Category
Robotics
Identifiers
URN: urn:nbn:se:kth:diva-220510OAI: oai:DiVA.org:kth-220510DiVA, id: diva2:1168668
Conference
1st Annual Conference on Robot Learning (CoRL)
Funder
Knut and Alice Wallenberg Foundation
Note

QC 20180108

Available from: 2017-12-21 Created: 2017-12-21 Last updated: 2018-01-08Bibliographically approved

Open Access in DiVA

fulltext(6908 kB)17 downloads
File information
File name FULLTEXT01.pdfFile size 6908 kBChecksum SHA-512
b5a1e6cccb4d29792e2b2700243c819b9b9dd8de80426e0f0ed15da10efebb745e9767383ba08052a81ba5b9d4858b303b547f06fe9412ef6adcd992160af145
Type fulltextMimetype application/pdf

Other links

Published version

Search in DiVA

By author/editor
Antonova, Rika
By organisation
Robotics, perception and learning, RPL
Robotics

Search outside of DiVA

GoogleGoogle Scholar
Total: 17 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 22 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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