Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • 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
Sample efficient optimization for learning controllers for bipedal locomotion
Robotics Institute, School of Computer Science, Carnegie Mellon University, USA.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.
2016 (engelsk)Inngår i: IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 2016, IEEE conference proceedings, 2016Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Learning policies for bipedal locomotion can be difficult, as experiments are expensive and simulation does not usually transfer well to hardware. To counter this, we need algorithms that are sample efficient and inherently safe. Bayesian Optimization is a powerful sample-efficient tool for optimizing non-convex black-box functions. However, its performance can degrade in higher dimensions. We develop a distance metric for bipedal locomotion that enhances the sample-efficiency of Bayesian Optimization and use it to train a 16 dimensional neuromuscular model for planar walking. This distance metric reflects some basic gait features of healthy walking and helps us quickly eliminate a majority of unstable controllers. With our approach we can learn policies for walking in less than 100 trials for a range of challenging settings. In simulation, we show results on two different costs and on various terrains including rough ground and ramps, sloping upwards and downwards. We also perturb our models with unknown inertial disturbances analogous with differences between simulation and hardware. These results are promising, as they indicate that this method can potentially be used to learn control policies on hardware.

sted, utgiver, år, opplag, sider
IEEE conference proceedings, 2016.
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-221061DOI: 10.1109/HUMANOIDS.2016.7803249ISI: 000403009300004Scopus ID: 2-s2.0-85010216190OAI: oai:DiVA.org:kth-221061DiVA, id: diva2:1172984
Konferanse
Humanoid Robots (Humanoids), 2016 IEEE-RAS 16th International Conference on
Merknad

QC 20171009

Tilgjengelig fra: 2018-01-11 Laget: 2018-01-11 Sist oppdatert: 2018-01-16bibliografisk kontrollert

Open Access i DiVA

fulltext(2689 kB)95 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 2689 kBChecksum SHA-512
46dd5400e44e644d5fb7f2b2f7d887fcddcd65c1f4203ecf9a55c35f78b2b47644a450880832a1d5e4e5e8bcf68fd54089394dc113fc7f7c117d2a517c103ace
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Søk i DiVA

Av forfatter/redaktør
Antonova, Rika

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 95 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 172 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • 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