DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cyr, Caralyn | - |
dc.contributor.author | Dostal, Leo | - |
dc.contributor.author | Dücker, Daniel-André | - |
dc.contributor.author | Kreuzer, Edwin | - |
dc.date.accessioned | 2019-09-16T13:20:11Z | - |
dc.date.available | 2019-09-16T13:20:11Z | - |
dc.date.issued | 2019-06 | - |
dc.identifier.citation | European Control Conference, ECC 2019 : 3934-3939 (2019-06) | de_DE |
dc.identifier.isbn | 978-390714400-8 | de_DE |
dc.identifier.uri | http://hdl.handle.net/11420/3365 | - |
dc.description.abstract | Harvesting energy from the environment, e.g. ocean waves, is a key capability for the long-term operation of remote electronic systems where standard energy supply is not available. Rotating pendulums can be used as energy converters when excited close to their eigenfrequency. However, to ensure robust operation of the harvester, the energy of the dynamic system has to be controlled. In this study, we deploy a light-weight reinforcement learning algorithm to drive the energy of an Acrobot pendulum towards a desired value. We analyze the algorithm in an extensive series of simulations. Moreover, we explore the real world application of our energy-based reinforcement learning algorithm using a computationally constrained hardware setup based on low-cost components, such as the Raspberry Pi platform. | en |
dc.language.iso | en | de_DE |
dc.subject.ddc | 620: Ingenieurwissenschaften | de_DE |
dc.title | Towards reinforcement learning-based control of an energy harvesting pendulum | de_DE |
dc.type | inProceedings | de_DE |
dc.type.dini | contributionToPeriodical | - |
dcterms.DCMIType | Text | - |
tuhh.abstract.english | Harvesting energy from the environment, e.g. ocean waves, is a key capability for the long-term operation of remote electronic systems where standard energy supply is not available. Rotating pendulums can be used as energy converters when excited close to their eigenfrequency. However, to ensure robust operation of the harvester, the energy of the dynamic system has to be controlled. In this study, we deploy a light-weight reinforcement learning algorithm to drive the energy of an Acrobot pendulum towards a desired value. We analyze the algorithm in an extensive series of simulations. Moreover, we explore the real world application of our energy-based reinforcement learning algorithm using a computationally constrained hardware setup based on low-cost components, such as the Raspberry Pi platform. | de_DE |
tuhh.publisher.doi | 10.23919/ECC.2019.8795916 | - |
tuhh.publication.institute | Mechanik und Meerestechnik M-13 | de_DE |
tuhh.type.opus | InProceedings (Aufsatz / Paper einer Konferenz etc.) | - |
tuhh.institute.german | Mechanik und Meerestechnik M-13 | de |
tuhh.institute.english | Mechanik und Meerestechnik M-13 | de_DE |
tuhh.gvk.hasppn | false | - |
dc.type.driver | contributionToPeriodical | - |
dc.type.casrai | Conference Paper | - |
tuhh.container.startpage | 3934 | de_DE |
tuhh.container.endpage | 3939 | de_DE |
dc.relation.conference | 18th European Control Conference, ECC 2019 | de_DE |
dc.relation.project | Dezentrale kooperative Exploration von nichtstationären räumlich und zeitlich verteilten Feldern mit autonomen Unterwasserfahrzeugen | de_DE |
dc.identifier.scopus | 2-s2.0-85071551553 | de_DE |
tuhh.container.articlenumber | 8795916 | de_DE |
local.status.inpress | false | de_DE |
datacite.resourceType | Conference Paper | - |
datacite.resourceTypeGeneral | ConferencePaper | - |
item.openairecristype | http://purl.org/coar/resource_type/c_5794 | - |
item.languageiso639-1 | en | - |
item.creatorGND | Cyr, Caralyn | - |
item.creatorGND | Dostal, Leo | - |
item.creatorGND | Dücker, Daniel-André | - |
item.creatorGND | Kreuzer, Edwin | - |
item.mappedtype | inProceedings | - |
item.cerifentitytype | Publications | - |
item.openairetype | inProceedings | - |
item.fulltext | No Fulltext | - |
item.grantfulltext | none | - |
item.creatorOrcid | Cyr, Caralyn | - |
item.creatorOrcid | Dostal, Leo | - |
item.creatorOrcid | Dücker, Daniel-André | - |
item.creatorOrcid | Kreuzer, Edwin | - |
crisitem.project.funder | Deutsche Forschungsgemeinschaft (DFG) | - |
crisitem.project.funderid | 501100001659 | - |
crisitem.project.funderrorid | 018mejw64 | - |
crisitem.project.grantno | KR 752/36-1 | - |
crisitem.author.dept | Mechanik und Meerestechnik M-13 | - |
crisitem.author.dept | Mechanik und Meerestechnik M-13 | - |
crisitem.author.dept | Mechanik und Meerestechnik M-13 | - |
crisitem.author.dept | Mechanik und Meerestechnik M-13 | - |
crisitem.author.orcid | 0000-0002-0365-2587 | - |
crisitem.author.orcid | 0000-0001-7256-6984 | - |
crisitem.author.parentorg | Studiendekanat Maschinenbau | - |
crisitem.author.parentorg | Studiendekanat Maschinenbau | - |
crisitem.author.parentorg | Studiendekanat Maschinenbau | - |
crisitem.author.parentorg | Studiendekanat Maschinenbau | - |
Appears in Collections: | Publications without fulltext |
Add Files to Item
Note about this record
Cite this record
Export
Items in TORE are protected by copyright, with all rights reserved, unless otherwise indicated.