DC FieldValueLanguage
dc.contributor.authorCyr, Caralyn-
dc.contributor.authorDostal, Leo-
dc.contributor.authorDücker, Daniel-André-
dc.contributor.authorKreuzer, Edwin-
dc.date.accessioned2019-09-16T13:20:11Z-
dc.date.available2019-09-16T13:20:11Z-
dc.date.issued2019-06-
dc.identifier.citationEuropean Control Conference, ECC 2019 : 3934-3939 (2019-06)de_DE
dc.identifier.isbn978-390714400-8de_DE
dc.identifier.urihttp://hdl.handle.net/11420/3365-
dc.description.abstractHarvesting 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.isoende_DE
dc.subject.ddc620: Ingenieurwissenschaftende_DE
dc.titleTowards reinforcement learning-based control of an energy harvesting pendulumde_DE
dc.typeinProceedingsde_DE
dc.type.dinicontributionToPeriodical-
dcterms.DCMITypeText-
tuhh.abstract.englishHarvesting 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.doi10.23919/ECC.2019.8795916-
tuhh.publication.instituteMechanik und Meerestechnik M-13de_DE
tuhh.type.opusInProceedings (Aufsatz / Paper einer Konferenz etc.)-
tuhh.institute.germanMechanik und Meerestechnik M-13de
tuhh.institute.englishMechanik und Meerestechnik M-13de_DE
tuhh.gvk.hasppnfalse-
dc.type.drivercontributionToPeriodical-
dc.type.casraiConference Paper-
tuhh.container.startpage3934de_DE
tuhh.container.endpage3939de_DE
dc.relation.conference18th European Control Conference, ECC 2019de_DE
dc.relation.projectDezentrale kooperative Exploration von nichtstationären räumlich und zeitlich verteilten Feldern mit autonomen Unterwasserfahrzeugende_DE
dc.identifier.scopus2-s2.0-85071551553de_DE
tuhh.container.articlenumber8795916de_DE
local.status.inpressfalsede_DE
datacite.resourceTypeConference Paper-
datacite.resourceTypeGeneralConferencePaper-
item.openairecristypehttp://purl.org/coar/resource_type/c_5794-
item.languageiso639-1en-
item.creatorGNDCyr, Caralyn-
item.creatorGNDDostal, Leo-
item.creatorGNDDücker, Daniel-André-
item.creatorGNDKreuzer, Edwin-
item.mappedtypeinProceedings-
item.cerifentitytypePublications-
item.openairetypeinProceedings-
item.fulltextNo Fulltext-
item.grantfulltextnone-
item.creatorOrcidCyr, Caralyn-
item.creatorOrcidDostal, Leo-
item.creatorOrcidDücker, Daniel-André-
item.creatorOrcidKreuzer, Edwin-
crisitem.project.funderDeutsche Forschungsgemeinschaft (DFG)-
crisitem.project.funderid501100001659-
crisitem.project.funderrorid018mejw64-
crisitem.project.grantnoKR 752/36-1-
crisitem.author.deptMechanik und Meerestechnik M-13-
crisitem.author.deptMechanik und Meerestechnik M-13-
crisitem.author.deptMechanik und Meerestechnik M-13-
crisitem.author.deptMechanik und Meerestechnik M-13-
crisitem.author.orcid0000-0002-0365-2587-
crisitem.author.orcid0000-0001-7256-6984-
crisitem.author.parentorgStudiendekanat Maschinenbau-
crisitem.author.parentorgStudiendekanat Maschinenbau-
crisitem.author.parentorgStudiendekanat Maschinenbau-
crisitem.author.parentorgStudiendekanat Maschinenbau-
Appears in Collections:Publications without fulltext
Show simple item record

Page view(s)

184
Last Week
1
Last month
7
checked on Jun 10, 2023

Google ScholarTM

Check

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.