Please use this identifier to cite or link to this item: https://doi.org/10.15480/882.4594
DC FieldValueLanguage
dc.contributor.authorWesselhöft, Mike-
dc.contributor.authorHinckeldeyn, Johannes-
dc.contributor.authorKreutzfeldt, Jochen-
dc.date.accessioned2022-09-19T13:16:36Z-
dc.date.available2022-09-19T13:16:36Z-
dc.date.issued2022-10-
dc.identifierdoi: 10.3390/robotics11050085-
dc.identifier.citationRobotics 11 (5): 85 (2022-10)de_DE
dc.identifier.issn2218-6581de_DE
dc.identifier.urihttp://hdl.handle.net/11420/13625-
dc.description.abstractControlling a fleet of autonomous mobile robots (AMR) is a complex problem of optimization. Many approached have been conducted for solving this problem. They range from heuristics, which usually do not find an optimum, to mathematical models, which are limited due to their high computational effort. Machine Learning (ML) methods offer another potential trajectory for solving such complex problems. The focus of this brief survey is on Reinforcement Learning (RL) as a particular type of ML. Due to the reward-based optimization, RL offers a good basis for the control of fleets of AMR. In the context of this survey, different control approaches are investigated and the aspects of fleet control of AMR with respect to RL are evaluated. As a result, six fundamental key problems should be put on the current research agenda to enable a broader application in industry: (1) overcoming the “sim-to-real gap”, (2) increasing the robustness of algorithms, (3) improving data efficiency, (4) integrating different fields of application, (5) enabling heterogeneous fleets with different types of AMR and (6) handling of deadlocks.-
dc.description.abstractControlling a fleet of autonomous mobile robots (AMR) is a complex problem of optimization. Many approached have been conducted for solving this problem. They range from heuristics, which usually do not find an optimum, to mathematical models, which are limited due to their high computational effort. Machine Learning (ML) methods offer another potential trajectory for solving such complex problems. The focus of this brief survey is on Reinforcement Learning (RL) as a particular type of ML. Due to the reward-based optimization, RL offers a good basis for the control of fleets of AMR. In the context of this survey, different control approaches are investigated and the aspects of fleet control of AMR with respect to RL are evaluated. As a result, six fundamental key problems should be put on the current research agenda to enable a broader application in industry: (1) overcoming the “sim-to-real gap”, (2) increasing the robustness of algorithms, (3) improving data efficiency, (4) integrating different fields of application, (5) enabling heterogeneous fleets with different types of AMR and (6) handling of deadlocks.en
dc.description.sponsorshipDeutsche Forschungsgemeinschaft (DFG)de_DE
dc.language.isoende_DE
dc.publisherMultidisciplinary Digital Publishing Institutede_DE
dc.relation.ispartofRobotics : open access journalde_DE
dc.rightsCC BY 4.0de_DE
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/de_DE
dc.subject.ddc004: Informatikde_DE
dc.subject.ddc600: Technikde_DE
dc.subject.ddc620: Ingenieurwissenschaftende_DE
dc.titleControlling fleets of autonomous mobile robots with reinforcement learning : a brief surveyde_DE
dc.typeArticlede_DE
dc.date.updated2022-09-08T13:23:53Z-
dc.identifier.doi10.15480/882.4594-
dc.type.diniarticle-
dcterms.DCMITypeText-
tuhh.identifier.urnurn:nbn:de:gbv:830-882.0196158-
tuhh.oai.showtruede_DE
tuhh.abstract.englishControlling a fleet of autonomous mobile robots (AMR) is a complex problem of optimization. Many approached have been conducted for solving this problem. They range from heuristics, which usually do not find an optimum, to mathematical models, which are limited due to their high computational effort. Machine Learning (ML) methods offer another potential trajectory for solving such complex problems. The focus of this brief survey is on Reinforcement Learning (RL) as a particular type of ML. Due to the reward-based optimization, RL offers a good basis for the control of fleets of AMR. In the context of this survey, different control approaches are investigated and the aspects of fleet control of AMR with respect to RL are evaluated. As a result, six fundamental key problems should be put on the current research agenda to enable a broader application in industry: (1) overcoming the “sim-to-real gap”, (2) increasing the robustness of algorithms, (3) improving data efficiency, (4) integrating different fields of application, (5) enabling heterogeneous fleets with different types of AMR and (6) handling of deadlocks.de_DE
tuhh.publisher.doi10.3390/robotics11050085-
tuhh.publication.instituteTechnische Logistik W-6de_DE
tuhh.identifier.doi10.15480/882.4594-
tuhh.type.opus(wissenschaftlicher) Artikel-
dc.type.driverarticle-
dc.type.casraiJournal Article-
tuhh.container.issue5de_DE
tuhh.container.volume11de_DE
dc.relation.projectOpen-Access-Publikationskosten / 2022-2024 / Technische Universität Hamburg (TUHH)de_DE
dc.rights.nationallicensefalsede_DE
dc.identifier.scopus2-s2.0-85140922725de_DE
tuhh.container.articlenumber85de_DE
local.status.inpressfalsede_DE
local.type.versionpublishedVersionde_DE
datacite.resourceTypeArticle-
datacite.resourceTypeGeneralJournalArticle-
item.grantfulltextopen-
item.cerifentitytypePublications-
item.openairetypeArticle-
item.creatorOrcidWesselhöft, Mike-
item.creatorOrcidHinckeldeyn, Johannes-
item.creatorOrcidKreutzfeldt, Jochen-
item.languageiso639-1en-
item.creatorGNDWesselhöft, Mike-
item.creatorGNDHinckeldeyn, Johannes-
item.creatorGNDKreutzfeldt, Jochen-
item.fulltextWith Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_6501-
item.mappedtypeArticle-
crisitem.project.funderDeutsche Forschungsgemeinschaft (DFG)-
crisitem.project.funderid501100001659-
crisitem.project.funderrorid018mejw64-
crisitem.author.deptTechnische Logistik W-6-
crisitem.author.deptTechnische Logistik W-6-
crisitem.author.deptTechnische Logistik W-6-
crisitem.author.orcid0000-0003-1797-6168-
crisitem.author.orcid0000-0001-9823-7679-
crisitem.author.orcid0000-0003-3648-576X-
crisitem.author.parentorgStudiendekanat Management-Wissenschaften und Technologie-
crisitem.author.parentorgStudiendekanat Management-Wissenschaften und Technologie-
crisitem.author.parentorgStudiendekanat Management-Wissenschaften und Technologie-
crisitem.funder.funderid501100001659-
crisitem.funder.funderrorid018mejw64-
Appears in Collections:Publications with fulltext
Files in This Item:
File Description SizeFormat
robotics-11-00085.pdf438,04 kBAdobe PDFView/Open
Thumbnail
Show simple item record

Page view(s)

63
checked on Dec 6, 2022

Download(s)

27
checked on Dec 6, 2022

Google ScholarTM

Check

Note about this record

Cite this record

Export

This item is licensed under a Creative Commons License Creative Commons