Publikation: Show me What you want : Inverse Reinforcement Learning to Automatically Design Robot Swarms by Demonstration
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
Automatic design is a promising approach to generating control software for robot swarms. So far, automatic design has relied on mission-specific objective functions to specify the desired collective behavior. In this paper, we explore the possibility to specify the desired collective behavior via demonstrations. We develop Demo-Cho, an automatic design method that combines inverse reinforcement learning with automatic modular design of control software for robot swarms. We show that, only on the basis of demonstrations and without the need to be provided with an explicit objective function, Demo-Cho successfully generated control software to perform four missions. We present results obtained in simulation and with physical robots.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
GHARBI, Ilyes, Jonas KUCKLING, David GARZÓN RAMOS, Mauro BIRATTARI, 2023. Show me What you want : Inverse Reinforcement Learning to Automatically Design Robot Swarms by Demonstration. ICRA 2023 : IEEE International Conference on Robotics and Automation. London, UK, 29. Mai 2023 - 2. Juni 2023. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), Conference Proceedings. Piscataway, NJ: IEEE, 2023, pp. 5063-5070. ISBN 979-8-3503-2365-8. Available under: doi: 10.1109/icra48891.2023.10160947BibTex
@inproceedings{Gharbi2023Inver-69655, year={2023}, doi={10.1109/icra48891.2023.10160947}, title={Show me What you want : Inverse Reinforcement Learning to Automatically Design Robot Swarms by Demonstration}, isbn={979-8-3503-2365-8}, publisher={IEEE}, address={Piscataway, NJ}, booktitle={2023 IEEE International Conference on Robotics and Automation (ICRA), Conference Proceedings}, pages={5063--5070}, author={Gharbi, Ilyes and Kuckling, Jonas and Garzón Ramos, David and Birattari, Mauro} }
RDF
<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/69655"> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:creator>Birattari, Mauro</dc:creator> <dc:creator>Kuckling, Jonas</dc:creator> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dc:contributor>Garzón Ramos, David</dc:contributor> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:creator>Garzón Ramos, David</dc:creator> <dcterms:abstract>Automatic design is a promising approach to generating control software for robot swarms. So far, automatic design has relied on mission-specific objective functions to specify the desired collective behavior. In this paper, we explore the possibility to specify the desired collective behavior via demonstrations. We develop Demo-Cho, an automatic design method that combines inverse reinforcement learning with automatic modular design of control software for robot swarms. We show that, only on the basis of demonstrations and without the need to be provided with an explicit objective function, Demo-Cho successfully generated control software to perform four missions. We present results obtained in simulation and with physical robots.</dcterms:abstract> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dc:contributor>Birattari, Mauro</dc:contributor> <dcterms:title>Show me What you want : Inverse Reinforcement Learning to Automatically Design Robot Swarms by Demonstration</dcterms:title> <dc:creator>Gharbi, Ilyes</dc:creator> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-03-20T12:23:10Z</dc:date> <dc:contributor>Gharbi, Ilyes</dc:contributor> <dc:language>eng</dc:language> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/69655"/> <dcterms:issued>2023</dcterms:issued> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-03-20T12:23:10Z</dcterms:available> <dc:contributor>Kuckling, Jonas</dc:contributor> </rdf:Description> </rdf:RDF>