Publikation: An Innate Motivation to Tidy Your Room : Online Onboard Evolution of Manipulation Behaviors in a Robot Swarm
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
As our contribution to the effort of developing methods to make robots more adaptive and robust to dynamic environments, we have proposed our method of ‘minimal surprise’ in a series of previous works. In a multi-robot setting, we use evolutionary computation to evolve pairs of artificial neural networks: an actor network to select motor speeds and a predictor network to predict future sensor input. By rewarding for prediction accuracy, we give robots an innate, task-independent motivation to behave in structured and thus, predictable ways. While we previously focused on feasibility studies using abstract simulations, we now present our first results using realistic robot simulations and first experiments with real robot hardware. In a centralized online and onboard evolution approach, we show that minimize surprise works effectively on Thymio II robots in an area cleaning scenario.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
KAISER, Tanja Katharina, Christine LANG, Florian Andreas MARWITZ, Christian CHARLES, Sven DREIER, Julian PETZOLD, Max Ferdinand HANNAWALD, Marian Johannes BEGEMANN, Heiko HAMANN, 2022. An Innate Motivation to Tidy Your Room : Online Onboard Evolution of Manipulation Behaviors in a Robot Swarm. DARS 2021 : 15th International Symposium Distributed Autonomous Robotic Systems. Kyoto, Japan, 1. Juni 2021 - 4. Juni 2021. In: MATSUNO, Fumitoshi, ed., Shun-ichi AZUMA, ed., Masahito YAMAMOTO, ed.. Distributed Autonomous Robotic Systems : 15th International Symposium : Conference Proceedings. Cham: Springer, 2022, pp. 190-201. Springer Proceedings in Advanced Robotics. 22. ISSN 2511-1256. eISSN 2511-1264. ISBN 978-3-030-92789-9. Available under: doi: 10.1007/978-3-030-92790-5_15BibTex
@inproceedings{Kaiser2022Innat-59706, year={2022}, doi={10.1007/978-3-030-92790-5_15}, title={An Innate Motivation to Tidy Your Room : Online Onboard Evolution of Manipulation Behaviors in a Robot Swarm}, number={22}, isbn={978-3-030-92789-9}, issn={2511-1256}, publisher={Springer}, address={Cham}, series={Springer Proceedings in Advanced Robotics}, booktitle={Distributed Autonomous Robotic Systems : 15th International Symposium : Conference Proceedings}, pages={190--201}, editor={Matsuno, Fumitoshi and Azuma, Shun-ichi and Yamamoto, Masahito}, author={Kaiser, Tanja Katharina and Lang, Christine and Marwitz, Florian Andreas and Charles, Christian and Dreier, Sven and Petzold, Julian and Hannawald, Max Ferdinand and Begemann, Marian Johannes and Hamann, Heiko} }
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/123456789/59706"> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/59706"/> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-01-13T11:26:32Z</dc:date> <dc:creator>Hannawald, Max Ferdinand</dc:creator> <dc:contributor>Marwitz, Florian Andreas</dc:contributor> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dc:contributor>Hannawald, Max Ferdinand</dc:contributor> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-01-13T11:26:32Z</dcterms:available> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dc:contributor>Begemann, Marian Johannes</dc:contributor> <dc:creator>Petzold, Julian</dc:creator> <dc:contributor>Lang, Christine</dc:contributor> <dc:language>eng</dc:language> <dc:creator>Hamann, Heiko</dc:creator> <dcterms:issued>2022</dcterms:issued> <dcterms:title>An Innate Motivation to Tidy Your Room : Online Onboard Evolution of Manipulation Behaviors in a Robot Swarm</dcterms:title> <dc:contributor>Kaiser, Tanja Katharina</dc:contributor> <dc:creator>Kaiser, Tanja Katharina</dc:creator> <dc:creator>Marwitz, Florian Andreas</dc:creator> <dc:rights>terms-of-use</dc:rights> <dc:contributor>Petzold, Julian</dc:contributor> <dc:creator>Begemann, Marian Johannes</dc:creator> <dc:contributor>Hamann, Heiko</dc:contributor> <dc:contributor>Dreier, Sven</dc:contributor> <dc:contributor>Charles, Christian</dc:contributor> <dc:creator>Charles, Christian</dc:creator> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:creator>Lang, Christine</dc:creator> <dc:creator>Dreier, Sven</dc:creator> <dcterms:abstract xml:lang="eng">As our contribution to the effort of developing methods to make robots more adaptive and robust to dynamic environments, we have proposed our method of ‘minimal surprise’ in a series of previous works. In a multi-robot setting, we use evolutionary computation to evolve pairs of artificial neural networks: an actor network to select motor speeds and a predictor network to predict future sensor input. By rewarding for prediction accuracy, we give robots an innate, task-independent motivation to behave in structured and thus, predictable ways. While we previously focused on feasibility studies using abstract simulations, we now present our first results using realistic robot simulations and first experiments with real robot hardware. In a centralized online and onboard evolution approach, we show that minimize surprise works effectively on Thymio II robots in an area cleaning scenario.</dcterms:abstract> </rdf:Description> </rdf:RDF>