{"id":"https://openalex.org/W2900325359","doi":"https://doi.org/10.1109/roman.2018.8525765","title":"Deep Reinforcement Learning for Formation Control","display_name":"Deep Reinforcement Learning for Formation Control","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2900325359","doi":"https://doi.org/10.1109/roman.2018.8525765","mag":"2900325359"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2018.8525765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2018.8525765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1468881","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066174382","display_name":"Can Aykin","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Can Aykin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084562346","display_name":"Martin Knopp","orcid":"https://orcid.org/0000-0002-1136-2950"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Knopp","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074346065","display_name":"Klaus Diepold","orcid":"https://orcid.org/0000-0003-0439-7511"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Diepold","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.786957323551178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7478910088539124},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7310135364532471},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6962466239929199},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6852124929428101},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5641219019889832},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.533883273601532},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.497348815202713},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46640291810035706},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.44421204924583435},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4357948303222656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786957323551178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7478910088539124},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7310135364532471},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6962466239929199},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6852124929428101},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5641219019889832},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.533883273601532},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.497348815202713},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46640291810035706},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.44421204924583435},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4357948303222656},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/roman.2018.8525765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2018.8525765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1468881","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1468881","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1468881","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1468881","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1994714538","https://openalex.org/W2066165078","https://openalex.org/W2082511574","https://openalex.org/W2121863487","https://openalex.org/W2143612262","https://openalex.org/W2144354855","https://openalex.org/W2145339207","https://openalex.org/W2147768505","https://openalex.org/W2163605009","https://openalex.org/W2170942820","https://openalex.org/W2173248099","https://openalex.org/W2240585996","https://openalex.org/W2774092941","https://openalex.org/W2963864421","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6684191040","https://openalex.org/W6684921986","https://openalex.org/W6689856497"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Continuing":[0],"our":[1],"work":[2,64],"on":[3,60],"using":[4],"reinforcement":[5],"learning":[6,15],"for":[7,56,72,94],"formation":[8],"control,":[9],"we":[10],"present":[11],"an":[12],"end-to-end":[13],"deep":[14],"system":[16],"which":[17],"uses":[18],"only":[19],"camera":[20,75,90],"images":[21,76],"to":[22,24,67],"learn":[23],"control":[25],"the":[26,32,43,74,79,83,103,106],"individual":[27],"system's":[28],"correct":[29],"position":[30],"within":[31],"formation.":[33],"Mnih":[34],"et":[35],"al.":[36],"created":[37],"AIs":[38],"playing":[39],"video":[40],"games":[41],"utilizing":[42],"same":[44,84],"visual":[45],"input":[46],"as":[47],"a":[48,69],"human":[49],"player":[50],"by":[51],"employing":[52],"convolutional":[53],"neural":[54],"networks":[55],"automatic":[57],"feature":[58],"extraction":[59],"images.":[61],"This":[62],"published":[63],"inspired":[65],"us":[66],"employ":[68],"similar":[70,99],"approach":[71],"processing":[73],"and":[77,100],"controlling":[78],"robot.":[80],"We":[81],"repeat":[82],"experiment":[85],"with":[86],"two":[87],"completely":[88],"different":[89],"positions.":[91],"The":[92],"results":[93],"both":[95],"positions":[96],"are":[97],"very":[98],"such":[101],"demonstrate":[102],"flexibility":[104],"of":[105],"presented":[107],"approach.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}