{"id":"https://openalex.org/W3138949668","doi":"https://doi.org/10.1109/icara51699.2021.9376509","title":"Self-Organised Swarm Flocking with Deep Reinforcement Learning","display_name":"Self-Organised Swarm Flocking with Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-02-04","ids":{"openalex":"https://openalex.org/W3138949668","doi":"https://doi.org/10.1109/icara51699.2021.9376509","mag":"3138949668"},"language":"en","primary_location":{"id":"doi:10.1109/icara51699.2021.9376509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icara51699.2021.9376509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 7th International Conference on Automation, Robotics and Applications (ICARA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.manchester.ac.uk/en/publications/d411694d-4771-436f-977e-6295986a9cb4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058842003","display_name":"Mehmet B. Bezcioglu","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mehmet B. Bezcioglu","raw_affiliation_strings":["Swarm & Computational Intelligence Lab (SwaCIL), The University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swarm & Computational Intelligence Lab (SwaCIL), The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011590665","display_name":"Barry Lennox","orcid":"https://orcid.org/0000-0003-0905-8324"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Barry Lennox","raw_affiliation_strings":["Swarm & Computational Intelligence Lab (SwaCIL), The University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swarm & Computational Intelligence Lab (SwaCIL), The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005614248","display_name":"Farshad Arvin","orcid":"https://orcid.org/0000-0001-7950-3193"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Farshad Arvin","raw_affiliation_strings":["Swarm & Computational Intelligence Lab (SwaCIL), The University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swarm & Computational Intelligence Lab (SwaCIL), The University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058842003"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":1.7622,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85067921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11486","display_name":"Micro and Nano Robotics","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3104","display_name":"Condensed Matter Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/flocking","display_name":"Flocking (texture)","score":0.8655073046684265},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.8547950387001038},{"id":"https://openalex.org/keywords/swarm-robotics","display_name":"Swarm robotics","score":0.7236301898956299},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6234039664268494},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.560218095779419},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.540598452091217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5222876071929932},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.46427175402641296},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4561764895915985},{"id":"https://openalex.org/keywords/collective-behavior","display_name":"Collective behavior","score":0.4297649562358856},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3239429295063019},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1989244520664215},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13588044047355652}],"concepts":[{"id":"https://openalex.org/C2781220375","wikidata":"https://www.wikidata.org/wiki/Q814208","display_name":"Flocking (texture)","level":2,"score":0.8655073046684265},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.8547950387001038},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.7236301898956299},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6234039664268494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.560218095779419},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.540598452091217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5222876071929932},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.46427175402641296},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4561764895915985},{"id":"https://openalex.org/C100339178","wikidata":"https://www.wikidata.org/wiki/Q2548752","display_name":"Collective behavior","level":2,"score":0.4297649562358856},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3239429295063019},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1989244520664215},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13588044047355652},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icara51699.2021.9376509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icara51699.2021.9376509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 7th International Conference on Automation, Robotics and Applications (ICARA)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/d411694d-4771-436f-977e-6295986a9cb4","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/d411694d-4771-436f-977e-6295986a9cb4","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bezcioglu, M, Lennox, B & Arvin, F 2021, Self-Organised Swarm Flocking with Deep Reinforcement Learning. in 2021 International Conference on Automation, Robotics and Applications, ICARA 2021., 9376509, 2021 International Conference on Automation, Robotics and Applications, ICARA 2021, pp. 226-230. https://doi.org/10.1109/ICARA51699.2021.9376509","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/d411694d-4771-436f-977e-6295986a9cb4","is_oa":false,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/selforganised-swarm-flocking-with-deep-reinforcement-learning(d411694d-4771-436f-977e-6295986a9cb4).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/d411694d-4771-436f-977e-6295986a9cb4","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/d411694d-4771-436f-977e-6295986a9cb4","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bezcioglu, M, Lennox, B & Arvin, F 2021, Self-Organised Swarm Flocking with Deep Reinforcement Learning. in 2021 International Conference on Automation, Robotics and Applications, ICARA 2021., 9376509, 2021 International Conference on Automation, Robotics and Applications, ICARA 2021, pp. 226-230. https://doi.org/10.1109/ICARA51699.2021.9376509","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2518717205","display_name":null,"funder_award_id":"EP/P01366X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1544602888","https://openalex.org/W1757796397","https://openalex.org/W2015410655","https://openalex.org/W2060203271","https://openalex.org/W2127683394","https://openalex.org/W2150312211","https://openalex.org/W2165150801","https://openalex.org/W2170169747","https://openalex.org/W2173248099","https://openalex.org/W2176056341","https://openalex.org/W2301345977","https://openalex.org/W2567990716","https://openalex.org/W2582001680","https://openalex.org/W2588790649","https://openalex.org/W2769883686","https://openalex.org/W2883532348","https://openalex.org/W2926233066","https://openalex.org/W2962832483","https://openalex.org/W2963864421","https://openalex.org/W2989598077","https://openalex.org/W2997995952","https://openalex.org/W3002855444","https://openalex.org/W3049672534","https://openalex.org/W3095315965","https://openalex.org/W3209101326","https://openalex.org/W4295252942","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6632641823"],"related_works":["https://openalex.org/W2002188687","https://openalex.org/W2142589698","https://openalex.org/W2794811781","https://openalex.org/W4327740834","https://openalex.org/W4387113913","https://openalex.org/W1596835606","https://openalex.org/W2138105113","https://openalex.org/W1871202614","https://openalex.org/W2124814448","https://openalex.org/W4304182880"],"abstract_inverted_index":{"Optimising":[0],"a":[1,9,24,29,50,61,112,119,154],"set":[2],"of":[3,16,31,88,95,108,145,148],"parameters":[4],"for":[5,92],"swarm":[6,30,44,93,150],"flocking":[7,26,48],"is":[8,66,125,153],"tedious":[10],"task":[11],"as":[12],"it":[13],"requires":[14],"hand-tuning":[15],"the":[17,43,47,81,89,106,140,146,149],"parameters.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22,117,133],"developed":[23],"self-organised":[25],"mechanism":[27,36],"with":[28],"homogeneous":[32],"robots.":[33,103],"The":[34],"proposed":[35],"used":[37],"deep":[38],"reinforcement":[39,109],"learning":[40,110],"to":[41,45,142],"teach":[42],"perform":[46],"in":[49,75,111],"continuous":[51],"state":[52,121],"and":[53,84,129],"action":[54],"space.":[55],"Collective":[56],"motion":[57],"was":[58],"represented":[59],"by":[60,127],"self-organising":[62],"dynamic":[63,90],"model":[64,91],"that":[65,124,135],"based":[67],"on":[68],"linear":[69],"spring-like":[70],"forces":[71],"between":[72],"self-propelled":[73],"particles":[74],"an":[76],"active":[77],"crystal.":[78],"We":[79,104],"tuned":[80],"inverse":[82],"rotational":[83],"translational":[85],"damping":[86],"coefficients":[87],"populations":[94],"N":[96],"\u2208":[97],"{25,":[98,101],"100}":[99,102],"E":[100],"study":[105],"application":[107],"centralised":[113],"multi-agent":[114],"approach,":[115],"where":[116],"have":[118],"global":[120],"space":[122],"matrix":[123],"accessible":[126],"actor":[128],"critic":[130],"networks.":[131],"Furthermore,":[132],"showed":[134],"our":[136],"method":[137],"could":[138],"train":[139],"system":[141],"flock":[143],"regardless":[144],"sparsity":[147],"population,":[151],"which":[152],"significant":[155],"result.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}