{"id":"https://openalex.org/W4408510357","doi":"https://doi.org/10.1109/jsyst.2025.3536783","title":"A Dual-Task Deep Reinforcement Learning and Domain Transfer Architecture for Bootstrapping Swarming Collective Motion Skills","display_name":"A Dual-Task Deep Reinforcement Learning and Domain Transfer Architecture for Bootstrapping Swarming Collective Motion Skills","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4408510357","doi":"https://doi.org/10.1109/jsyst.2025.3536783"},"language":"en","primary_location":{"id":"doi:10.1109/jsyst.2025.3536783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsyst.2025.3536783","pdf_url":null,"source":{"id":"https://openalex.org/S95999327","display_name":"IEEE Systems Journal","issn_l":"1932-8184","issn":["1932-8184","1937-9234","2373-7816"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Systems Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009535593","display_name":"Shadi Abpeikar","orcid":"https://orcid.org/0000-0002-8404-0290"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shadi Abpeikar","raw_affiliation_strings":["School of Engineering, Technology, University of New South Wales, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8404-0290","affiliations":[{"raw_affiliation_string":"School of Engineering, Technology, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064811459","display_name":"Matthew Garratt","orcid":"https://orcid.org/0000-0003-0222-430X"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Matt Garratt","raw_affiliation_strings":["School of Systems, Computing, University of New South Wales, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0222-430X","affiliations":[{"raw_affiliation_string":"School of Systems, Computing, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032529996","display_name":"Sreenatha G. Anavatti","orcid":"https://orcid.org/0000-0002-4754-8191"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sreenatha Anavatti","raw_affiliation_strings":["School of Engineering, Technology, University of New South Wales, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4754-8191","affiliations":[{"raw_affiliation_string":"School of Engineering, Technology, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021051563","display_name":"Reda Ghanem","orcid":"https://orcid.org/0000-0003-1663-8263"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Reda Ghanem","raw_affiliation_strings":["School of Systems, Computing, University of New South Wales, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1663-8263","affiliations":[{"raw_affiliation_string":"School of Systems, Computing, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047705901","display_name":"Kathryn Kasmarik","orcid":"https://orcid.org/0000-0001-7187-0474"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kathryn Kasmarik","raw_affiliation_strings":["School of Systems, Computing, University of New South Wales, Canberra, ACT, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Systems, Computing, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009535593"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":1.2027,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.763393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"19","issue":"1","first_page":"327","last_page":"338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.978600025177002,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.978600025177002,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9336000084877014,"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/swarming","display_name":"Swarming (honey bee)","score":0.7952538728713989},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7195526361465454},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6351507902145386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5672798156738281},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5247937440872192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4691528081893921},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.43712764978408813},{"id":"https://openalex.org/keywords/collective-motion","display_name":"Collective motion","score":0.42055219411849976},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39163222908973694},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09611284732818604}],"concepts":[{"id":"https://openalex.org/C164017216","wikidata":"https://www.wikidata.org/wiki/Q1549094","display_name":"Swarming (honey bee)","level":2,"score":0.7952538728713989},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7195526361465454},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6351507902145386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5672798156738281},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5247937440872192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4691528081893921},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.43712764978408813},{"id":"https://openalex.org/C2780499737","wikidata":"https://www.wikidata.org/wiki/Q24755076","display_name":"Collective motion","level":2,"score":0.42055219411849976},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39163222908973694},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09611284732818604},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jsyst.2025.3536783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsyst.2025.3536783","pdf_url":null,"source":{"id":"https://openalex.org/S95999327","display_name":"IEEE Systems Journal","issn_l":"1932-8184","issn":["1932-8184","1937-9234","2373-7816"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Systems Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2087370230","https://openalex.org/W2138165608","https://openalex.org/W2142838345","https://openalex.org/W2150312211","https://openalex.org/W2324853504","https://openalex.org/W2413992829","https://openalex.org/W2587734485","https://openalex.org/W2739678353","https://openalex.org/W2805394695","https://openalex.org/W2892046370","https://openalex.org/W2892091182","https://openalex.org/W2904062650","https://openalex.org/W2963207707","https://openalex.org/W2990602094","https://openalex.org/W2995705068","https://openalex.org/W2998978051","https://openalex.org/W3014630000","https://openalex.org/W3027990637","https://openalex.org/W3089254795","https://openalex.org/W3208824085","https://openalex.org/W4210672213","https://openalex.org/W4214717370","https://openalex.org/W4229007397","https://openalex.org/W4280598010","https://openalex.org/W4285734556","https://openalex.org/W4313063061","https://openalex.org/W4327616149","https://openalex.org/W4378194724","https://openalex.org/W4385819634","https://openalex.org/W4391406076","https://openalex.org/W4402269365","https://openalex.org/W6793853427","https://openalex.org/W6841313221","https://openalex.org/W6849098635","https://openalex.org/W7011416813"],"related_works":["https://openalex.org/W2361442589","https://openalex.org/W2129322309","https://openalex.org/W71677715","https://openalex.org/W237242145","https://openalex.org/W2389991495","https://openalex.org/W1956255817","https://openalex.org/W3208647225","https://openalex.org/W2184674118","https://openalex.org/W2244676710","https://openalex.org/W2512482127"],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2,27],"shown":[3],"it":[4],"is":[5,82,122,151],"possible":[6],"for":[7,84,90],"groups":[8],"of":[9,31,100,148,155],"robots":[10,140],"to":[11,70,76,153],"automatically":[12,73],"\u201cbootstrap\u201d":[13],"their":[14],"own":[15],"collective":[16,46,67,87,117,126],"motion":[17,47,68,88,127],"behaviors,":[18],"particularly":[19],"movement":[20,92],"in":[21,33,160],"a":[22,54,98,133,161],"group.":[23],"However,":[24],"existing":[25],"work":[26],"primarily":[28],"provided":[29],"proof":[30],"concept":[32],"regular,":[34],"open":[35],"arenas":[36],"without":[37,96,146],"obstacles.":[38],"For":[39],"practical":[40],"applications":[41],"on":[42],"real":[43,77,138],"robots,":[44],"multiple":[45,66],"skills":[48,69,89,128],"are":[49],"required.":[50],"This":[51],"article":[52],"proposes":[53],"novel,":[55],"multitask":[56],"deep":[57],"reinforcement":[58],"learning":[59],"algorithm":[60,158],"and":[61,74,93],"domain":[62,143],"transfer":[63,144],"architecture":[64],"permitting":[65],"be":[71,130],"bootstrapped":[72],"applied":[75],"robots.":[78],"The":[79],"proposed":[80],"approach":[81,107],"tested":[83],"tuning":[85],"two":[86],"grouped":[91],"obstacle":[94,110,121],"avoidance,":[95],"requiring":[97],"map":[99],"the":[101],"environment.":[102],"We":[103],"show":[104],"that":[105,154],"our":[106,142],"can":[108,129],"tune":[109],"avoidance":[111],"parameters":[112],"while":[113],"maintaining":[114],"high-quality":[115],"swarming":[116],"behavior":[118],"when":[119],"an":[120,156],"detected.":[123],"Furthermore,":[124],"learned":[125],"transferred":[131],"from":[132],"point":[134],"mass":[135],"simulation":[136],"onto":[137],"mobile":[139],"using":[141],"architecture,":[145],"loss":[147],"quality.":[149],"Transferability":[150],"comparable":[152],"evolutionary":[157],"run":[159],"high-fidelity":[162],"simulator.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
