{"id":"https://openalex.org/W3205608407","doi":"https://doi.org/10.1109/icra48506.2021.9562019","title":"Decentralized Circle Formation Control for Fish-like Robots in the Real-world via Reinforcement Learning","display_name":"Decentralized Circle Formation Control for Fish-like Robots in the Real-world via Reinforcement Learning","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3205608407","doi":"https://doi.org/10.1109/icra48506.2021.9562019","mag":"3205608407"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9562019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9562019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100669565","display_name":"Tianhao Zhang","orcid":"https://orcid.org/0000-0002-5939-3932"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4391767778","display_name":"State Key Laboratory of Turbulence and Complex Systems","ror":"https://ror.org/04km98768","country_code":null,"type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Zhang","raw_affiliation_strings":["Peking University,The State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,The State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering,Beijing,China,100871","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101753750","display_name":"Yueheng Li","orcid":"https://orcid.org/0000-0003-1327-3334"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4391767778","display_name":"State Key Laboratory of Turbulence and Complex Systems","ror":"https://ror.org/04km98768","country_code":null,"type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueheng Li","raw_affiliation_strings":["Peking University,The State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,The State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering,Beijing,China,100871","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424052","display_name":"Shuai Li","orcid":"https://orcid.org/0000-0001-5510-8180"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4391767778","display_name":"State Key Laboratory of Turbulence and Complex Systems","ror":"https://ror.org/04km98768","country_code":null,"type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Li","raw_affiliation_strings":["Peking University,The State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,The State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering,Beijing,China,100871","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089028438","display_name":"Qiwei Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiwei Ye","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China,100871","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001586420","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0002-4484-8885"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4391767778","display_name":"State Key Laboratory of Turbulence and Complex Systems","ror":"https://ror.org/04km98768","country_code":null,"type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["Peking University,The State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering,Beijing,China,100871","National Engineering Research Center of Software Engineering, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,The State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering,Beijing,China,100871","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]},{"raw_affiliation_string":"National Engineering Research Center of Software Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044920558","display_name":"Guangming Xie","orcid":"https://orcid.org/0000-0001-6504-0087"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4391767778","display_name":"State Key Laboratory of Turbulence and Complex Systems","ror":"https://ror.org/04km98768","country_code":null,"type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Xie","raw_affiliation_strings":["Peking University,The State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,The State Key Laboratory of Turbulence and Complex Systems, Intelligent Biomimetic Design Lab, College of Engineering,Beijing,China,100871","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0695,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95470172,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8814","last_page":"8820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9995999932289124,"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":0.9995999932289124,"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/T11486","display_name":"Micro and Nano Robotics","score":0.9948999881744385,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/robot","display_name":"Robot","score":0.7474251389503479},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7447123527526855},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.7064540982246399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6612129211425781},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5563503503799438},{"id":"https://openalex.org/keywords/decentralised-system","display_name":"Decentralised system","score":0.5034465193748474},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4981660842895508},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.452053040266037},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.43055790662765503},{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.41526907682418823},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3578140139579773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3510107696056366},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3346966803073883},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15790694952011108}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7474251389503479},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7447123527526855},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.7064540982246399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6612129211425781},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5563503503799438},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.5034465193748474},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4981660842895508},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.452053040266037},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.43055790662765503},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.41526907682418823},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3578140139579773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3510107696056366},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3346966803073883},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15790694952011108},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9562019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9562019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W327294579","https://openalex.org/W1981209947","https://openalex.org/W2070636161","https://openalex.org/W2081329272","https://openalex.org/W2173248099","https://openalex.org/W2489211088","https://openalex.org/W2495373952","https://openalex.org/W2548997266","https://openalex.org/W2568019971","https://openalex.org/W2624295978","https://openalex.org/W2747213132","https://openalex.org/W2782411383","https://openalex.org/W2799475528","https://openalex.org/W2807741983","https://openalex.org/W2921814844","https://openalex.org/W2946606218","https://openalex.org/W2949963774","https://openalex.org/W2963407617","https://openalex.org/W2963729305","https://openalex.org/W2963864421","https://openalex.org/W2980225219","https://openalex.org/W2981038142","https://openalex.org/W2997070234","https://openalex.org/W2999176108","https://openalex.org/W3037683188","https://openalex.org/W3041925030","https://openalex.org/W3046131678","https://openalex.org/W3093287223","https://openalex.org/W3094496700","https://openalex.org/W3150700316","https://openalex.org/W3156506101","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4388322344","https://openalex.org/W6684921986","https://openalex.org/W6729933147","https://openalex.org/W6738796088","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6762491519","https://openalex.org/W6794510017"],"related_works":["https://openalex.org/W587013945","https://openalex.org/W4288862394","https://openalex.org/W1485310626","https://openalex.org/W33907905","https://openalex.org/W4292915238","https://openalex.org/W4285553839","https://openalex.org/W3011477119","https://openalex.org/W2371440471","https://openalex.org/W2075135955","https://openalex.org/W2144839145"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,26,39,42,45,68,85,97,101,112,116],"circle":[4,123],"formation":[5,89,124],"control":[6,90],"problem":[7],"is":[8,59,92],"addressed":[9],"for":[10,122],"a":[11,35],"group":[12,98],"of":[13,41,44,100,118],"cooperative":[14],"underactuated":[15],"fish-like":[16,46],"robots":[17,76,102],"involving":[18],"unknown":[19],"nonlinear":[20],"dynamics":[21,43],"and":[22,29,67,103],"disturbances.":[23],"Based":[24],"on":[25],"reinforcement":[27],"learning":[28],"cognitive":[30],"consistency":[31],"theory,":[32],"we":[33],"propose":[34],"decentralized":[36],"controller":[37,50,70],"without":[38,77],"knowledge":[40],"robots.":[47],"The":[48],"proposed":[49,86],"can":[51,71],"be":[52,72],"transferred":[53],"from":[54],"simulation":[55,65],"to":[56,74,96],"reality.":[57],"It":[58],"only":[60],"trained":[61,69],"in":[62,111],"our":[63,119],"established":[64],"environment,":[66],"deployed":[73],"real":[75,113],"any":[78],"manual":[79],"tuning.":[80],"Simulation":[81],"results":[82],"confirm":[83],"that":[84],"model-free":[87],"robust":[88],"method":[91],"scalable":[93],"with":[94],"respect":[95],"size":[99],"outperforms":[104],"other":[105],"representative":[106],"RL":[107],"algorithms.":[108],"Several":[109],"experiments":[110],"world":[114],"verify":[115],"effectiveness":[117],"RL-based":[120],"approach":[121],"control.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}