{"id":"https://openalex.org/W3056510116","doi":"https://doi.org/10.1109/access.2020.3016951","title":"Multi-Robot Flocking Control Based on Deep Reinforcement Learning","display_name":"Multi-Robot Flocking Control Based on Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3056510116","doi":"https://doi.org/10.1109/access.2020.3016951","mag":"3056510116"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3016951","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3016951","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09169650.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09169650.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051281038","display_name":"Pengming Zhu","orcid":"https://orcid.org/0000-0002-2440-5331"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengming Zhu","raw_affiliation_strings":["Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2440-5331","affiliations":[{"raw_affiliation_string":"Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671164","display_name":"Wei Dai","orcid":"https://orcid.org/0000-0002-7571-4863"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Dai","raw_affiliation_strings":["Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041756875","display_name":"Weijia Yao","orcid":"https://orcid.org/0000-0003-0361-6620"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijia Yao","raw_affiliation_strings":["Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-0361-6620","affiliations":[{"raw_affiliation_string":"Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004141995","display_name":"Junchong Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junchong Ma","raw_affiliation_strings":["Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004379460","display_name":"Zhiwen Zeng","orcid":"https://orcid.org/0000-0002-8566-6965"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Zeng","raw_affiliation_strings":["Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036075088","display_name":"Huimin Lu","orcid":"https://orcid.org/0000-0002-6375-581X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Lu","raw_affiliation_strings":["Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6375-581X","affiliations":[{"raw_affiliation_string":"Robotics Research Center, College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":6.0935,"has_fulltext":true,"cited_by_count":77,"citation_normalized_percentile":{"value":0.97043483,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"150397","last_page":"150406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9990000128746033,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9939000010490417,"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/flocking","display_name":"Flocking (texture)","score":0.9239081144332886},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8342863321304321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7926660776138306},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7219452261924744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48361149430274963},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4481564462184906},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4441908597946167},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.42690759897232056}],"concepts":[{"id":"https://openalex.org/C2781220375","wikidata":"https://www.wikidata.org/wiki/Q814208","display_name":"Flocking (texture)","level":2,"score":0.9239081144332886},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8342863321304321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926660776138306},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7219452261924744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48361149430274963},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4481564462184906},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4441908597946167},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.42690759897232056},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3016951","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3016951","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09169650.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:17bec4a3249d473284b09a407ffc4828","is_oa":true,"landing_page_url":"https://doaj.org/article/17bec4a3249d473284b09a407ffc4828","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 150397-150406 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3016951","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3016951","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09169650.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2544253145","display_name":null,"funder_award_id":"U1913202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6035072949","display_name":null,"funder_award_id":"CX2018B010","funder_id":"https://openalex.org/F4320326217","funder_display_name":"Hunan Provincial Innovation Foundation for Postgraduate"},{"id":"https://openalex.org/G8615171270","display_name":null,"funder_award_id":"U1813205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326217","display_name":"Hunan Provincial Innovation Foundation for Postgraduate","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3056510116.pdf","grobid_xml":"https://content.openalex.org/works/W3056510116.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W615006660","https://openalex.org/W1969839206","https://openalex.org/W2015410655","https://openalex.org/W2048074430","https://openalex.org/W2074491591","https://openalex.org/W2074803050","https://openalex.org/W2119693819","https://openalex.org/W2145339207","https://openalex.org/W2150312211","https://openalex.org/W2155968351","https://openalex.org/W2201581102","https://openalex.org/W2248010213","https://openalex.org/W2345097924","https://openalex.org/W2395575420","https://openalex.org/W2403130913","https://openalex.org/W2411650265","https://openalex.org/W2617547828","https://openalex.org/W2734878594","https://openalex.org/W2736026938","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2766980381","https://openalex.org/W2806824292","https://openalex.org/W2887881780","https://openalex.org/W2953334758","https://openalex.org/W2963762747","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964338167","https://openalex.org/W2976344064","https://openalex.org/W2981946308","https://openalex.org/W2984557458","https://openalex.org/W3036305875","https://openalex.org/W4299802797","https://openalex.org/W6683001934","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6741408367","https://openalex.org/W6766805167"],"related_works":["https://openalex.org/W2008369823","https://openalex.org/W2102861135","https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W4384574988","https://openalex.org/W2130711276"],"abstract_inverted_index":{"In":[0,138],"this":[1,97],"paper,":[2],"we":[3,30],"apply":[4],"deep":[5,53],"reinforcement":[6],"learning":[7,69,87],"(DRL)":[8],"to":[9,71,127,162],"solve":[10],"the":[11,26,41,51,62,68,74,82,94,108,116,135,139,141,145,148,159,164,168],"flocking":[12,28,38,165],"control":[13,47],"problem":[14],"of":[15,44,64,93,147],"multi-robot":[16,37],"systems":[17],"in":[18,67,167],"complex":[19],"environments":[20],"with":[21,170],"dynamic":[22],"obstacles.":[23,171],"Starting":[24],"from":[25,134],"traditional":[27],"model,":[29],"propose":[31],"a":[32,100,121,153],"DRL":[33],"framework":[34],"for":[35],"implementing":[36],"control,":[39],"eliminating":[40],"tedious":[42],"work":[43],"modeling":[45],"and":[46,89,106,157],"designing.":[48],"We":[49],"adopt":[50],"multi-agent":[52],"deterministic":[54],"policy":[55],"gradient":[56],"(MADDPG)":[57],"algorithm,":[58,96],"which":[59,129],"additionally":[60],"uses":[61],"information":[63],"multiple":[65],"robots":[66,77],"process":[70],"better":[72],"predict":[73],"actions":[75],"that":[76],"will":[78],"take.":[79],"To":[80],"address":[81],"problems":[83],"such":[84],"as":[85],"low":[86],"efficiency":[88],"slow":[90],"convergence":[91,155],"speed":[92,156],"MADDPG":[95],"paper":[98],"studies":[99],"prioritized":[101],"experience":[102],"replay":[103,136],"(PER)":[104],"mechanism":[105],"proposes":[107],"Prioritized":[109],"Experience":[110],"Replay-MADDPG":[111],"(PER-MADDPG)":[112],"algorithm.":[113,150],"Based":[114],"on":[115],"temporal":[117],"difference":[118],"(TD)":[119],"error,":[120],"priority":[122],"evaluation":[123],"function":[124],"is":[125],"designed":[126],"determine":[128],"experiences":[130],"are":[131],"sampled":[132],"preferentially":[133],"buffer.":[137],"end,":[140],"simulation":[142],"results":[143],"verify":[144],"effectiveness":[146],"proposed":[149],"It":[151],"has":[152],"faster":[154],"enables":[158],"robot":[160],"group":[161],"complete":[163],"task":[166],"environment":[169]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}