{"id":"https://openalex.org/W4388017433","doi":"https://doi.org/10.1109/lra.2023.3328448","title":"Heterogeneous Multi-Robot Cooperation With Asynchronous Multi-Agent Reinforcement Learning","display_name":"Heterogeneous Multi-Robot Cooperation With Asynchronous Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-30","ids":{"openalex":"https://openalex.org/W4388017433","doi":"https://doi.org/10.1109/lra.2023.3328448"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3328448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3328448","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5069227036","display_name":"Han Zhang","orcid":"https://orcid.org/0000-0002-8591-7736"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Han Zhang","raw_affiliation_strings":["School of Power and Mechanical Engineering, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Power and Mechanical Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013649360","display_name":"Xiaohui Zhang","orcid":"https://orcid.org/0009-0008-2436-5350"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["School of Power and Mechanical Engineering, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Power and Mechanical Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060727044","display_name":"Zhao Feng","orcid":"https://orcid.org/0000-0001-7213-9413"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Feng","raw_affiliation_strings":["School of Power and Mechanical Engineering, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Power and Mechanical Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101658729","display_name":"Xiaohui Xiao","orcid":"https://orcid.org/0000-0002-8212-2452"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Xiao","raw_affiliation_strings":["School of Power and Mechanical Engineering, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Power and Mechanical Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069227036"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":3.3127,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.9375047,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":"1","first_page":"159","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9244999885559082,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8474045991897583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7980082035064697},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6812548041343689},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6604384779930115},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5639453530311584},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5202023386955261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31362277269363403},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.17443594336509705}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8474045991897583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980082035064697},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6812548041343689},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6604384779930115},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5639453530311584},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5202023386955261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31362277269363403},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.17443594336509705},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3328448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3328448","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1979071892","https://openalex.org/W2145339207","https://openalex.org/W2148831627","https://openalex.org/W2593237273","https://openalex.org/W2619089718","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2805031923","https://openalex.org/W2924816077","https://openalex.org/W2963762747","https://openalex.org/W2991046523","https://openalex.org/W3004640943","https://openalex.org/W3176420870","https://openalex.org/W3178293862","https://openalex.org/W3202938653","https://openalex.org/W3206518075","https://openalex.org/W4210879033","https://openalex.org/W4220817121","https://openalex.org/W4285506552","https://openalex.org/W6683300800","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6738796088","https://openalex.org/W6740092555","https://openalex.org/W6741002519","https://openalex.org/W6752380930","https://openalex.org/W6766805167","https://openalex.org/W6766956246","https://openalex.org/W6773620346","https://openalex.org/W6775788706","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2116677773","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Multi-robot":[0],"systems":[1],"(MRSs)":[2],"are":[3],"becoming":[4],"increasingly":[5],"important":[6],"in":[7,48,116,123,157,166],"various":[8],"domains.":[9],"However,":[10],"effective":[11,74],"communication":[12],"and":[13,32,65,73,84,99,130,142,161,168],"coordination":[14],"among":[15],"multiple":[16],"robots":[17,45,165],"remain":[18],"significant":[19],"challenges.":[20],"In":[21,137],"this":[22],"letter,":[23],"we":[24,94],"introduce":[25],"a":[26,101,131],"novel":[27],"architecture":[28,41,122,153],"for":[29,128],"multi-robot":[30,132,170],"decision-making":[31],"control":[33],"based":[34],"on":[35,62],"multi-agent":[36],"reinforcement":[37],"learning":[38],"(MARL).":[39],"Our":[40],"can":[42],"accommodate":[43],"heterogeneous":[44,169],"operating":[46],"asynchronously":[47],"different":[49],"scenarios.":[50,118],"We":[51,119],"propose":[52],"an":[53],"improved":[54],"practical":[55],"Q-value":[56],"mixing":[57],"network":[58],"(Qrainbow),":[59],"which":[60],"builds":[61],"value-decomposition":[63],"networks":[64],"applies":[66],"the":[67,90,105,109,125],"multi-head":[68],"attention":[69],"mixer":[70],"of":[71,107,139],"Qatten":[72],"components":[75],"from":[76],"Rainbow,":[77],"such":[78],"as":[79],"double":[80],"network,":[81,83],"dueling":[82],"prioritized":[85],"experience":[86],"replay.":[87],"To":[88],"migrate":[89],"algorithm":[91],"to":[92,104,114],"MRS,":[93],"fuse":[95],"macro-action":[96],"into":[97],"Qrainbow":[98,113,145],"make":[100],"slight":[102],"change":[103],"process":[106],"calculating":[108],"loss":[110],"function,":[111],"enabling":[112],"work":[115],"asynchronous":[117],"evaluate":[120],"our":[121,152],"both":[124],"benchmark":[126],"environment":[127,133],"MARL":[129,149],"with":[134],"varying":[135],"layouts.":[136],"terms":[138],"convergence":[140],"speed":[141],"final":[143],"result,":[144],"outperforms":[146],"other":[147],"state-of-the-art":[148],"algorithms.":[150],"Additionally,":[151],"achieves":[154],"superior":[155],"performance":[156],"reducing":[158],"time":[159],"costs":[160],"avoiding":[162],"collisions":[163],"between":[164],"homogeneous":[167],"cooperation":[171],"tasks.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}