{"id":"https://openalex.org/W4365421101","doi":"https://doi.org/10.1109/tro.2023.3257541","title":"Asymmetric Self-Play-Enabled Intelligent Heterogeneous Multirobot Catching System Using Deep Multiagent Reinforcement Learning","display_name":"Asymmetric Self-Play-Enabled Intelligent Heterogeneous Multirobot Catching System Using Deep Multiagent Reinforcement Learning","publication_year":2023,"publication_date":"2023-04-12","ids":{"openalex":"https://openalex.org/W4365421101","doi":"https://doi.org/10.1109/tro.2023.3257541"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2023.3257541","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2023.3257541","pdf_url":"https://ieeexplore.ieee.org/ielx7/8860/4359257/10101687.pdf","source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/8860/4359257/10101687.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073421475","display_name":"Yuan Gao","orcid":"https://orcid.org/0009-0004-1987-1639"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Gao","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426704","display_name":"Junfeng Chen","orcid":"https://orcid.org/0000-0003-0617-5031"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Chen","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654576","display_name":"Xi Chen","orcid":"https://orcid.org/0009-0008-3234-6408"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700778","display_name":"Chongyang Wang","orcid":"https://orcid.org/0000-0002-9819-088X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chongyang Wang","raw_affiliation_strings":["University College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"University College London, London, U.K","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085263462","display_name":"Junjie Hu","orcid":"https://orcid.org/0000-0002-1911-4361"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Hu","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082314454","display_name":"Fuqin Deng","orcid":"https://orcid.org/0000-0002-7071-7184"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I4210151615","display_name":"Wuyi University","ror":"https://ror.org/0488wz367","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210151615"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuqin Deng","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China","School of Intelligent Manufacturing, Wuyi University, Jiangmen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Intelligent Manufacturing, Wuyi University, Jiangmen, China","institution_ids":["https://openalex.org/I4210151615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076185690","display_name":"Tin Lun Lam","orcid":"https://orcid.org/0000-0002-6363-1446"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tin Lun Lam","raw_affiliation_strings":["Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China","School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5073421475"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":5.9148,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.96989448,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"39","issue":"4","first_page":"2603","last_page":"2622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9958000183105469,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7316017746925354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7044824957847595},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6529092788696289},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6187835931777954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5580852031707764},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47934895753860474},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4427449703216553},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4182049036026001},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33351361751556396},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2055688202381134},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.19509539008140564}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7316017746925354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044824957847595},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6529092788696289},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6187835931777954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580852031707764},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47934895753860474},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4427449703216553},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4182049036026001},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33351361751556396},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2055688202381134},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.19509539008140564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tro.2023.3257541","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2023.3257541","pdf_url":"https://ieeexplore.ieee.org/ielx7/8860/4359257/10101687.pdf","source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tro.2023.3257541","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2023.3257541","pdf_url":"https://ieeexplore.ieee.org/ielx7/8860/4359257/10101687.pdf","source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2951312632","display_name":null,"funder_award_id":"2022A1515110787","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G3303920830","display_name":null,"funder_award_id":"2022M721838","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G4579490052","display_name":null,"funder_award_id":"2022A151511","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6536786679","display_name":null,"funder_award_id":"A1515110","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4365421101.pdf","grobid_xml":"https://content.openalex.org/works/W4365421101.grobid-xml"},"referenced_works_count":95,"referenced_works":["https://openalex.org/W1527571715","https://openalex.org/W1989407213","https://openalex.org/W1996542214","https://openalex.org/W2057861900","https://openalex.org/W2078895652","https://openalex.org/W2095905067","https://openalex.org/W2111020647","https://openalex.org/W2151834591","https://openalex.org/W2161608691","https://openalex.org/W2163922914","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2346245116","https://openalex.org/W2411491336","https://openalex.org/W2412503523","https://openalex.org/W2439962905","https://openalex.org/W2464436066","https://openalex.org/W2514576092","https://openalex.org/W2558431499","https://openalex.org/W2575523922","https://openalex.org/W2603088459","https://openalex.org/W2605102758","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2760243623","https://openalex.org/W2766447205","https://openalex.org/W2791697444","https://openalex.org/W2797121477","https://openalex.org/W2803770871","https://openalex.org/W2807778117","https://openalex.org/W2889987506","https://openalex.org/W2891663723","https://openalex.org/W2891816981","https://openalex.org/W2895492692","https://openalex.org/W2897884082","https://openalex.org/W2903998385","https://openalex.org/W2909076853","https://openalex.org/W2909746114","https://openalex.org/W2912971983","https://openalex.org/W2919115771","https://openalex.org/W2924078280","https://openalex.org/W2936516903","https://openalex.org/W2947979298","https://openalex.org/W2948937890","https://openalex.org/W2953672042","https://openalex.org/W2963634205","https://openalex.org/W2963780790","https://openalex.org/W2963821308","https://openalex.org/W2964313027","https://openalex.org/W2965230525","https://openalex.org/W2967053680","https://openalex.org/W2968213087","https://openalex.org/W2972699522","https://openalex.org/W2977093897","https://openalex.org/W2981946308","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2999446437","https://openalex.org/W3001988640","https://openalex.org/W3007547569","https://openalex.org/W3008404222","https://openalex.org/W3018311626","https://openalex.org/W3028498088","https://openalex.org/W3040904863","https://openalex.org/W3045974612","https://openalex.org/W3046288222","https://openalex.org/W3089590059","https://openalex.org/W3100296869","https://openalex.org/W3103532359","https://openalex.org/W3110457222","https://openalex.org/W3112239567","https://openalex.org/W3120327542","https://openalex.org/W3123681199","https://openalex.org/W3147173284","https://openalex.org/W3154202793","https://openalex.org/W3174967682","https://openalex.org/W4210868137","https://openalex.org/W4211017739","https://openalex.org/W4287674167","https://openalex.org/W4295598622","https://openalex.org/W4309432140","https://openalex.org/W4385245566","https://openalex.org/W6735789912","https://openalex.org/W6739901393","https://openalex.org/W6749304979","https://openalex.org/W6753526802","https://openalex.org/W6754964036","https://openalex.org/W6763056091","https://openalex.org/W6772005887","https://openalex.org/W6773355059","https://openalex.org/W6774026654","https://openalex.org/W6781750019","https://openalex.org/W6782566759","https://openalex.org/W6788682413","https://openalex.org/W6803876132"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W2110944602","https://openalex.org/W3213722473"],"abstract_inverted_index":{"Aiming":[0],"to":[1,33,72,94,106,123,165],"develop":[2],"a":[3,59,118,128,146,184],"more":[4],"robust":[5],"and":[6,15,29,39,87,103,137,158,178],"intelligent":[7,189],"heterogeneous":[8,46,67,134],"system":[9],"for":[10,78,186],"adversarial":[11,143],"catching":[12,80,114,135,170],"in":[13,18,44,111,133,142,175],"security":[14,190],"rescue":[16,192],"tasks,":[17],"this":[19],"article,":[20],"we":[21,148],"discuss":[22],"the":[23,36,73,151,168,179],"specialities":[24],"of":[25,41,75],"applying":[26],"asymmetric":[27,156],"self-play":[28,157],"curriculum":[30,159],"learning":[31,160],"techniques":[32],"deal":[34],"with":[35,127],"increasing":[37],"heterogeneity":[38],"number":[40],"different":[42,96],"robots":[43],"modern":[45],"multirobot":[47,68],"systems":[48],"(HMRS).":[49],"Our":[50],"method,":[51],"based":[52],"on":[53,99],"actor-critic":[54],"multiagent":[55],"reinforcement":[56],"learning,":[57],"provides":[58],"framework":[60],"that":[61,82,150],"can":[62],"enable":[63],"cooperative":[64],"behaviors":[65],"among":[66],"teams.":[69],"This":[70],"leads":[71],"development":[74],"an":[76],"HMRS":[77,169],"complex":[79,112],"scenarios":[81],"involve":[83],"several":[84],"robot":[85],"teams":[86],"real-world":[88,104,113],"constraints.":[89],"We":[90],"conduct":[91],"simulated":[92],"experiments":[93,105],"evaluate":[95],"mechanisms'":[97],"influence":[98],"our":[100,108,125,138],"method's":[101],"performance,":[102],"assess":[107],"system's":[109],"performance":[110],"problems.":[115],"In":[116],"addition,":[117],"bridging":[119],"study":[120],"is":[121,163],"conducted":[122],"compare":[124],"method":[126,130,139],"state-of-the-art":[129],"called":[131],"S2M2":[132],"problems,":[136],"performs":[140],"better":[141],"settings.":[144],"As":[145],"result,":[147],"show":[149],"proposed":[152],"framework,":[153],"through":[154],"fusing":[155],"during":[161],"training,":[162],"able":[164],"successfully":[166],"complete":[167],"task":[171],"under":[172],"realistic":[173],"constraints":[174],"both":[176],"simulation":[177],"real":[180],"world,":[181],"thus":[182],"providing":[183],"direction":[185],"future":[187],"large-scale":[188],"&":[191],"HMRS.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}