{"id":"https://openalex.org/W3031798691","doi":"https://doi.org/10.1177/0278364920916531","title":"Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios","display_name":"Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios","publication_year":2020,"publication_date":"2020-05-31","ids":{"openalex":"https://openalex.org/W3031798691","doi":"https://doi.org/10.1177/0278364920916531","mag":"3031798691"},"language":"en","primary_location":{"id":"doi:10.1177/0278364920916531","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364920916531","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","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/A5054924375","display_name":"Tingxiang Fan","orcid":"https://orcid.org/0009-0005-6314-2596"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tingxiang Fan","raw_affiliation_strings":["Department of Computer Science, University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016889301","display_name":"Pinxin Long","orcid":"https://orcid.org/0000-0001-8440-3218"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pinxin Long","raw_affiliation_strings":["Baidu Research, Baidu, Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Baidu, Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045303340","display_name":"Wenxi Liu","orcid":"https://orcid.org/0000-0002-3630-6322"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxi Liu","raw_affiliation_strings":["College of Mathematics and Computer Science, Fuzhou University, China"],"affiliations":[{"raw_affiliation_string":"College of Mathematics and Computer Science, Fuzhou University, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076812698","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0001-9003-2054"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Jia Pan","raw_affiliation_strings":["Department of Computer Science, University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076812698"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":23.1063,"has_fulltext":false,"cited_by_count":319,"citation_normalized_percentile":{"value":0.99618937,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"39","issue":"7","first_page":"856","last_page":"892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9965000152587891,"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":0.8494628667831421},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7739184498786926},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.751071572303772},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6702232360839844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6046784520149231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5064817667007446},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.48921918869018555},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.450111985206604},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4010038375854492},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10203614830970764}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8494628667831421},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7739184498786926},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.751071572303772},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6702232360839844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6046784520149231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5064817667007446},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.48921918869018555},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.450111985206604},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4010038375854492},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10203614830970764},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0278364920916531","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364920916531","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1014609275","display_name":null,"funder_award_id":"11202119","funder_id":"https://openalex.org/F4320335882","funder_display_name":"General Research Fund of Shanghai Normal University"},{"id":"https://openalex.org/G1723910461","display_name":null,"funder_award_id":"11207818","funder_id":"https://openalex.org/F4320335882","funder_display_name":"General Research Fund of Shanghai Normal University"}],"funders":[{"id":"https://openalex.org/F4320335882","display_name":"General Research Fund of Shanghai Normal University","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W178419168","https://openalex.org/W192919555","https://openalex.org/W774034202","https://openalex.org/W1595533192","https://openalex.org/W1731081199","https://openalex.org/W1923344279","https://openalex.org/W1964462572","https://openalex.org/W1965760189","https://openalex.org/W1976517551","https://openalex.org/W1980969546","https://openalex.org/W1989407213","https://openalex.org/W1994511055","https://openalex.org/W1995408953","https://openalex.org/W2005389191","https://openalex.org/W2008518509","https://openalex.org/W2012252652","https://openalex.org/W2022020194","https://openalex.org/W2041600899","https://openalex.org/W2043718304","https://openalex.org/W2057555599","https://openalex.org/W2071356645","https://openalex.org/W2072337003","https://openalex.org/W2072956256","https://openalex.org/W2096263982","https://openalex.org/W2097482220","https://openalex.org/W2097639646","https://openalex.org/W2105932936","https://openalex.org/W2107280071","https://openalex.org/W2116113712","https://openalex.org/W2117211893","https://openalex.org/W2119120935","https://openalex.org/W2142943472","https://openalex.org/W2143612262","https://openalex.org/W2144412323","https://openalex.org/W2145339207","https://openalex.org/W2167052694","https://openalex.org/W2194775991","https://openalex.org/W2202983866","https://openalex.org/W2241553860","https://openalex.org/W2296073425","https://openalex.org/W2424778531","https://openalex.org/W2518708963","https://openalex.org/W2524241275","https://openalex.org/W2549139847","https://openalex.org/W2573311857","https://openalex.org/W2604272474","https://openalex.org/W2605102758","https://openalex.org/W2744979297","https://openalex.org/W2777057360","https://openalex.org/W2790268363","https://openalex.org/W2913756371","https://openalex.org/W2962887844","https://openalex.org/W2962957005","https://openalex.org/W2963001155","https://openalex.org/W2963722165","https://openalex.org/W2963809389","https://openalex.org/W3099533866","https://openalex.org/W3142707146","https://openalex.org/W4230504900"],"related_works":["https://openalex.org/W4317634134","https://openalex.org/W2981729160","https://openalex.org/W4310743282","https://openalex.org/W4306904969","https://openalex.org/W2743212448","https://openalex.org/W1819938260","https://openalex.org/W2340892746","https://openalex.org/W3163022373","https://openalex.org/W2742483371","https://openalex.org/W3005999311"],"abstract_inverted_index":{"Developing":[0],"a":[1,46,78,114,129,144,155,166,186,210,219,225,295,300,309,316],"safe":[2,289],"and":[3,29,54,124,176,190,224,250,290],"efficient":[4],"collision-avoidance":[5,34,81,277],"policy":[6,82,96,140,184,206,233,278,307,324],"for":[7,83,197,288,294],"multiple":[8],"robots":[9,148,223,247],"is":[10,51,64,141,162,207,234],"challenging":[11],"in":[12,71,90,107,149,185,209,260,299,315],"the":[13,59,110,119,173,180,204,216,232,257,264,268,276,323],"decentralized":[14,79,123],"scenarios":[15,192,214],"where":[16],"each":[17],"robot":[18,297,310,334],"generates":[19],"its":[20],"paths":[21],"with":[22,67,193,228,248],"limited":[23],"observation":[24],"of":[25,61,109,147,188,203,212,218,221,332],"other":[26],"robots\u2019":[27],"states":[28],"intentions.":[30],"Prior":[31],"distributed":[32],"multi-robot":[33,84,199,281],"systems":[35],"often":[36],"require":[37],"frequent":[38],"inter-robot":[39],"communication":[40],"or":[41],"agent-level":[42],"features":[43],"to":[44,102,134,170,262,311],"plan":[45],"local":[47],"collision-free":[48],"action,":[49],"which":[50,86],"not":[52,65],"robust":[53],"computationally":[55],"prohibitive.":[56],"In":[57,73,93],"addition,":[58],"performance":[60,120,195],"these":[62],"methods":[63],"comparable":[66],"their":[68],"centralized":[69,125],"counterparts":[70],"practice.":[72],"this":[74],"article,":[75],"we":[76,127,240,273],"present":[77,128],"sensor-level":[80,182],"systems,":[85],"shows":[87],"promising":[88],"results":[89],"practical":[91],"applications.":[92],"particular,":[94],"our":[95],"directly":[97],"maps":[98],"raw":[99],"sensor":[100],"measurements":[101],"an":[103,136,285],"agent\u2019s":[104],"steering":[105],"commands":[106],"terms":[108],"movement":[111],"velocity.":[112],"As":[113],"first":[115],"step":[116],"toward":[117],"reducing":[118],"gap":[121],"between":[122],"methods,":[126],"multi-scenario":[130],"multi-stage":[131],"training":[132],"framework":[133,169],"learn":[135],"optimal":[137],"policy.":[138],"The":[139,159,201],"trained":[142,235],"over":[143],"large":[145],"number":[146],"rich,":[150],"complex":[151],"environments":[152],"simultaneously":[153],"using":[154,236],"policy-gradient-based":[156],"reinforcement-learning":[157],"algorithm.":[158],"learning":[160],"algorithm":[161],"also":[163],"integrated":[164],"into":[165],"hybrid":[167],"control":[168],"further":[171],"improve":[172],"policy\u2019s":[174],"robustness":[175,266],"effectiveness.":[177],"We":[178],"validate":[179],"learned":[181,205,279,306],"collision-3avoidance":[183],"variety":[187],"simulated":[189,258],"real-world":[191],"thorough":[194],"evaluations":[196],"large-scale":[198,226],"systems.":[200],"generalization":[202],"verified":[208],"set":[211],"unseen":[213],"including":[215],"navigation":[217,282,293],"group":[220],"heterogeneous":[222],"scenario":[227],"100":[229],"robots.":[230],"Although":[231],"simulation":[237],"data":[238],"only,":[239],"have":[241],"successfully":[242,327],"deployed":[243,328],"it":[244],"on":[245,329],"physical":[246,333],"shapes":[249],"dynamics":[251],"characteristics":[252],"that":[253,275],"are":[254,341],"different":[255,330],"from":[256,280],"agents,":[259],"order":[261],"demonstrate":[263],"controller\u2019s":[265],"against":[267],"simulation-to-real":[269],"modeling":[270],"error.":[271],"Finally,":[272],"show":[274],"tasks":[283],"provides":[284],"excellent":[286],"solution":[287],"effective":[291,313],"autonomous":[292],"single":[296],"working":[298],"dense":[301],"real":[302],"human":[303],"crowd.":[304],"Our":[305],"enables":[308],"make":[312],"progress":[314],"crowd":[317],"without":[318,336],"getting":[319],"stuck.":[320],"More":[321],"importantly,":[322],"has":[325],"been":[326],"types":[331],"platforms":[335],"tedious":[337],"parameter":[338],"tuning.":[339],"Videos":[340],"available":[342],"at":[343],"https://sites.google.com/view/hybridmrca":[344],".":[345]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":72},{"year":2024,"cited_by_count":68},{"year":2023,"cited_by_count":59},{"year":2022,"cited_by_count":56},{"year":2021,"cited_by_count":48},{"year":2020,"cited_by_count":7}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}