{"id":"https://openalex.org/W4220817121","doi":"https://doi.org/10.1109/lra.2022.3161699","title":"Reinforcement Learned Distributed Multi-Robot Navigation With Reciprocal Velocity Obstacle Shaped Rewards","display_name":"Reinforcement Learned Distributed Multi-Robot Navigation With Reciprocal Velocity Obstacle Shaped Rewards","publication_year":2022,"publication_date":"2022-03-23","ids":{"openalex":"https://openalex.org/W4220817121","doi":"https://doi.org/10.1109/lra.2022.3161699"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3161699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3161699","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/A5062988632","display_name":"Ruihua Han","orcid":"https://orcid.org/0000-0001-6206-5289"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"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":["CN","HK"],"is_corresponding":false,"raw_author_name":"Ruihua Han","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong","Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-6206-5289","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058043624","display_name":"Shengduo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengduo Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082746949","display_name":"Shuaijun Wang","orcid":"https://orcid.org/0000-0003-4007-4541"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaijun Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0003-4007-4541","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003718185","display_name":"Zeqing Zhang","orcid":"https://orcid.org/0000-0002-5935-3674"},"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":"Zeqing Zhang","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-5935-3674","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089860344","display_name":"Rui Gao","orcid":"https://orcid.org/0009-0004-0229-2753"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Gao","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037660521","display_name":"Qi Hao","orcid":"https://orcid.org/0000-0002-2792-5965"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Hao","raw_affiliation_strings":["Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-2792-5965","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"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":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9003-2054","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.7245,"has_fulltext":false,"cited_by_count":146,"citation_normalized_percentile":{"value":0.99296859,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"7","issue":"3","first_page":"5896","last_page":"5903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.998199999332428,"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":0.8404991030693054},{"id":"https://openalex.org/keywords/reciprocal","display_name":"Reciprocal","score":0.769883394241333},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.6967856884002686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6657658815383911},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.6293457746505737},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.6172900795936584},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.605294942855835},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.5363726615905762},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.532166600227356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5028306841850281},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.43057239055633545},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.32515275478363037},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13445261120796204}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8404991030693054},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.769883394241333},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.6967856884002686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6657658815383911},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.6293457746505737},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.6172900795936584},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.605294942855835},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5363726615905762},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.532166600227356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5028306841850281},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.43057239055633545},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.32515275478363037},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13445261120796204},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3161699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3161699","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":[],"awards":[{"id":"https://openalex.org/G345495281","display_name":null,"funder_award_id":"JCYJ20200109141622964","funder_id":"https://openalex.org/F4320329791","funder_display_name":"Shenzhen Fundamental Research Program"}],"funders":[{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W6827933","https://openalex.org/W178419168","https://openalex.org/W192919555","https://openalex.org/W2097639646","https://openalex.org/W2142943472","https://openalex.org/W2477170489","https://openalex.org/W2604216058","https://openalex.org/W2736601468","https://openalex.org/W2775408149","https://openalex.org/W2797537646","https://openalex.org/W2890001928","https://openalex.org/W2890059413","https://openalex.org/W2963809389","https://openalex.org/W2963821308","https://openalex.org/W2964319688","https://openalex.org/W2981759303","https://openalex.org/W3031798691","https://openalex.org/W3081975785","https://openalex.org/W3090254537","https://openalex.org/W3130079089","https://openalex.org/W3131482536","https://openalex.org/W3205553845","https://openalex.org/W3206270475","https://openalex.org/W3210542994","https://openalex.org/W4299802797","https://openalex.org/W6600296044","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6780226713","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2930076404","https://openalex.org/W4253519380","https://openalex.org/W2071957557","https://openalex.org/W2596413128","https://openalex.org/W4391249562","https://openalex.org/W2356867392","https://openalex.org/W2913749762","https://openalex.org/W2321940404","https://openalex.org/W2782776446","https://openalex.org/W3043170174"],"abstract_inverted_index":{"The":[0,60,140,172],"challenges":[1],"to":[2,50,77,109,125],"solving":[3],"the":[4,35,43,52,79,100,110,151,158,180,191],"collision":[5,54,120,128,135],"avoidance":[6,55,129],"problem":[7,56],"lie":[8],"in":[9,15,160,188],"adaptively":[10],"choosing":[11],"optimal":[12],"robot":[13],"velocities":[14],"complex":[16,161],"scenarios":[17,147],"full":[18],"of":[19,37,45,62,71,83,102,106,166,190],"interactive":[20,80],"obstacles.":[21,171],"In":[22],"this":[23,63],"letter,":[24],"we":[25],"propose":[26],"a":[27,69,91,103,115],"distributed":[28],"approach":[29,178],"for":[30],"multi-robot":[31],"navigation":[32],"which":[33,98],"combines":[34],"concept":[36],"reciprocal":[38,53,127],"velocity":[39],"obstacle":[40],"(RVO)":[41],"and":[42,74,85,118,131,137,148,170,183,196],"scheme":[44],"deep":[46],"reinforcement":[47],"learning":[48,185],"(DRL)":[49],"solve":[51],"under":[57],"limited":[58],"information.":[59],"novelty":[61],"work":[64],"is":[65,143],"threefold:":[66],"(1)":[67],"using":[68],"set":[70],"sequential":[72],"VO":[73],"RVO":[75,116],"vectors":[76],"represent":[78],"environmental":[81],"states":[82,101],"static":[84],"dynamic":[86],"obstacles,":[87],"respectively;":[88],"(2)":[89],"developing":[90,114],"bidirectional":[92],"recurrent":[93],"module":[94],"based":[95,122,153,186],"neural":[96],"network,":[97],"maps":[99],"varying":[104],"number":[105],"surrounding":[107],"obstacles":[108],"actions":[111],"directly;":[112],"(3)":[113],"area":[117],"expected":[119],"time":[121],"reward":[123],"function":[124],"encourage":[126],"behaviors":[130],"trade":[132],"off":[133],"between":[134],"risk":[136],"travel":[138,194],"time.":[139],"proposed":[141],"policy":[142,159],"trained":[144],"through":[145],"simulated":[146],"updated":[149],"by":[150],"actor-critic":[152],"DRL":[154],"algorithm.":[155],"We":[156],"validate":[157],"environments":[162],"with":[163],"various":[164],"numbers":[165],"differential":[167],"drive":[168],"robots":[169],"experiment":[173],"results":[174],"demonstrate":[175],"that":[176],"our":[177],"outperforms":[179],"state-of-art":[181],"methods":[182],"other":[184],"approaches":[187],"terms":[189],"success":[192],"rate,":[193],"time,":[195],"average":[197],"speed.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":48},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}