{"id":"https://openalex.org/W3211667558","doi":"https://doi.org/10.1109/icra46639.2022.9812263","title":"Relative Distributed Formation and Obstacle Avoidance with Multi-agent Reinforcement Learning","display_name":"Relative Distributed Formation and Obstacle Avoidance with Multi-agent Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W3211667558","doi":"https://doi.org/10.1109/icra46639.2022.9812263","mag":"3211667558"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9812263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812263","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5010122282","display_name":"Yuzi Yan","orcid":"https://orcid.org/0000-0002-3117-3305"},"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":true,"raw_author_name":"Yuzi Yan","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101557288","display_name":"Xiaoxiang Li","orcid":null},"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":"Xiaoxiang Li","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073994535","display_name":"Xinyou Qiu","orcid":"https://orcid.org/0000-0001-9443-5133"},"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":"Xinyou Qiu","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090846991","display_name":"Jiantao Qiu","orcid":"https://orcid.org/0000-0002-1328-2639"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiantao Qiu","raw_affiliation_strings":["Shanghai AI Laboratory,Shanghai,China","Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,Shanghai,China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333084","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-2525-4272"},"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":"Jian Wang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"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":"Yu Wang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052022779","display_name":"Yuan Shen","orcid":"https://orcid.org/0000-0002-9396-1964"},"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":"Yuan Shen","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5010122282"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":5.3777,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97593028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1661","last_page":"1667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9995999932289124,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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/T10524","display_name":"Traffic control and management","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.8041980266571045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7341742515563965},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.7113200426101685},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7043466567993164},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.7035088539123535},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.45560163259506226},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.4508143365383148},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4364606738090515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3673585057258606},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3522529602050781},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.329532265663147},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.19388577342033386},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.1791447401046753}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8041980266571045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341742515563965},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.7113200426101685},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7043466567993164},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.7035088539123535},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.45560163259506226},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.4508143365383148},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4364606738090515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3673585057258606},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3522529602050781},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.329532265663147},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.19388577342033386},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.1791447401046753},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9812263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812263","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7877711908","display_name":null,"funder_award_id":"2020YFC1511803","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1542094515","https://openalex.org/W1569051833","https://openalex.org/W1974395690","https://openalex.org/W1980755499","https://openalex.org/W1981826826","https://openalex.org/W2038946940","https://openalex.org/W2057555599","https://openalex.org/W2119616217","https://openalex.org/W2140621405","https://openalex.org/W2143148002","https://openalex.org/W2149372643","https://openalex.org/W2171353551","https://openalex.org/W2296073425","https://openalex.org/W2532784434","https://openalex.org/W2565972716","https://openalex.org/W2736601468","https://openalex.org/W2774092941","https://openalex.org/W2780149228","https://openalex.org/W2780814805","https://openalex.org/W2791307664","https://openalex.org/W2891076394","https://openalex.org/W2897780214","https://openalex.org/W2907916537","https://openalex.org/W2915044648","https://openalex.org/W2937310911","https://openalex.org/W2963407617","https://openalex.org/W2964045297","https://openalex.org/W2964121744","https://openalex.org/W2977794319","https://openalex.org/W3004300588","https://openalex.org/W3012544020","https://openalex.org/W3037540495","https://openalex.org/W3043763914","https://openalex.org/W3085438811","https://openalex.org/W3134226813","https://openalex.org/W3140164279","https://openalex.org/W3196353861","https://openalex.org/W3198375707","https://openalex.org/W3203067260","https://openalex.org/W3208337653","https://openalex.org/W4288090372","https://openalex.org/W4288624752","https://openalex.org/W4299802797","https://openalex.org/W6738796088","https://openalex.org/W6768842719","https://openalex.org/W6803436624"],"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/W2782776446","https://openalex.org/W3043170174","https://openalex.org/W2155948905","https://openalex.org/W2357323510"],"abstract_inverted_index":{"Multi-agent":[0],"formation":[1,93,144,146],"as":[2,4],"well":[3],"obstacle":[5,95,154],"avoid-ance":[6],"is":[7,47,136,172],"one":[8],"of":[9,18,37,40,134,153,169],"the":[10,16,54,64,74],"most":[11,39],"actively":[12],"studied":[13],"topics":[14],"in":[15,50,82,105,130],"field":[17],"multi-agent":[19,100],"systems.":[20],"Although":[21],"some":[22,57],"classic":[23,160],"controllers":[24],"like":[25],"model":[26],"predictive":[27],"control":[28,32,118,161],"(MPC)":[29],"and":[30,84,94,111,117,121,149,163,177],"fuzzy":[31],"achieve":[33],"a":[34,91,126],"certain":[35],"measure":[36],"success,":[38],"them":[41,135],"require":[42],"precise":[43],"global":[44],"information":[45,113],"which":[46,72],"not":[48],"accessible":[49],"harsh":[51],"environments.":[52],"On":[53],"other":[55],"hand,":[56],"reinforcement":[58,101],"learning":[59,102],"(RL)":[60],"based":[61,98],"approaches":[62],"adopt":[63],"leader-follower":[65],"structure":[66],"to":[67,114],"organize":[68],"different":[69],"agents'":[70],"behaviors,":[71],"sacrifices":[73],"collaboration":[75],"between":[76],"agents":[77],"thus":[78],"suffering":[79],"from":[80],"bottlenecks":[81],"maneuver-ability":[83],"robustness.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"propose":[90],"distributed":[92],"avoidance":[96,155],"method":[97,139,171],"on":[99],"(MARL).":[103],"Agents":[104],"our":[106,170],"system":[107],"only":[108],"utilize":[109],"local":[110],"relative":[112],"make":[115],"decisions":[116],"themselves":[119,124],"distributively,":[120],"will":[122],"reorganize":[123],"into":[125],"new":[127],"topology":[128],"quickly":[129],"case":[131],"that":[132],"any":[133],"dis-connected.":[137],"Our":[138],"achieves":[140],"better":[141],"performance":[142],"regarding":[143],"error,":[145],"convergence":[147],"rate":[148,152],"on-par":[150],"success":[151],"compared":[156],"with":[157,180],"baselines":[158],"(both":[159],"methods":[162],"another":[164],"RL-based":[165],"method).":[166],"The":[167],"feasibility":[168],"verified":[173],"by":[174],"both":[175],"simulation":[176],"hardware":[178],"implementation":[179],"Ackermann-steering":[181],"vehicles.":[182]},"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":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}