{"id":"https://openalex.org/W4413018059","doi":"https://doi.org/10.1109/iv64158.2025.11097389","title":"Decentralized Reinforcement Learning for Multi-Agent Navigation in Unconstrained Environments","display_name":"Decentralized Reinforcement Learning for Multi-Agent Navigation in Unconstrained Environments","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4413018059","doi":"https://doi.org/10.1109/iv64158.2025.11097389"},"language":"en","primary_location":{"id":"doi:10.1109/iv64158.2025.11097389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv64158.2025.11097389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Intelligent Vehicles Symposium (IV)","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/A5110818174","display_name":"F. A. F\u00f6rster","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Felix Forster","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Computer Vision Group,Germany"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Computer Vision Group,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029411186","display_name":"Qadeer Khan","orcid":"https://orcid.org/0000-0001-9600-9031"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Qadeer Khan","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Computer Vision Group,Germany"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Computer Vision Group,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087710605","display_name":"Daniel Cremers","orcid":"https://orcid.org/0000-0002-3079-7984"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Cremers","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Computer Vision Group,Germany"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Computer Vision Group,Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110818174"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22925007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2067","last_page":"2073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9975000023841858,"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":0.9975000023841858,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9860000014305115,"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":0.9753000140190125,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.839552640914917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6847570538520813},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4755106568336487},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.41578975319862366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40550094842910767},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3761904239654541}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.839552640914917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6847570538520813},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4755106568336487},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.41578975319862366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40550094842910767},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3761904239654541}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv64158.2025.11097389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv64158.2025.11097389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2104034461","https://openalex.org/W2892258706","https://openalex.org/W2905173465","https://openalex.org/W2948342290","https://openalex.org/W2962999504","https://openalex.org/W3167586364","https://openalex.org/W3179076235","https://openalex.org/W4200218019","https://openalex.org/W4224222720","https://openalex.org/W4285813069","https://openalex.org/W4292347911","https://openalex.org/W4309565568","https://openalex.org/W4312862130","https://openalex.org/W4322007488","https://openalex.org/W4385359649","https://openalex.org/W4388579659","https://openalex.org/W4390575480","https://openalex.org/W4391335029","https://openalex.org/W4391768553","https://openalex.org/W4399772654","https://openalex.org/W6637967152","https://openalex.org/W6684338915","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6745935785","https://openalex.org/W6747473740","https://openalex.org/W6750106230","https://openalex.org/W6759754333","https://openalex.org/W6849609359"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W2786230833","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152","https://openalex.org/W1493952344"],"abstract_inverted_index":{"Supervised":[0],"learning":[1],"has":[2],"demonstrated":[3],"to":[4,33,60,80,96,132,148,152,168,187,209,238,242],"be":[5,24,34,218],"an":[6,111],"effective":[7],"strategy":[8,225],"in":[9,62,110],"training":[10],"neural":[11],"networks":[12],"for":[13,46,92],"vehicle":[14,72,151,171],"navigation.":[15],"However,":[16,53],"it":[17],"requires":[18],"labeled":[19],"data,":[20],"which":[21],"may":[22],"not":[23,69],"available":[25],"when":[26],"a":[27,118,223,231],"large":[28],"number":[29],"of":[30,155,181,214,234],"vehicles":[31,83,95,216,244],"need":[32],"controlled":[35],"simultaneously.":[36],"In":[37,74],"contrast,":[38],"Deep":[39],"Reinforcement":[40],"Learning":[41],"(DRL)":[42],"circumvents":[43],"the":[44,63,71,94,153,160,163,173,182,202],"necessity":[45],"ground":[47],"truth":[48],"labels":[49],"through":[50],"environmental":[51],"exploration.":[52],"most":[54],"concurrent":[55],"DRL":[56,79,125],"approaches":[57],"either":[58],"tend":[59],"operate":[61],"discrete":[64],"action/state":[65],"space":[66],"or":[67,107],"do":[68],"consider":[70],"kinematics.":[73,88],"this":[75,207],"paper,":[76],"we":[77,116],"use":[78],"control":[81,130],"multiple":[82,215],"while":[84,101,236],"also":[85],"considering":[86],"their":[87,98],"The":[89,135,144,178],"task":[90],"is":[91,137,146,166],"all":[93,210],"reach":[97],"desired":[99],"destination/target":[100],"avoiding":[102],"collisions":[103],"with":[104,199,240],"each":[105,133,150,185],"other":[106],"static":[108],"obstacles":[109],"unconstrained":[112],"environment.":[113],"For":[114],"this,":[115],"propose":[117],"decentralized":[119,179],"Proximal":[120],"Policy":[121],"Optimization":[122],"(PPO)":[123],"based":[124,138],"agent":[126,136,186],"that":[127,170,226],"independently":[128],"provides":[129],"commands":[131],"vehicle.":[134],"on":[139,190],"two":[140],"separate":[141],"PPO":[142],"models.":[143],"first":[145],"used":[147,167],"drive":[149],"proximity":[154],"its":[156,193],"target.":[157],"Once":[158],"within":[159],"target's":[161],"proximity,":[162],"second":[164],"model":[165],"park":[169],"at":[172],"correct":[174],"position":[175],"and":[176,196,245],"orientation.":[177],"nature":[180],"algorithm":[183],"allows":[184,227],"rely":[188],"only":[189],"information":[191],"about":[192],"current":[194],"state":[195],"target,":[197],"along":[198],"details":[200],"regarding":[201],"closest":[203],"obstacle/agent.":[204],"By":[205],"scaling":[206,237],"approach":[208],"vehicles,":[211],"simultaneous":[212],"navigation":[213],"can":[217],"achieved.":[219],"Experimental":[220],"results":[221,229],"show":[222],"collective":[224],"consistent":[228],"across":[230],"wide":[232],"range":[233],"scenarios":[235],"situations":[239],"up":[241],"20":[243],"12":[246],"stationary":[247],"obstacles.":[248]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}