{"id":"https://openalex.org/W7124172669","doi":"https://doi.org/10.1109/icpads67057.2025.11323034","title":"Decentralized Reinforcement Learning for Cooperative Multi-Robot Navigation","display_name":"Decentralized Reinforcement Learning for Cooperative Multi-Robot Navigation","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124172669","doi":"https://doi.org/10.1109/icpads67057.2025.11323034"},"language":"en","primary_location":{"id":"doi:10.1109/icpads67057.2025.11323034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/ICPADS67057.2025.11323034","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101027341","display_name":"Yihao Zheng","orcid":"https://orcid.org/0000-0002-0346-3006"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yihao Zheng","raw_affiliation_strings":["Durham University,Department of Computer Science,Durham,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University,Department of Computer Science,Durham,UK","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059547542","display_name":"Farshad Arvin","orcid":null},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Farshad Arvin","raw_affiliation_strings":["Durham University,Department of Computer Science,Durham,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University,Department of Computer Science,Durham,UK","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122998761","display_name":"Junyan Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junyan Hu","raw_affiliation_strings":["Durham University,Department of Computer Science,Durham,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University,Department of Computer Science,Durham,UK","institution_ids":["https://openalex.org/I190082696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I190082696"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6514000296592712,"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":0.6514000296592712,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.08829999715089798,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.03849999979138374,"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":0.7128999829292297},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6916000247001648},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.61080002784729},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5914999842643738},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5266000032424927},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.48330000042915344},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734000027179718},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7128999829292297},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6916000247001648},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6319000124931335},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.61080002784729},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48500001430511475},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.36039999127388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.266400009393692},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},{"id":"pmh:oai:durham-repository.worktribe.com:4696308","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICPADS67057.2025.11323034","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"}],"best_oa_location":{"id":"pmh:oai:durham-repository.worktribe.com:4696308","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICPADS67057.2025.11323034","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.49787095189094543,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1969483458","https://openalex.org/W1989407213","https://openalex.org/W2088956500","https://openalex.org/W2296073425","https://openalex.org/W2575733488","https://openalex.org/W2593237273","https://openalex.org/W2892258706","https://openalex.org/W2903998385","https://openalex.org/W2964211993","https://openalex.org/W2964997335","https://openalex.org/W3130631955","https://openalex.org/W3166401044","https://openalex.org/W3175724379","https://openalex.org/W3201099806","https://openalex.org/W3206082228","https://openalex.org/W4383112356","https://openalex.org/W4385245566","https://openalex.org/W4388010330","https://openalex.org/W4389689571","https://openalex.org/W4391471217","https://openalex.org/W4405785123","https://openalex.org/W4409473730","https://openalex.org/W4409660543"],"related_works":[],"abstract_inverted_index":{"Cooperative":[0],"multi-robot":[1],"navigation":[2,116],"requires":[3],"large":[4],"teams":[5],"of":[6,31,93,125],"robots":[7],"to":[8,40],"reach":[9],"individual":[10],"goals":[11],"without":[12],"collisions":[13],"in":[14,117,147],"shared":[15],"spaces,":[16],"which":[17],"is":[18],"a":[19,61,68,85],"challenge":[20],"compounded":[21],"by":[22],"partial":[23],"observability,":[24],"dynamic":[25],"interactions,":[26],"and":[27,52,77,97,107,113,128,141],"the":[28],"combinatorial":[29],"nature":[30],"joint":[32],"decision-making.":[33],"Centralized":[34],"methods":[35,146],"provide":[36],"optimality":[37],"but":[38],"fail":[39],"scale,":[41],"while":[42],"decentralized":[43,62],"approaches":[44],"offer":[45],"efficiency":[46],"yet":[47],"often":[48],"suffer":[49],"from":[50],"deadlocks":[51],"weak":[53],"cooperation.":[54],"To":[55],"overcome":[56],"these":[57],"limitations,":[58],"we":[59],"propose":[60],"reinforcement":[63],"learning":[64],"framework":[65],"that":[66,89,132],"integrates":[67],"dual-head":[69],"soft":[70],"actor-critic":[71],"architecture":[72],"with":[73],"selective":[74],"graph-attention":[75],"communication":[76],"task-specific":[78],"reward":[79],"shaping.":[80],"A":[81],"compact":[82],"encoder":[83],"processes":[84],"novel":[86],"observation":[87],"representation":[88],"combines":[90],"local":[91],"fields":[92],"view,":[94],"goal":[95],"projections,":[96],"directional":[98],"heuristics,":[99],"enabling":[100],"scalable":[101],"awareness":[102],"under":[103],"limited":[104],"sensing.":[105],"Heuristic":[106],"blocking":[108],"rewards":[109],"further":[110],"accelerate":[111],"convergence":[112],"promote":[114],"cooperative":[115],"congested":[118],"regions.":[119],"Extensive":[120],"experiments":[121],"on":[122],"grid":[123],"environments":[124],"varying":[126],"sizes":[127],"robot":[129],"densities":[130],"show":[131],"our":[133],"method":[134],"achieves":[135],"faster":[136],"convergence,":[137],"higher":[138],"success":[139],"rates,":[140],"stronger":[142],"scalability":[143],"than":[144],"state-of-the-art":[145],"this":[148],"domain.":[149]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-15T00:00:00"}