{"id":"https://openalex.org/W7124160873","doi":"https://doi.org/10.1109/icpads67057.2025.11323196","title":"Hierarchical Multi-Agent Deep Reinforcement Learning for Cooperative Exploration of UAV Swarms","display_name":"Hierarchical Multi-Agent Deep Reinforcement Learning for Cooperative Exploration of UAV Swarms","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124160873","doi":"https://doi.org/10.1109/icpads67057.2025.11323196"},"language":"en","primary_location":{"id":"doi:10.1109/icpads67057.2025.11323196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323196","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/ICPADS67057.2025.11323196","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123044075","display_name":"Nathaniel Mackay Salt","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":"Nathaniel Mackay Salt","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":1,"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/T12158","display_name":"Guidance and Control Systems","score":0.28780001401901245,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.28780001401901245,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.28769999742507935,"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":0.08910000324249268,"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":0.7226999998092651},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.59170001745224},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5436999797821045},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.48840001225471497},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.48500001430511475},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.46369999647140503},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.44620001316070557},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.40860000252723694}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7226999998092651},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6571999788284302},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303999781608582},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.48500001430511475},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4717999994754791},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.3734999895095825},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35040000081062317},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2687000036239624},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2671000063419342}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323196","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:4696319","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICPADS67057.2025.11323196","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:4696319","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ICPADS67057.2025.11323196","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1497695555","https://openalex.org/W2222512263","https://openalex.org/W2910054127","https://openalex.org/W2973229164","https://openalex.org/W2996134258","https://openalex.org/W4289829044","https://openalex.org/W4312812232","https://openalex.org/W4319302559","https://openalex.org/W4319993446","https://openalex.org/W4324119510","https://openalex.org/W4383108450","https://openalex.org/W4383109033","https://openalex.org/W4392114333","https://openalex.org/W4405785979","https://openalex.org/W4405873206","https://openalex.org/W4406354887","https://openalex.org/W4409473730","https://openalex.org/W4413918062"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"exploration":[1,122],"of":[2],"unknown,":[3],"cluttered":[4],"environments":[5],"using":[6],"unmanned":[7],"aerial":[8],"vehicle":[9],"swarms":[10],"is":[11],"critical":[12],"for":[13,70,79,105],"applications":[14],"like":[15,47],"search":[16],"and":[17,26,35,50,86,124],"rescue,":[18],"yet":[19],"poses":[20],"significant":[21],"challenges":[22],"in":[23,121],"coordination,":[24],"scalability,":[25],"adaptability.":[27],"Classical":[28],"methods":[29],"often":[30],"struggle":[31],"with":[32,75,128],"dynamic":[33],"conditions":[34],"large":[36],"swarm":[37],"sizes,":[38],"while":[39,100],"standard":[40],"Multi-Agent":[41],"Reinforcement":[42],"Learning":[43],"(MARL)":[44],"faces":[45],"issues":[46],"state-space":[48],"explosion":[49],"non-stationarity.":[51],"This":[52,64],"work":[53],"proposes":[54],"a":[55,91,117],"novel":[56],"hierarchical":[57,67,112],"MARL":[58],"framework":[59],"to":[60,97],"address":[61],"these":[62],"limitations.":[63],"approach":[65,114],"integrates":[66],"grid":[68],"decomposition":[69],"high-level":[71],"strategic":[72],"task":[73],"allocation":[74],"multi-agent":[76],"soft":[77],"actor-critic":[78],"low-level":[80],"reactive":[81],"control,":[82],"enabling":[83],"efficient":[84],"navigation":[85],"collision":[87],"avoidance.":[88],"Training":[89],"employs":[90],"centralised":[92],"training":[93],"decentralised":[94,102],"execution":[95],"paradigm":[96],"foster":[98],"cooperation":[99],"maintaining":[101],"operation":[103],"suitable":[104],"real-world":[106],"constraints.":[107],"Results":[108],"demonstrate":[109],"that":[110],"the":[111],"learning":[113],"significantly":[115],"outperforms":[116],"non-learning":[118],"heuristic":[119],"baseline":[120],"efficiency":[123],"exhibits":[125],"robust":[126],"scalability":[127],"increasing":[129],"agent":[130],"numbers.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-15T00:00:00"}