{"id":"https://openalex.org/W4405903347","doi":"https://doi.org/10.1109/tro.2026.3686265","title":"Large-Scale Multirobot Task Planning Using Efficient Hierarchical Reinforcement Learning","display_name":"Large-Scale Multirobot Task Planning Using Efficient Hierarchical Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4405903347","doi":"https://doi.org/10.1109/tro.2026.3686265"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2026.3686265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2026.3686265","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"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 Transactions on Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.19538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100670119","display_name":"Xuan Zhou","orcid":"https://orcid.org/0000-0002-3602-5870"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Zhou","raw_affiliation_strings":["State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-0809-4234","affiliations":[{"raw_affiliation_string":"State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101446912","display_name":"Xiang Shi","orcid":"https://orcid.org/0000-0003-1517-8947"},"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":"Xiang Shi","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2672-6128","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079289315","display_name":"Lele Zhang","orcid":"https://orcid.org/0009-0003-5789-9547"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lele Zhang","raw_affiliation_strings":["State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9661-2543","affiliations":[{"raw_affiliation_string":"State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418404","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0002-0184-4681"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9354-6974","affiliations":[{"raw_affiliation_string":"State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402167","display_name":"Hongbo Li","orcid":"https://orcid.org/0000-0002-6990-4855"},"institutions":[{"id":"https://openalex.org/I2802536167","display_name":"Beijing Film Academy","ror":"https://ror.org/03y0w9190","country_code":"CN","type":"education","lineage":["https://openalex.org/I2802536167"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Li","raw_affiliation_strings":["Beijing Geek+ Technology Comoany, Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-4050-1755","affiliations":[{"raw_affiliation_string":"Beijing Geek+ Technology Comoany, Ltd., Beijing, China","institution_ids":["https://openalex.org/I2802536167"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018662596","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0003-1684-9714"},"institutions":[{"id":"https://openalex.org/I4210163926","display_name":"Zhejiang Medicine (China)","ror":"https://ror.org/05h86nk22","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210163926"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Zhejiang Cainiao Supply Chain Management Company, Ltd., Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6446-1824","affiliations":[{"raw_affiliation_string":"Zhejiang Cainiao Supply Chain Management Company, Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I4210163926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050766","display_name":"Fang Deng","orcid":"https://orcid.org/0000-0002-1111-7285"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Deng","raw_affiliation_strings":["State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1111-7285","affiliations":[{"raw_affiliation_string":"State Key Lab of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100333005","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0003-2449-9793"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2449-9793","affiliations":[{"raw_affiliation_string":"State Key Lab of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00638688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":null,"first_page":"2146","last_page":"2165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9369000196456909,"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":0.9369000196456909,"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":0.8619247674942017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6707085371017456},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6089011430740356},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6074582934379578},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5433012843132019},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49904656410217285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4634395241737366},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41201484203338623},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12166038155555725},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08933418989181519},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.0499647855758667},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.04466351866722107}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8619247674942017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6707085371017456},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6089011430740356},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6074582934379578},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5433012843132019},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49904656410217285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634395241737366},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41201484203338623},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12166038155555725},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08933418989181519},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0499647855758667},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.04466351866722107},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tro.2026.3686265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2026.3686265","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"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 Transactions on Robotics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2412.19538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.19538","pdf_url":"https://arxiv.org/pdf/2412.19538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:arXiv.org:2412.19538","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2412.19538","pdf_url":"https://arxiv.org/pdf/2412.19538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.19538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.19538","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.19538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.19538","pdf_url":"https://arxiv.org/pdf/2412.19538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405903347.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2389214306","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Multi-robot":[0],"task":[1,36,58],"planning":[2,47,59],"(MRTP)":[3],"at":[4],"scale":[5],"in":[6,123,146],"robotic":[7],"mobile":[8],"fulfillment":[9],"systems":[10,43],"(RMFS)":[11],"remains":[12],"a":[13,54,77,103,128],"challenge":[14],"due":[15],"to":[16,26,41,61,84,115,137,218,222],"the":[17,63,89,94,99,143,152,157],"curse":[18,64],"of":[19,39,65],"dimensionality":[20,66],"and":[21,118,212],"complex":[22],"dynamic":[23,70,159],"properties.":[24],"Aiming":[25],"solve":[27],"these":[28],"challenges,":[29],"we":[30,52,75,97,191],"construct":[31],"an":[32,170],"end-to-end":[33],"scalable":[34],"multi-robot":[35],"planner":[37,202],"capable":[38],"scaling":[40],"large-scale":[42],"by":[44],"learning":[45],"hierarchical":[46,56,129,164,172],"policies.":[48],"In":[49],"this":[50,73,147],"planner,":[51],"design":[53],"centralized":[55],"temporal":[57,81,130,134],"framework":[60],"mitigate":[62],"while":[67,187,231],"ensuring":[68],"timely":[69],"response.":[71],"Following":[72],"framework,":[74],"propose":[76],"novel":[78],"cycle-constrained":[79],"asynchronous":[80],"graph":[82,95],"(CycATG)":[83],"provide":[85],"foundation":[86],"for":[87],"modeling":[88],"system":[90],"dynamics.":[91],"Based":[92],"on":[93,111,184,206,228],"representation,":[96],"formulate":[98],"MRTP":[100,208],"problem":[101],"as":[102],"semi-Markov":[104],"decision":[105],"process":[106],"(SMDP)":[107],"that":[108,151,200],"focuses":[109],"solely":[110],"critical":[112],"interaction":[113],"points":[114],"improve":[116],"computational":[117],"sampling":[119],"efficiency.":[120],"The":[121,162],"policies":[122,165],"SMDP":[124],"are":[125,166],"parameterized":[126],"via":[127],"attention":[131],"network":[132,148],"with":[133,174,194,220],"embedding":[135],"layers":[136],"enhance":[138,181],"spatio-temporal":[139],"feature":[140],"extraction.":[141],"Additionally,":[142],"decoder":[144],"masks":[145],"naturally":[149],"ensure":[150],"generated":[153],"actions":[154],"strictly":[155],"satisfy":[156],"required":[158],"hard":[160],"constraints.":[161],"above":[163],"jointly":[167],"optimized":[168],"using":[169],"efficient":[171],"REINFORCE":[173],"rollout":[175],"counterfactual":[176],"baseline":[177],"method.":[178],"To":[179],"further":[180],"generalization":[182],"performance":[183,233],"unlearned":[185,229],"instances":[186,209,219],"preventing":[188],"catastrophic":[189],"forgetting,":[190],"extend":[192],"it":[193],"region":[195],"expansion":[196],"curricula.":[197],"Experiments":[198],"demonstrate":[199],"our":[201],"outperforms":[203],"state-of-the-art":[204],"methods":[205],"different":[207],"across":[210],"simulated":[211],"real-world":[213],"RMFS.":[214],"It":[215],"successfully":[216],"scales":[217],"up":[221],"200":[223],"robots,":[224],"1000":[225],"retrieval":[226],"racks":[227],"maps":[230],"maintaining":[232],"advantages.":[234]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2024-12-31T00:00:00"}
