{"id":"https://openalex.org/W4417057011","doi":"https://doi.org/10.1109/tase.2025.3641025","title":"Integrated Task and Motion Planner Using Hierarchical Reinforcement Learning for Multi-Robot Collaboration","display_name":"Integrated Task and Motion Planner Using Hierarchical Reinforcement Learning for Multi-Robot Collaboration","publication_year":2025,"publication_date":"2025-12-05","ids":{"openalex":"https://openalex.org/W4417057011","doi":"https://doi.org/10.1109/tase.2025.3641025"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2025.3641025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3641025","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-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/A5003736415","display_name":"Jiadong Zhang","orcid":"https://orcid.org/0009-0004-1042-5421"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junnan Zhang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057898837","display_name":"Chaoxu Mu","orcid":"https://orcid.org/0000-0003-1055-9513"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoxu Mu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040414354","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0002-8306-1663"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028426177","display_name":"Lei Ren","orcid":"https://orcid.org/0000-0001-6346-6930"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Ren","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003736415"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47331445,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"743","last_page":"755"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8427000045776367,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8427000045776367,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.06459999829530716,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.0215000007301569,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8219000101089478},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.784500002861023},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6819999814033508},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6758000254631042},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6216999888420105},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.5134000182151794},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.49729999899864197},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.4415999948978424}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8219000101089478},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.784500002861023},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6819999814033508},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6758000254631042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585999727249146},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6216999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535099983215332},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.4415999948978424},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.43560001254081726},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4327999949455261},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.41119998693466187},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.3555000126361847},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3292999863624573},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2574000060558319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3641025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3641025","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7181085981","display_name":null,"funder_award_id":"62503356","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G751832858","display_name":null,"funder_award_id":"62333016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2796419292","https://openalex.org/W2888838050","https://openalex.org/W2950069298","https://openalex.org/W2967969632","https://openalex.org/W2997072274","https://openalex.org/W3004407706","https://openalex.org/W3035869396","https://openalex.org/W3134939669","https://openalex.org/W3185500914","https://openalex.org/W3198389305","https://openalex.org/W3200237136","https://openalex.org/W3206495137","https://openalex.org/W4200635426","https://openalex.org/W4221151438","https://openalex.org/W4225896760","https://openalex.org/W4293776518","https://openalex.org/W4319302764","https://openalex.org/W4320015828","https://openalex.org/W4327571609","https://openalex.org/W4353083671","https://openalex.org/W4368232266","https://openalex.org/W4380606960","https://openalex.org/W4385299175","https://openalex.org/W4387350600","https://openalex.org/W4388579704","https://openalex.org/W4390492413","https://openalex.org/W4392172923","https://openalex.org/W4392405809","https://openalex.org/W4402216176","https://openalex.org/W4402217883","https://openalex.org/W4402810883","https://openalex.org/W4403123342"],"related_works":[],"abstract_inverted_index":{"The":[0,138,176],"task":[1,9,42,58,81,187],"planning":[2,5,43,119],"and":[3,10,44,82,99,114,133,140,147,169,188],"motion":[4,45,55,86,118],"problems":[6],"in":[7,24,79,145],"multi":[8,11,80,83,186,189],"robot":[12,54,84,109,123,190],"collaboration":[13],"are":[14,143],"usually":[15],"considered":[16],"as":[17,48],"independent":[18,30],"parts":[19],"to":[20,35,51,75,103,107,128],"be":[21],"solved.":[22],"However,":[23],"long-horizon,":[25],"multi-step":[26],"collaborative":[27,85,191],"scenarios,":[28],"this":[29,180],"solution":[31],"approach":[32],"is":[33],"difficult":[34],"effectively":[36],"handle":[37],"the":[38,49,130,155,158],"coupling":[39],"problem":[40],"between":[41],"planning,":[46,87],"such":[47],"inability":[50],"simultaneously":[52],"consider":[53],"collisions":[56],"during":[57],"allocation.":[59],"To":[60,153],"address":[61],"these":[62],"limitations,":[63],"we":[64,160],"develop":[65],"a":[66,94,111,125,164],"unified":[67],"hierarchical":[68],"reinforcement":[69],"learning":[70],"framework":[71],"that":[72,179],"enables":[73],"agents":[74],"learn":[76],"effective":[77],"policies":[78,120,142],"supplemented":[88],"by":[89],"two":[90],"techniques:":[91],"1)":[92],"using":[93],"shared":[95],"graph":[96],"attention":[97],"network":[98],"distributed":[100],"police":[101],"networks":[102],"assign":[104],"target":[105,134],"tasks":[106],"each":[108,122],"at":[110,124],"high":[112],"level,":[113],"2)":[115],"training":[116],"decentralized":[117],"for":[121],"low":[126],"level":[127],"control":[129],"workspace":[131],"state":[132],"end":[135],"actuator":[136],"posture.":[137],"high-level":[139],"low-level":[141],"trained":[144],"parallel":[146],"stabilized":[148],"through":[149],"expert":[150],"dataset":[151],"guidance.":[152],"verify":[154],"effectiveness":[156],"of":[157],"method,":[159],"conduct":[161],"experiments":[162],"on":[163],"general":[165],"object":[166],"placement":[167],"platform":[168],"an":[170],"engine":[171],"hydraulic":[172],"column":[173],"assembly":[174],"platform.":[175],"results":[177],"indicate":[178],"method":[181],"can":[182],"more":[183],"efficiently":[184],"complete":[185],"work.":[192]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-05T00:00:00"}