{"id":"https://openalex.org/W4387587658","doi":"https://doi.org/10.1109/access.2023.3324039","title":"A Hierarchical Robot Learning Framework for Manipulator Reactive Motion Generation via Multi-Agent Reinforcement Learning and Riemannian Motion Policies","display_name":"A Hierarchical Robot Learning Framework for Manipulator Reactive Motion Generation via Multi-Agent Reinforcement Learning and Riemannian Motion Policies","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387587658","doi":"https://doi.org/10.1109/access.2023.3324039"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3324039","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3324039","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10283841.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10283841.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068191896","display_name":"Yuliu Wang","orcid":"https://orcid.org/0000-0001-5037-4324"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuliu Wang","raw_affiliation_strings":["Intelligent and Mechanical Interaction Systems Program, University of Tsukuba, Ibaraki, Tsukuba, Japan","Computer Vision Research Team, Artificial Intelligence Research Center, The National Institute of Advanced Industrial Science and Technology, 1-1-1 Umezono, Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"Intelligent and Mechanical Interaction Systems Program, University of Tsukuba, Ibaraki, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Computer Vision Research Team, Artificial Intelligence Research Center, The National Institute of Advanced Industrial Science and Technology, 1-1-1 Umezono, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076890403","display_name":"Ryusuke Sagawa","orcid":"https://orcid.org/0000-0002-6778-8838"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryusuke Sagawa","raw_affiliation_strings":["Intelligent and Mechanical Interaction Systems Program, University of Tsukuba, Ibaraki, Tsukuba, Japan","Computer Vision Research Team, Artificial Intelligence Research Center, The National Institute of Advanced Industrial Science and Technology, 1-1-1 Umezono, Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"Intelligent and Mechanical Interaction Systems Program, University of Tsukuba, Ibaraki, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Computer Vision Research Team, Artificial Intelligence Research Center, The National Institute of Advanced Industrial Science and Technology, 1-1-1 Umezono, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023347873","display_name":"Yusuke Yoshiyasu","orcid":"https://orcid.org/0000-0002-0433-9832"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Yoshiyasu","raw_affiliation_strings":["Computer Vision Research Team, Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Ibaraki, Tsukuba, Japan","Computer Vision Research Team, Artificial Intelligence Research Center, The National Institute of Advanced Industrial Science and Technology, 1-1-1 Umezono, Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"Computer Vision Research Team, Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Ibaraki, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Computer Vision Research Team, Artificial Intelligence Research Center, The National Institute of Advanced Industrial Science and Technology, 1-1-1 Umezono, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068191896"],"corresponding_institution_ids":["https://openalex.org/I146399215","https://openalex.org/I73613424"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.3457,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66570141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"11","issue":null,"first_page":"126979","last_page":"126994"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9987000226974487,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9986000061035156,"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":0.852198600769043},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.659085750579834},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6284871101379395},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4746868312358856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4626276195049286},{"id":"https://openalex.org/keywords/robot-manipulator","display_name":"Robot manipulator","score":0.41214701533317566}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.852198600769043},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.659085750579834},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6284871101379395},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4746868312358856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4626276195049286},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.41214701533317566}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3324039","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3324039","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10283841.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a8cd61dc61eb446a89086e496eefcf85","is_oa":true,"landing_page_url":"https://doaj.org/article/a8cd61dc61eb446a89086e496eefcf85","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 126979-126994 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3324039","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3324039","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10283841.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1036901904","display_name":"\u6570\u5b66\u6559\u80b2\u306e\u6620\u50cf\u5316\u3068\u6559\u5177\u306e\u958b\u767a","funder_award_id":"20006","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1386331666","display_name":null,"funder_award_id":"JPMJSP2124","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3499414489","display_name":null,"funder_award_id":"JP22H05002","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3818729332","display_name":null,"funder_award_id":"JPNP20006","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4022835417","display_name":null,"funder_award_id":"22H00545","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G403036907","display_name":null,"funder_award_id":"22H0054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6725152017","display_name":null,"funder_award_id":"JPNP20006","funder_id":"https://openalex.org/F4320321034","funder_display_name":"New Energy and Industrial Technology Development Organization"},{"id":"https://openalex.org/G7752643416","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8227167501","display_name":null,"funder_award_id":"JP22H00545","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8642918698","display_name":null,"funder_award_id":"22H05002","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387587658.pdf","grobid_xml":"https://content.openalex.org/works/W4387587658.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W931741147","https://openalex.org/W1584761227","https://openalex.org/W1974812331","https://openalex.org/W1979318851","https://openalex.org/W1997543377","https://openalex.org/W2104144149","https://openalex.org/W2113122939","https://openalex.org/W2121517924","https://openalex.org/W2133105703","https://openalex.org/W2141664020","https://openalex.org/W2155007355","https://openalex.org/W2172968643","https://openalex.org/W2404399993","https://openalex.org/W2490314460","https://openalex.org/W2575705757","https://openalex.org/W2618749399","https://openalex.org/W2736601468","https://openalex.org/W2912222576","https://openalex.org/W2963864421","https://openalex.org/W2964036701","https://openalex.org/W3003997138","https://openalex.org/W3036295212","https://openalex.org/W3091673899","https://openalex.org/W3092031423","https://openalex.org/W3101552411","https://openalex.org/W3117976796","https://openalex.org/W3129265343","https://openalex.org/W3140178043","https://openalex.org/W3174491581","https://openalex.org/W3212380917","https://openalex.org/W4205437745","https://openalex.org/W4206165650","https://openalex.org/W4214717370","https://openalex.org/W4281480521","https://openalex.org/W4286748781","https://openalex.org/W4294411035","https://openalex.org/W4298857966","https://openalex.org/W4312717586","https://openalex.org/W4362672763","https://openalex.org/W4383108656","https://openalex.org/W6637967152","https://openalex.org/W6676748545","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6748012927","https://openalex.org/W6748202546","https://openalex.org/W6755437240","https://openalex.org/W6768237719","https://openalex.org/W6778225464","https://openalex.org/W6779416026","https://openalex.org/W6780559895","https://openalex.org/W6784930079","https://openalex.org/W6838701874"],"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/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Manipulators":[0],"motion":[1,23],"planning":[2],"faces":[3],"new":[4],"challenges":[5],"as":[6,215],"robots":[7],"are":[8,154],"increasingly":[9],"used":[10,155,170],"in":[11,48,254],"dense,":[12],"cluttered":[13],"and":[14,56,68,138,151,180,187,219,234,243,251,277,280],"dynamic":[15,49,255,275],"environments.":[16,256],"The":[17],"recently":[18],"proposed":[19,228,260],"technique":[20],"called":[21],"Riemannian":[22],"policies(RMPs)":[24],"provides":[25],"an":[26,173],"elegant":[27],"solution":[28],"with":[29,51,88,207,230],"clear":[30],"mathematical":[31],"interpretations":[32],"to":[33,75,81,98,111,156,171,211,274],"such":[34,113,214],"challenging":[35],"scenarios.":[36],"It":[37],"is":[38,59,169,244],"based":[39,120,183],"on":[40,121,184],"differential":[41],"geometry":[42],"policies":[43,115,210],"that":[44,132,175,236],"generate":[45],"reactive":[46,158],"motions":[47,83],"environments":[50,276],"real-time":[52],"performance.":[53],"However,":[54],"designing":[55],"combining":[57],"RMPs":[58,73,95,148,179],"still":[60],"a":[61,85,109,127,164,198,217],"difficult":[62],"task":[63],"involving":[64],"extensive":[65],"parameter":[66],"tuning,":[67],"typically":[69],"seven":[70],"or":[71],"more":[72,89],"need":[74],"be":[76,99,189],"combined":[77],"by":[78],"using":[79],"RMPflow":[80],"realize":[82],"of":[84,134,271],"robot":[86,129],"manipulator":[87],"than":[90],"6":[91],"degrees-of-freedoms,":[92],"where":[93],"the":[94,135,142,161,195,205,227,231,259,268],"parameters":[96,182],"have":[97],"empirically":[100],"set":[101],"each":[102,192],"time.":[103],"In":[104,257],"this":[105],"paper,":[106],"we":[107,125,225],"take":[108],"policy":[110],"decompose":[112],"complex":[114],"into":[116],"multiple":[117],"learning":[118,130,167,201,273],"modules":[119],"reinforcement":[122,166,200,272],"learning.":[123],"Specifically,":[124],"propose":[126],"three-layer":[128],"framework":[131,261],"consists":[133],"basic-level,":[136],"middle-level":[137,162],"top-level":[139,196],"layers.":[140],"At":[141,160,194],"basic":[143],"layer,":[144,163,197],"only":[145],"two":[146],"base":[147],"i.e.":[149],"target":[150,218],"collision":[152],"avoidance":[153],"output":[157],"actions.":[159],"hierarchical":[165],"approach":[168,202],"train":[172],"agent":[174],"automatically":[176],"selects":[177],"those":[178],"their":[181],"environmental":[185],"changes":[186],"will":[188],"deployed":[190],"at":[191,246],"joint.":[193],"multi-agent":[199],"trains":[203],"all":[204],"joints":[206],"high-level":[208],"collaborative":[209],"accomplish":[212],"actions":[213,242],"tracking":[216],"avoiding":[220,247,252],"obstacles.":[221],"With":[222],"simulation":[223],"experiments,":[224],"compare":[226],"method":[229,233,238],"baseline":[232],"find":[235],"our":[237],"effectively":[239],"produces":[240],"superior":[241],"better":[245],"obstacles,":[248],"handling":[249],"self-collisions,":[250],"singularities":[253],"addition,":[258],"possesses":[262],"higher":[263],"training":[264],"efficiency":[265],"while":[266],"leveraging":[267],"generalization":[269],"ability":[270],"improving":[278],"safety":[279],"interpretability.":[281]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}