{"id":"https://openalex.org/W4377704939","doi":"https://doi.org/10.1109/icara56516.2023.10125281","title":"Hierarchical Reinforcement Learning for In-hand Robotic Manipulation Using Davenport Chained Rotations","display_name":"Hierarchical Reinforcement Learning for In-hand Robotic Manipulation Using Davenport Chained Rotations","publication_year":2023,"publication_date":"2023-02-10","ids":{"openalex":"https://openalex.org/W4377704939","doi":"https://doi.org/10.1109/icara56516.2023.10125281"},"language":"en","primary_location":{"id":"doi:10.1109/icara56516.2023.10125281","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icara56516.2023.10125281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 9th International Conference on Automation, Robotics and Applications (ICARA)","raw_type":"proceedings-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/A5005226665","display_name":"Francisco Rold\u00e1n S\u00e1nchez","orcid":"https://orcid.org/0009-0001-5954-0971"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Francisco Roldan Sanchez","raw_affiliation_strings":["Dublin City University,Insight Centre for Data Analytics,Dublin,Ireland","Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Dublin City University,Insight Centre for Data Analytics,Dublin,Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367092","display_name":"Qiang Wang","orcid":"https://orcid.org/0009-0008-2473-710X"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["University College Dublin,Dublin,Ireland","University College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"University College Dublin,Dublin,Ireland","institution_ids":["https://openalex.org/I100930933"]},{"raw_affiliation_string":"University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074319083","display_name":"David C\u00f3rdova Bulens","orcid":"https://orcid.org/0000-0003-2466-7179"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"David Cordova Bulens","raw_affiliation_strings":["University College Dublin,Dublin,Ireland","University College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"University College Dublin,Dublin,Ireland","institution_ids":["https://openalex.org/I100930933"]},{"raw_affiliation_string":"University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073924795","display_name":"Kevin McGuinness","orcid":"https://orcid.org/0000-0003-1336-6477"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Kevin McGuinness","raw_affiliation_strings":["Dublin City University,Insight Centre for Data Analytics,Dublin,Ireland","Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Dublin City University,Insight Centre for Data Analytics,Dublin,Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013317847","display_name":"Stephen J. Redmond","orcid":"https://orcid.org/0000-0002-2630-5449"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]},{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Stephen J. Redmond","raw_affiliation_strings":["University College Dublin,Insight Centre for Data Analytics,Dublin,Ireland","Insight Centre for Data Analytics, University College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"University College Dublin,Insight Centre for Data Analytics,Dublin,Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Insight Centre for Data Analytics, University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106498523","display_name":"Noel E. O\u2019Connor","orcid":"https://orcid.org/0000-0002-4033-9135"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Noel E. O'Connor","raw_affiliation_strings":["Dublin City University,Insight Centre for Data Analytics,Dublin,Ireland","Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Dublin City University,Insight Centre for Data Analytics,Dublin,Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005226665"],"corresponding_institution_ids":["https://openalex.org/I42934936"],"apc_list":null,"apc_paid":null,"fwci":0.1876,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43515379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"40","issue":null,"first_page":"160","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8107694983482361},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.7765923738479614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7430709600448608},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.6075296998023987},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6015784740447998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5673437118530273},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5435656309127808},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4808300733566284},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4470481872558594},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4406300485134125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38910508155822754},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32401853799819946},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1298472285270691},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.11164876818656921}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8107694983482361},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.7765923738479614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430709600448608},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.6075296998023987},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6015784740447998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5673437118530273},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5435656309127808},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4808300733566284},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4470481872558594},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4406300485134125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38910508155822754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32401853799819946},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1298472285270691},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.11164876818656921},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icara56516.2023.10125281","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icara56516.2023.10125281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 9th International Conference on Automation, Robotics and Applications (ICARA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2632164605","display_name":null,"funder_award_id":"SFI/12/RC/2289_P2","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G630502101","display_name":null,"funder_award_id":"202006540003","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W819707303","https://openalex.org/W1989002554","https://openalex.org/W2060914855","https://openalex.org/W2070629246","https://openalex.org/W2078765782","https://openalex.org/W2081668151","https://openalex.org/W2109572794","https://openalex.org/W2161395589","https://openalex.org/W2166164107","https://openalex.org/W2208932597","https://openalex.org/W2789008106","https://openalex.org/W2950471160","https://openalex.org/W2963864421","https://openalex.org/W3005595008","https://openalex.org/W3043057128","https://openalex.org/W3091673899","https://openalex.org/W3107359931","https://openalex.org/W3174167970","https://openalex.org/W3205321526","https://openalex.org/W4283784507","https://openalex.org/W4287714048","https://openalex.org/W4293872189","https://openalex.org/W4300799055","https://openalex.org/W6684921986","https://openalex.org/W6696324988"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W2139970489","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3089780453","https://openalex.org/W3148904318","https://openalex.org/W3012552522"],"abstract_inverted_index":{"End-to-end":[0],"reinforcement":[1],"learning":[2,72,129],"techniques":[3],"are":[4,184],"among":[5],"the":[6,15,35,67,71,77,90,132,144,162,195,203,226],"most":[7,196,227],"successful":[8],"methods":[9,116],"for":[10],"robotic":[11,152],"manipulation":[12,55],"tasks.":[13],"However,":[14],"training":[16,80],"time":[17],"required":[18,81],"to":[19,44,53,60,82,96,202],"find":[20,170],"a":[21,103,106,150,156,208],"good":[22],"policy":[23],"capable":[24],"of":[25,50,70,79,92,105,109,147,161,188,191,218],"solving":[26],"complex":[27,98,197],"tasks":[28,56],"is":[29,179],"prohibitively":[30],"large.":[31],"Therefore,":[32],"depending":[33],"on":[34,194,225],"computing":[36,182],"resources":[37,183],"available,":[38],"it":[39],"might":[40],"not":[41],"be":[42,61,119],"feasible":[43],"use":[45,49,91],"such":[46],"techniques.":[47],"The":[48],"domain":[51],"knowledge":[52],"decompose":[54,97],"into":[57,102,176],"primitive":[58,163],"skills,":[59],"performed":[62],"in":[63,139,149,159,212],"sequence,":[64],"could":[65],"reduce":[66,76],"overall":[68,123],"complexity":[69],"problem,":[73],"and":[74,216,223],"hence":[75],"amount":[78,146],"achieve":[83],"dexterity.":[84],"In":[85],"this":[86,128],"paper,":[87],"we":[88,169],"propose":[89],"Davenport":[93],"chained":[94],"rotations":[95,175,178,199],"3D":[99,174,198],"rotation":[100,112],"goals":[101],"concatenation":[104],"smaller":[107],"set":[108],"more":[110],"simple":[111,228],"skills.":[113],"State-of-the-art":[114],"reinforcement-learning-based":[115],"can":[117],"then":[118],"trained":[120,138,211],"using":[121,143],"less":[122],"simulated":[124,151],"experience.":[125],"We":[126],"compare":[127],"approach":[130,210],"with":[131,200],"popular":[133],"Hindsight":[134],"Experience":[135],"Replay":[136],"method,":[137],"an":[140,213],"end-to-end":[141,214],"fashion":[142],"same":[145],"experience":[148],"hand":[153],"environment.":[154],"Despite":[155],"general":[157],"decrease":[158],"performance":[160],"skills":[164],"when":[165,181],"being":[166],"sequentially":[167],"executed,":[168],"that":[171],"decomposing":[172],"arbitrary":[173],"elementary":[177],"beneficial":[180],"limited,":[185],"obtaining":[186],"increases":[187,217],"success":[189,204,219],"rates":[190,205,220],"approximately":[192],"10%":[193],"respect":[201],"obtained":[206],"by":[207],"HER-based":[209],"fashion,":[215],"between":[221],"20%":[222],"40%":[224],"rotations.":[229]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
