{"id":"https://openalex.org/W4389667645","doi":"https://doi.org/10.1109/iros55552.2023.10341629","title":"Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration","display_name":"Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667645","doi":"https://doi.org/10.1109/iros55552.2023.10341629"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/368410439/Nonprehensile_Planar_Manipulation_FERRANDIS_DOA30062023_AFV_CC_BY.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104265869","display_name":"Juan Del Aguila Ferrandis","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Juan Del Aguila Ferrandis","raw_affiliation_strings":["School of Informatics, The University of Edinburgh,Edinburgh,UK","School of Informatics, The University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, The University of Edinburgh,Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090546247","display_name":"Jo\u00e3o Moura","orcid":"https://orcid.org/0000-0002-1812-7857"},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Moura","raw_affiliation_strings":["School of Informatics, The University of Edinburgh,Edinburgh,UK","School of Informatics, The University of Edinburgh, Edinburgh, UK","The Alan Turing Institute, London, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, The University of Edinburgh,Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Alan Turing Institute, London, U.K","institution_ids":["https://openalex.org/I4210128584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069715982","display_name":"Sethu Vijayakumar","orcid":"https://orcid.org/0000-0003-0649-7241"},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sethu Vijayakumar","raw_affiliation_strings":["School of Informatics, The University of Edinburgh,Edinburgh,UK","School of Informatics, The University of Edinburgh, Edinburgh, UK","The Alan Turing Institute, London, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, The University of Edinburgh,Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Alan Turing Institute, London, U.K","institution_ids":["https://openalex.org/I4210128584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.7673,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.98931169,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5606","last_page":"5613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9958999752998352,"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":0.7323509454727173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7212808132171631},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.690638542175293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5856066942214966},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5753438472747803},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.525455117225647},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.41591787338256836},{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.4158411920070648},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11685830354690552}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7323509454727173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7212808132171631},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.690638542175293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5856066942214966},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5753438472747803},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.525455117225647},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.41591787338256836},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.4158411920070648},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11685830354690552},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iros55552.2023.10341629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/b3044c6b-1694-4b31-aa68-e8850b8f118f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/368410439/Nonprehensile_Planar_Manipulation_FERRANDIS_DOA30062023_AFV_CC_BY.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.ed.ac.uk:publications/b3044c6b-1694-4b31-aa68-e8850b8f118f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b3044c6b-1694-4b31-aa68-e8850b8f118f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/b3044c6b-1694-4b31-aa68-e8850b8f118f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/368410439/Nonprehensile_Planar_Manipulation_FERRANDIS_DOA30062023_AFV_CC_BY.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1583837637","https://openalex.org/W1635062593","https://openalex.org/W2010072864","https://openalex.org/W2050708324","https://openalex.org/W2726187156","https://openalex.org/W2729705546","https://openalex.org/W2736601468","https://openalex.org/W2767050701","https://openalex.org/W2962867039","https://openalex.org/W2963677339","https://openalex.org/W2963892386","https://openalex.org/W2980820015","https://openalex.org/W2990747716","https://openalex.org/W2997902164","https://openalex.org/W3024987186","https://openalex.org/W3101442004","https://openalex.org/W3203017576","https://openalex.org/W3216772467","https://openalex.org/W4205430897","https://openalex.org/W4214902667","https://openalex.org/W4298857966","https://openalex.org/W4383097376","https://openalex.org/W4383097672","https://openalex.org/W6627932998","https://openalex.org/W6747473740","https://openalex.org/W6800425027","https://openalex.org/W6804601995","https://openalex.org/W6846211847"],"related_works":["https://openalex.org/W587013945","https://openalex.org/W4288862394","https://openalex.org/W1485310626","https://openalex.org/W4292915238","https://openalex.org/W4285553839","https://openalex.org/W3011477119","https://openalex.org/W2371440471","https://openalex.org/W2075135955","https://openalex.org/W3135136999","https://openalex.org/W2548084816"],"abstract_inverted_index":{"Developing":[0],"robot":[1,51,105,188,194],"controllers":[2],"capable":[3],"of":[4,24,74,92,177],"achieving":[5],"dexterous":[6],"nonprehensile":[7,59],"manipulation,":[8],"such":[9,50,109],"as":[10,110],"pushing":[11,60,133],"an":[12],"object":[13,141],"on":[14],"a":[15,45,120,186],"table,":[16],"is":[17,44],"challenging.":[18],"The":[19],"underactuated":[20],"and":[21,67,106,113,139,145,147,162,165],"hybrid-dynamics":[22,91],"nature":[23],"the":[25,30,34,58,75,89,93,97,104,107,154,175,178,191],"problem,":[26],"further":[27],"complicated":[28],"by":[29],"uncertainty":[31],"resulting":[32],"from":[33,96],"frictional":[35],"interactions,":[36],"requires":[37],"sophisticated":[38],"control":[39],"behaviors.":[40],"Reinforcement":[41],"Learning":[42],"(RL)":[43],"powerful":[46],"framework":[47],"for":[48,136],"developing":[49],"controllers.":[52],"However,":[53],"previous":[54],"RL":[55,134],"literature":[56],"addressing":[57],"task":[61],"achieves":[62],"low":[63],"accuracy,":[64],"non-smooth":[65],"trajectories,":[66],"only":[68],"simple":[69],"motions,":[70],"i.e.":[71,143],"without":[72],"rotation":[73],"manipulated":[76],"object.":[77],"We":[78,151],"conjecture":[79],"that":[80,153],"previously":[81],"used":[82],"unimodal":[83],"exploration":[84,122],"strategies":[85],"fail":[86],"to":[87,130,159,167,185],"capture":[88],"inherent":[90],"task,":[94],"arising":[95],"different":[98],"possible":[99],"contact":[100],"interaction":[101],"modes":[102],"between":[103],"object,":[108],"sticking,":[111],"sliding,":[112],"separation.":[114],"In":[115],"this":[116],"work,":[117],"we":[118,173],"propose":[119],"multimodal":[121],"approach":[123],"through":[124],"categorical":[125],"distributions,":[126],"which":[127],"enables":[128],"us":[129],"train":[131],"planar":[132],"policies":[135,156],"arbitrary":[137],"starting":[138],"target":[140],"poses,":[142],"positions":[144],"orientations,":[146],"with":[148,169],"improved":[149],"accuracy.":[150],"show":[152],"learned":[155,179],"are":[157],"robust":[158],"external":[160],"disturbances":[161],"observation":[163],"noise,":[164],"scale":[166],"tasks":[168],"multiple":[170],"pushers.":[171],"Furthermore,":[172],"validate":[174],"transferability":[176],"policies,":[180],"trained":[181],"entirely":[182],"in":[183],"simulation,":[184],"physical":[187],"hardware":[189],"using":[190],"KUKA":[192],"iiwa":[193],"arm.":[195],"See":[196],"our":[197],"supplemental":[198],"video:":[199],"https://youtu.be/vTdvalmgrk4.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}