{"id":"https://openalex.org/W4221116293","doi":"https://doi.org/10.1109/sii52469.2022.9708850","title":"Variationally Autoencoded Dynamic Policy Programming for Robotic Cloth Manipulation Planning based on Raw Images","display_name":"Variationally Autoencoded Dynamic Policy Programming for Robotic Cloth Manipulation Planning based on Raw Images","publication_year":2022,"publication_date":"2022-01-09","ids":{"openalex":"https://openalex.org/W4221116293","doi":"https://doi.org/10.1109/sii52469.2022.9708850"},"language":"en","primary_location":{"id":"doi:10.1109/sii52469.2022.9708850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii52469.2022.9708850","pdf_url":null,"source":{"id":"https://openalex.org/S4363605592","display_name":"2022 IEEE/SICE International Symposium on System Integration (SII)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/SICE International Symposium on System Integration (SII)","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/A5056162412","display_name":"Yoshihisa Tsurumine","orcid":"https://orcid.org/0000-0002-1514-1135"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihisa Tsurumine","raw_affiliation_strings":["Nara Institute of Science and Technology,Department of Science and Technology Graduate School of Science and Technology,Nara,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Department of Science and Technology Graduate School of Science and Technology,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":["Nara Institute of Science and Technology,Department of Science and Technology Graduate School of Science and Technology,Nara,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Department of Science and Technology Graduate School of Science and Technology,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4153,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55276968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"416","last_page":"421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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":0.9980999827384949,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9921000003814697,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9894000291824341,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7898007035255432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7282474637031555},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6978888511657715},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6903420090675354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6116812229156494},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6070268154144287},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5480116605758667},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5394203662872314},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5371307730674744},{"id":"https://openalex.org/keywords/folding","display_name":"Folding (DSP implementation)","score":0.47609269618988037},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4697055518627167},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.44893795251846313},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4449616074562073},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.404754638671875},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3793797194957733},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.31880632042884827},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2119351327419281},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16073349118232727},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14285922050476074},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12351563572883606}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7898007035255432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282474637031555},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6978888511657715},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6903420090675354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116812229156494},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6070268154144287},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5480116605758667},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5394203662872314},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5371307730674744},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.47609269618988037},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4697055518627167},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44893795251846313},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4449616074562073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.404754638671875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3793797194957733},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.31880632042884827},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2119351327419281},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16073349118232727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14285922050476074},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12351563572883606},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii52469.2022.9708850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii52469.2022.9708850","pdf_url":null,"source":{"id":"https://openalex.org/S4363605592","display_name":"2022 IEEE/SICE International Symposium on System Integration (SII)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1488001421","https://openalex.org/W1808898315","https://openalex.org/W1959608418","https://openalex.org/W1977655452","https://openalex.org/W2130179125","https://openalex.org/W2281096776","https://openalex.org/W2558355904","https://openalex.org/W2750248772","https://openalex.org/W2751471435","https://openalex.org/W2789645218","https://openalex.org/W2900582619","https://openalex.org/W2938421504","https://openalex.org/W2952629144","https://openalex.org/W2962901215","https://openalex.org/W3012523854","https://openalex.org/W4214717370","https://openalex.org/W4298206671","https://openalex.org/W6640963894","https://openalex.org/W6679486095","https://openalex.org/W6682330108","https://openalex.org/W6728925229","https://openalex.org/W6743839283","https://openalex.org/W6744063608","https://openalex.org/W6751494529","https://openalex.org/W6761822005"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W1589140671","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"This":[0,27],"paper":[1],"proposes":[2],"a":[3,40,98,102,115],"framework":[4,28],"for":[5,67,73],"model":[6],"learning":[7],"and":[8,19,50,72,117],"action":[9,90],"planning":[10],"of":[11,42,62,101],"cloth":[12],"manipulation":[13],"tasks":[14],"based":[15],"on":[16],"such":[17],"high-dimensional":[18],"redundant":[20],"sensor":[21],"observations":[22],"as":[23],"raw":[24],"pixel":[25],"images.":[26],"is":[29,39,58,82],"called":[30],"the":[31,68,74,85,128],"variationally":[32,43],"autoencoded":[33,44],"dynamic":[34,51],"policy":[35,52],"programming":[36,53],"(VAE-DPP),":[37],"which":[38,60],"combination":[41],"hidden":[45,75],"Markov":[46,76],"decision":[47,77],"process":[48,78],"(VAE-HMDP)":[49],"(DPP).":[54],"At":[55],"first,":[56],"VAE-HMDP":[57],"learned,":[59],"consists":[61],"two":[63,109],"disentangled":[64],"latent":[65],"spaces:":[66],"image":[69],"with":[70],"VAE":[71],"(HMDP).":[79],"Then":[80],"DPP":[81],"applied":[83,106],"to":[84,88,108],"learned":[86],"HMDP":[87],"plan":[89],"sequences":[91],"efficiently.":[92],"After":[93],"investigating":[94],"its":[95],"effectiveness":[96],"through":[97],"simple":[99],"simulation":[100],"toy":[103],"problem,":[104],"we":[105],"VAE-DPP":[107],"robotic":[110],"cloth-folding":[111],"tasks:":[112],"(1)":[113],"folding":[114,119,130],"handkerchief":[116],"(2)":[118],"trousers.":[120],"We":[121],"successfully":[122],"generated":[123],"appropriate":[124],"actions":[125],"that":[126],"reached":[127],"target":[129],"state.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}