{"id":"https://openalex.org/W4396542830","doi":"https://doi.org/10.1109/mhs59931.2023.10510085","title":"Deformable Object Manipulation Using Human Demonstration Enhanced Deep Deterministic Policy Gradient","display_name":"Deformable Object Manipulation Using Human Demonstration Enhanced Deep Deterministic Policy Gradient","publication_year":2023,"publication_date":"2023-11-20","ids":{"openalex":"https://openalex.org/W4396542830","doi":"https://doi.org/10.1109/mhs59931.2023.10510085"},"language":"en","primary_location":{"id":"doi:10.1109/mhs59931.2023.10510085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mhs59931.2023.10510085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Symposium on Micro-NanoMehatronics and Human Science (MHS)","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/A5041446903","display_name":"Zihao Dong","orcid":"https://orcid.org/0000-0002-5927-7974"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zihao Dong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066790771","display_name":"Jian Huang","orcid":"https://orcid.org/0000-0002-6267-8824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101988619","display_name":"Haoyuan Wang","orcid":"https://orcid.org/0000-0003-4392-1435"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyuan Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102728060","display_name":"Bo Yang","orcid":"https://orcid.org/0000-0003-1766-4025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008740867","display_name":"Dongrui Wu","orcid":"https://orcid.org/0000-0002-7153-9703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongrui Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100878097","display_name":"Yaonan Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaonan Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067104092","display_name":"Yasuhisa Hasegawa","orcid":"https://orcid.org/0000-0001-9917-098X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasuhisa Hasegawa","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5041446903"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29027405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9987999796867371,"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":0.9987999796867371,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9976999759674072,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.988099992275238,"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/computer-science","display_name":"Computer science","score":0.6891764998435974},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5311058163642883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49603375792503357},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4073522686958313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891764998435974},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5311058163642883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49603375792503357},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4073522686958313}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mhs59931.2023.10510085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mhs59931.2023.10510085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Symposium on Micro-NanoMehatronics and Human Science (MHS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1969865247","https://openalex.org/W1982920857","https://openalex.org/W2005503440","https://openalex.org/W2137549137","https://openalex.org/W2560940104","https://openalex.org/W2736750746","https://openalex.org/W2741122588","https://openalex.org/W2767221003","https://openalex.org/W2900582619","https://openalex.org/W2990499011","https://openalex.org/W3040477237","https://openalex.org/W3091544428","https://openalex.org/W6752818329"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"demonstrated":[4],"potential":[5],"in":[6,66],"addressing":[7],"deformable":[8,56],"object":[9,57],"manipulation":[10,58,71],"problems.":[11],"However,":[12],"significant":[13],"challenges":[14],"remain":[15],"regarding":[16],"the":[17,23,55,62,99,107,111,116,127,130,156,159,169,178],"complexity":[18,69],"of":[19,26,64,70,98,129,137,158],"these":[20],"tasks":[21,72],"and":[22,38,60,81,148,154,168,184],"limited":[24],"efficiency":[25],"policy":[27,50,79],"initialization":[28],"with":[29],"human":[30,45],"demonstrations":[31,46],"(HD),":[32],"which":[33,150],"may":[34],"necessitate":[35],"substantial":[36],"data":[37],"time":[39],"for":[40,92],"convergence.":[41],"This":[42],"paper":[43],"proposes":[44],"enhanced":[47],"deep":[48],"deterministic":[49],"gradients":[51],"(HDE-DDPG)":[52],"to":[53,106,109,118,122],"simplify":[54],"problem":[59],"maximize":[61],"benefits":[63],"HD":[65,123,153],"RL.":[67],"The":[68,96],"is":[73,101,132,144],"reduced":[74],"by":[75],"carrying":[76],"out":[77],"conditional":[78],"training":[80,115,128,157,180],"utilizing":[82],"a":[83,135],"fuzzy":[84],"classification":[85],"system":[86],"known":[87],"as":[88,104],"high-dimensional":[89],"Takagi\u2013Sugeno\u2013Kang":[90],"(HTSK)":[91],"grasp":[93],"point":[94],"selection.":[95],"output":[97],"HTSK":[100],"then":[102],"fed":[103],"input":[105],"actor":[108],"determine":[110],"placement":[112],"position.":[113],"By":[114],"critic":[117,131],"assign":[119],"higher":[120],"scores":[121],"actions":[124],"during":[125],"pretraining,":[126],"accelerated.":[133],"As":[134],"result":[136],"an":[138],"improved":[139],"critic,":[140],"behavior":[141],"cloning":[142],"(BC)":[143],"used":[145],"more":[146],"frequently":[147],"appropriately,":[149],"fully":[151],"exploits":[152],"accelerates":[155],"entire":[160],"system.":[161],"HDE-DDPG":[162],"was":[163],"evaluated":[164],"through":[165],"ablation":[166],"experiments,":[167],"results":[170],"demonstrate":[171],"that":[172],"our":[173],"method":[174],"significantly":[175],"speeds":[176],"up":[177],"agent's":[179],"while":[181],"achieving":[182],"superior":[183],"consistent":[185],"performance.":[186]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}