{"id":"https://openalex.org/W2965014427","doi":"https://doi.org/10.1109/urai.2019.8768699","title":"End-to-end robot manipulation using demonstration-guided goal strategie","display_name":"End-to-end robot manipulation using demonstration-guided goal strategie","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2965014427","doi":"https://doi.org/10.1109/urai.2019.8768699","mag":"2965014427"},"language":"en","primary_location":{"id":"doi:10.1109/urai.2019.8768699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/urai.2019.8768699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 16th International Conference on Ubiquitous Robots (UR)","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/A5005874280","display_name":"Cheol-Hui Min","orcid":"https://orcid.org/0000-0002-2275-1564"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Cheol-Hui Min","raw_affiliation_strings":["School of Mechanical Eng., Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Eng., Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013838439","display_name":"Jae-Bok Song","orcid":"https://orcid.org/0000-0002-5818-1938"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Bok Song","raw_affiliation_strings":["School of Mechanical Eng., Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Eng., Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005874280"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08050549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"164"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9969000220298767,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.8775926232337952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628806829452515},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6471577882766724},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5113336443901062},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5080678462982178},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4857635796070099},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44181787967681885},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.43529215455055237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4119929075241089},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3666123151779175}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.8775926232337952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628806829452515},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6471577882766724},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5113336443901062},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5080678462982178},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4857635796070099},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44181787967681885},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.43529215455055237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4119929075241089},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3666123151779175},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/urai.2019.8768699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/urai.2019.8768699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 16th International Conference on Ubiquitous Robots (UR)","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":33,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W567721252","https://openalex.org/W1191599655","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2173248099","https://openalex.org/W2342662072","https://openalex.org/W2342840547","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2754517384","https://openalex.org/W2766614170","https://openalex.org/W2787938642","https://openalex.org/W2963616477","https://openalex.org/W2963641140","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964161785","https://openalex.org/W2964198579","https://openalex.org/W4300799055","https://openalex.org/W6616173779","https://openalex.org/W6627932998","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6691861496","https://openalex.org/W6704559304","https://openalex.org/W6704571135","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6744123322","https://openalex.org/W6745744936","https://openalex.org/W6748839928"],"related_works":["https://openalex.org/W2890406131","https://openalex.org/W2804672169","https://openalex.org/W3158799570","https://openalex.org/W4226449863","https://openalex.org/W2127107099","https://openalex.org/W3188986767","https://openalex.org/W2962686687","https://openalex.org/W3152815381","https://openalex.org/W2353270753","https://openalex.org/W2891470378"],"abstract_inverted_index":{"In":[0],"deep":[1],"reinforcement":[2],"learning,":[3],"finding":[4],"the":[5,21,25,35,69,96,103,109,113],"optimal":[6,26],"manipulation":[7,54,70],"policy":[8,71,110],"of":[9,34,72,117],"a":[10,57,65,73,76,118],"multi-DOF":[11],"manipulator":[12,74,120],"in":[13,75,126,130],"3D":[14],"space":[15],"requires":[16,31],"intricate":[17],"reward":[18,29,36,59,78,128],"shaping":[19,30],"for":[20,102],"agent":[22],"to":[23,45,51],"find":[24],"policy.":[27,104],"However,":[28],"cumbersome":[32],"optimization":[33],"function":[37],"based":[38],"on":[39,42],"prior":[40],"knowledge":[41],"robotic":[43],"tasks":[44],"achieve.":[46],"This":[47],"makes":[48],"it":[49],"desirable":[50],"learn":[52],"various":[53],"policies":[55],"with":[56,89],"simple":[58],"function.In":[60],"this":[61,81],"study,":[62],"we":[63],"propose":[64],"method":[66],"that":[67,99,108],"learns":[68],"sparse":[77,127],"setting.":[79],"To":[80],"end,":[82],"Hindsight":[83],"Experience":[84],"Replay":[85],"(HER)":[86],"is":[87,106],"combined":[88],"Twin":[90],"Delayed":[91],"DDPG":[92],"(TD3)":[93],"by":[94],"applying":[95],"goal":[97],"strategy":[98],"incorporates":[100],"demonstrations":[101],"It":[105],"shown":[107],"can":[111],"estimate":[112],"joint":[114],"control":[115],"command":[116],"7-DoF":[119],"from":[121],"raw":[122],"RGB":[123],"video":[124],"inputs":[125],"setting":[129],"an":[131],"end-to-end":[132],"manner.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
