{"id":"https://openalex.org/W4200298755","doi":"https://doi.org/10.1109/ictc52510.2021.9620901","title":"Reward Shaping to Learn Natural Object Manipulation With an Anthropomorphic Robotic Hand and Hand Pose Priors via On-Policy Reinforcement Learning","display_name":"Reward Shaping to Learn Natural Object Manipulation With an Anthropomorphic Robotic Hand and Hand Pose Priors via On-Policy Reinforcement Learning","publication_year":2021,"publication_date":"2021-10-20","ids":{"openalex":"https://openalex.org/W4200298755","doi":"https://doi.org/10.1109/ictc52510.2021.9620901"},"language":"en","primary_location":{"id":"doi:10.1109/ictc52510.2021.9620901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc52510.2021.9620901","pdf_url":null,"source":{"id":"https://openalex.org/S4363607766","display_name":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","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":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","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/A5084726485","display_name":"Patricio Rivera","orcid":"https://orcid.org/0000-0001-6440-5478"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Patricio Rivera","raw_affiliation_strings":["Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075510117","display_name":"Ji-Heon Oh","orcid":"https://orcid.org/0000-0003-0488-116X"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiheon Oh","raw_affiliation_strings":["Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017083347","display_name":"Edwin Valarezo A\u00f1azco","orcid":"https://orcid.org/0000-0003-0077-8528"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Edwin Valarezo","raw_affiliation_strings":["Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053483057","display_name":"Gahyeon Ryu","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gahyeon Ryu","raw_affiliation_strings":["Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056250040","display_name":"Hwanseok Jung","orcid":"https://orcid.org/0000-0003-2694-2525"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwanseok Jung","raw_affiliation_strings":["Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038791367","display_name":"Jin Hyunk Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jin Hyunk Lee","raw_affiliation_strings":["Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078328765","display_name":"Jin Gyun Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jin Gyun Jeong","raw_affiliation_strings":["Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102935360","display_name":"Tae\u2010Seong Kim","orcid":"https://orcid.org/0009-0008-2751-3267"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Seong Kim","raw_affiliation_strings":["Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Information Convergence Engineering, Kyung Hee University, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5084726485"],"corresponding_institution_ids":["https://openalex.org/I35928602"],"apc_list":null,"apc_paid":null,"fwci":0.8709,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6598597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"167","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9879000186920166,"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":0.7768237590789795},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7380424737930298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7295380234718323},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6376854181289673},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6115034222602844},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5143433809280396},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4304755926132202},{"id":"https://openalex.org/keywords/degrees-of-freedom","display_name":"Degrees of freedom (physics and chemistry)","score":0.4176666736602783},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41253501176834106},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35631170868873596},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35201597213745117},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34902316331863403},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13767355680465698}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7768237590789795},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7380424737930298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7295380234718323},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6376854181289673},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6115034222602844},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5143433809280396},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4304755926132202},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.4176666736602783},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41253501176834106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35631170868873596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35201597213745117},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34902316331863403},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13767355680465698},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc52510.2021.9620901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc52510.2021.9620901","pdf_url":null,"source":{"id":"https://openalex.org/S4363607766","display_name":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","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":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5233055659","display_name":null,"funder_award_id":"NRF-2019R1A2C1003713","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2130801532","https://openalex.org/W2158782408","https://openalex.org/W2290104316","https://openalex.org/W2342840547","https://openalex.org/W2575705757","https://openalex.org/W2736601468","https://openalex.org/W2740210681","https://openalex.org/W2741122588","https://openalex.org/W2789805345","https://openalex.org/W2791846357","https://openalex.org/W2908466110","https://openalex.org/W2945136467","https://openalex.org/W2963170432","https://openalex.org/W2963321092","https://openalex.org/W2963403593","https://openalex.org/W2963411833","https://openalex.org/W2963713397","https://openalex.org/W2968340082","https://openalex.org/W3109929115","https://openalex.org/W6638018090","https://openalex.org/W6679257226","https://openalex.org/W6696380822","https://openalex.org/W6704559304","https://openalex.org/W6741002519","https://openalex.org/W6741832191","https://openalex.org/W6744563498","https://openalex.org/W6756293349","https://openalex.org/W6757432186","https://openalex.org/W6762006211"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W2085259108","https://openalex.org/W3041320102","https://openalex.org/W2111669074","https://openalex.org/W3123087812","https://openalex.org/W2063076820"],"abstract_inverted_index":{"A":[0],"key":[1],"challenge":[2],"in":[3],"reinforcement":[4],"learning":[5,21,63,167],"(RL)":[6],"for":[7,44,62,83,96,122,151,166],"robot":[8,72],"manipulation":[9,86],"is":[10,39],"to":[11,22,75,129],"provide":[12],"a":[13,59,64,80,169],"reward":[14,60,82,114],"function":[15,61],"that":[16,138,150],"allows":[17,168],"reliable":[18],"and":[19,36,41,124,160],"stable":[20],"achieve":[23],"their":[24,37],"goals":[25],"while":[26],"interacting":[27],"with":[28,49,111,132],"the":[29,67,71,100,104,116,133,146,152],"environment.":[30],"Unfortunately,":[31],"rewards":[32],"are":[33],"usually":[34],"task-specific,":[35],"engineering":[38],"challenging":[40],"laborious":[42],"especially":[43],"an":[45,156],"anthropomorphic":[46],"robotic":[47],"hand":[48,73,91,163,172],"high":[50],"degrees":[51],"of":[52,69,93,103],"freedom.":[53],"In":[54],"this":[55],"work,":[56],"we":[57],"consider":[58],"policy":[65,109],"under":[66],"constrain":[68],"minimizing":[70],"pose":[74,164],"demonstration":[76],"priors.":[77],"We":[78,136],"propose":[79],"shaped":[81],"obtaining":[84],"efficient":[85],"policies":[87],"after":[88],"incorporating":[89,162],"five-fingered":[90],"poses":[92],"grasping":[94,123],"demonstrations":[95],"various":[97],"objects":[98,127,153],"into":[99],"early":[101],"timesteps":[102],"training":[105],"episodes.":[106],"The":[107],"trained":[108],"NPG+SR":[110],"our":[112,139],"proposed":[113],"improves":[115],"average":[117],"success":[118],"rate":[119],"over":[120],"95%":[121],"relocating":[125],"all":[126],"compared":[128],"68%":[130],"obtained":[131],"baseline":[134],"NPG-B.":[135],"noticed":[137],"method":[140],"not":[141],"only":[142],"performs":[143],"better":[144],"but":[145],"qualitative":[147],"results":[148],"indicate":[149],"such":[154],"as":[155],"apple,":[157],"water":[158],"bottle,":[159],"lightbulb":[161],"priors":[165],"more":[170],"natural":[171],"grasping.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-30T09:15:22.047038","created_date":"2025-10-10T00:00:00"}