{"id":"https://openalex.org/W4392248581","doi":"https://doi.org/10.1109/icce59016.2024.10444355","title":"Interactive Robot-Robot Reinforcement Learning for Object Balancing Task","display_name":"Interactive Robot-Robot Reinforcement Learning for Object Balancing Task","publication_year":2024,"publication_date":"2024-01-06","ids":{"openalex":"https://openalex.org/W4392248581","doi":"https://doi.org/10.1109/icce59016.2024.10444355"},"language":"en","primary_location":{"id":"doi:10.1109/icce59016.2024.10444355","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce59016.2024.10444355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Consumer Electronics (ICCE)","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/A5060656385","display_name":"Yewon Kim","orcid":"https://orcid.org/0000-0002-0774-7217"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yewon Kim","raw_affiliation_strings":["Kyungpook National University,the Dept. of Artificial Intelligence,Daegu,South Korea,41566"],"affiliations":[{"raw_affiliation_string":"Kyungpook National University,the Dept. of Artificial Intelligence,Daegu,South Korea,41566","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046609375","display_name":"Haein Jeon","orcid":"https://orcid.org/0000-0002-3113-2191"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Haein Jeon","raw_affiliation_strings":["Kyungpook National University,the Dept. of Artificial Intelligence,Daegu,South Korea,41566"],"affiliations":[{"raw_affiliation_string":"Kyungpook National University,the Dept. of Artificial Intelligence,Daegu,South Korea,41566","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085958723","display_name":"Bo\u2010Yeong Kang","orcid":"https://orcid.org/0000-0002-0546-7457"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bo-Yeong Kang","raw_affiliation_strings":["Kyungpook National University,the Dept. of Robot and Smart System Engineering,Daegu,South Korea,41566"],"affiliations":[{"raw_affiliation_string":"Kyungpook National University,the Dept. of Robot and Smart System Engineering,Daegu,South Korea,41566","institution_ids":["https://openalex.org/I31419693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060656385"],"corresponding_institution_ids":["https://openalex.org/I31419693"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01566854,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9746000170707703,"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":0.9746000170707703,"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/T14011","display_name":"Elevator Systems and Control","score":0.9402999877929688,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9047999978065491,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7986819744110107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7465484738349915},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7200563549995422},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6104561686515808},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6070659160614014},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5159885883331299},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4630013108253479},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4552924931049347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45381683111190796},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4175017774105072},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14526841044425964}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7986819744110107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465484738349915},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7200563549995422},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6104561686515808},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6070659160614014},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5159885883331299},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4630013108253479},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4552924931049347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45381683111190796},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4175017774105072},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14526841044425964},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce59016.2024.10444355","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce59016.2024.10444355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":15,"referenced_works":["https://openalex.org/W2111975591","https://openalex.org/W2160660844","https://openalex.org/W2735700496","https://openalex.org/W2998008599","https://openalex.org/W3028676366","https://openalex.org/W3089853974","https://openalex.org/W3106576492","https://openalex.org/W3185319788","https://openalex.org/W4241519124","https://openalex.org/W4298857966","https://openalex.org/W4378983114","https://openalex.org/W6637967152","https://openalex.org/W6653538868","https://openalex.org/W6676744775","https://openalex.org/W6769609827"],"related_works":["https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W2171912896","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W4220829754","https://openalex.org/W2165180011","https://openalex.org/W2724299411"],"abstract_inverted_index":{"Robots":[0],"with":[1],"machine":[2,18],"learning":[3,19,37,44,151,179],"are":[4],"expanding":[5],"their":[6],"application":[7,147],"fields,":[8],"such":[9],"as":[10,116,155,157],"serving":[11],"robots":[12,21],"and":[13,59,63,85,93,124],"guiding":[14],"robots,":[15],"but":[16],"applying":[17],"to":[20,28,39,82,112,133,166,176,181],"has":[22,76],"a":[23,182],"high":[24],"labor":[25],"cost":[26],"due":[27],"human":[29,41],"intervention.":[30],"This":[31],"paper":[32],"proposes":[33],"interactive":[34],"robot-robot":[35,150],"reinforcement":[36,69],"technology":[38],"minimize":[40],"intervention":[42],"in":[43,80,188],"tasks":[45],"that":[46,75],"successfully":[47],"balance":[48],"objects":[49],"between":[50],"two":[51],"robots.":[52],"In":[53,101],"this":[54],"proposed":[55,122,161],"technique,":[56],"the":[57,98,104,108,113,121,125,138,146,169,178],"teacher":[58],"student":[60,83,109,127],"robot":[61,72,110,128,184],"guide":[62],"learn":[64],"object":[65],"balancing":[66],"based":[67],"on":[68,97],"learning.":[70,159],"Teacher":[71],"teaches":[73,86],"knowledge":[74,171],"not":[77],"been":[78],"learned":[79,170],"advance":[81],"robot,":[84],"more":[87],"effectively":[88],"by":[89,137],"providing":[90],"various":[91,134],"positive":[92],"negative":[94],"text":[95],"feedback":[96],"training":[99,105],"results.":[100],"virtual":[102],"simulations,":[103],"results":[106],"of":[107,120,149],"converge":[111],"optimal":[114],"policy":[115],"an":[117,186,189],"evaluation":[118],"result":[119],"method,":[123],"trained":[126],"performs":[129],"appropriate":[130],"actions":[131],"according":[132],"table":[135],"states":[136],"teacher\u2019s":[139],"random":[140],"action.":[141],"Through":[142],"our":[143],"experimental":[144],"results,":[145],"possibility":[148],"is":[152,174],"verified":[153],"being":[154],"good":[156],"human-robot":[158],"Our":[160],"method":[162],"could":[163],"be":[164],"utilized":[165],"seamlessly":[167],"transfer":[168],"when":[172],"it":[173],"challenging":[175],"apply":[177],"model":[180],"heterogeneous":[183],"or":[185],"agent":[187],"IoT":[190],"environment.":[191]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}