{"id":"https://openalex.org/W3024744364","doi":"https://doi.org/10.1080/01969722.2020.1758466","title":"Robot Position/Force Control in Unknown Environment Using Hybrid Reinforcement Learning","display_name":"Robot Position/Force Control in Unknown Environment Using Hybrid Reinforcement Learning","publication_year":2020,"publication_date":"2020-05-12","ids":{"openalex":"https://openalex.org/W3024744364","doi":"https://doi.org/10.1080/01969722.2020.1758466","mag":"3024744364"},"language":"en","primary_location":{"id":"doi:10.1080/01969722.2020.1758466","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01969722.2020.1758466","pdf_url":null,"source":{"id":"https://openalex.org/S117436046","display_name":"Cybernetics & Systems","issn_l":"0196-9722","issn":["0196-9722","1087-6553"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cybernetics and Systems","raw_type":"journal-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/A5065156490","display_name":"Adolfo Perrusqu\u00eda","orcid":"https://orcid.org/0000-0003-2290-1160"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Centro de Investigaci\u00f3n y de Estudios Avanzados del Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Adolfo Perrusqu\u00eda","raw_affiliation_strings":["Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Mexico City, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Mexico City, Mexico","institution_ids":["https://openalex.org/I68368234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008201587","display_name":"Wen Yu","orcid":"https://orcid.org/0000-0002-9540-7924"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Centro de Investigaci\u00f3n y de Estudios Avanzados del Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Wen Yu","raw_affiliation_strings":["Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Mexico City, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Mexico City, Mexico","institution_ids":["https://openalex.org/I68368234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5008201587"],"corresponding_institution_ids":["https://openalex.org/I68368234"],"apc_list":null,"apc_paid":null,"fwci":2.0032,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.85629533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"51","issue":"4","first_page":"542","last_page":"560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9822999835014343,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9822999835014343,"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":0.8474496603012085},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.7038031816482544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6970294117927551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5837167501449585},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5799819827079773},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5457656979560852},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.49762704968452454},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.49384409189224243},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.48119932413101196},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4593847393989563},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3600870370864868},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34286069869995117},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.33521801233291626},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.21624886989593506}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8474496603012085},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.7038031816482544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6970294117927551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5837167501449585},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5799819827079773},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5457656979560852},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.49762704968452454},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49384409189224243},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.48119932413101196},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4593847393989563},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3600870370864868},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34286069869995117},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.33521801233291626},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.21624886989593506},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/01969722.2020.1758466","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01969722.2020.1758466","pdf_url":null,"source":{"id":"https://openalex.org/S117436046","display_name":"Cybernetics & Systems","issn_l":"0196-9722","issn":["0196-9722","1087-6553"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cybernetics and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1568229137","https://openalex.org/W1626155273","https://openalex.org/W1966086707","https://openalex.org/W1967377907","https://openalex.org/W1991927580","https://openalex.org/W2012279256","https://openalex.org/W2103791569","https://openalex.org/W2113501460","https://openalex.org/W2124815790","https://openalex.org/W2130135496","https://openalex.org/W2141103690","https://openalex.org/W2142163623","https://openalex.org/W2233997862","https://openalex.org/W2240536489","https://openalex.org/W2438255111","https://openalex.org/W2626674277","https://openalex.org/W2633195366","https://openalex.org/W2772589676","https://openalex.org/W2916544653","https://openalex.org/W2943867327","https://openalex.org/W2956146357"],"related_works":["https://openalex.org/W3148138296","https://openalex.org/W4294873804","https://openalex.org/W3153786280","https://openalex.org/W2171128163","https://openalex.org/W2808546214","https://openalex.org/W2643884694","https://openalex.org/W3127551068","https://openalex.org/W2152445738","https://openalex.org/W1987864653","https://openalex.org/W1502839564"],"abstract_inverted_index":{"Robot":[0],"position/force":[1],"control":[2],"provides":[3],"an":[4],"interaction":[5],"scheme":[6],"between":[7],"the":[8,11,14,23,33,37,82,89,93,98,110,116],"robot":[9,114],"and":[10,26,36,53,63,112,115],"environment.":[12,95],"When":[13],"environment":[15],"is":[16,70,102],"unknown,":[17],"learning":[18,24,27,34,38,45,58,61,65,69,75,80,100],"algorithms":[19],"are":[20,29,106],"needed.":[21],"But,":[22],"space":[25],"time":[28],"big.":[30],"To":[31],"balance":[32],"accuracy":[35,62],"time,":[39],"we":[40],"propose":[41],"a":[42],"hybrid":[43,78],"reinforcement":[44,79],"method,":[46],"which":[47],"can":[48],"be":[49],"in":[50,92],"both":[51],"discrete":[52],"continuous":[54],"domains.":[55],"The":[56,67],"discrete-time":[57],"has":[59,73],"poor":[60],"less":[64],"time.":[66],"continuous-time":[68],"slow":[71],"but":[72],"better":[74],"precision.":[76],"This":[77],"learns":[81],"optimal":[83],"contact":[84],"force,":[85],"meanwhile":[86],"it":[87],"minimizes":[88],"position":[90],"error":[91],"unknown":[94],"Convergence":[96],"of":[97],"proposed":[99],"algorithm":[101],"proven.":[103],"Real-time":[104],"experiments":[105],"carried":[107],"out":[108],"using":[109],"pan":[111],"tilt":[113],"force/torque":[117],"sensor.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}