{"id":"https://openalex.org/W2972280472","doi":"https://doi.org/10.1109/codit.2019.8820575","title":"Large space dimension Reinforcement Learning for Robot Position/Force Discrete Control","display_name":"Large space dimension Reinforcement Learning for Robot Position/Force Discrete Control","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2972280472","doi":"https://doi.org/10.1109/codit.2019.8820575","mag":"2972280472"},"language":"en","primary_location":{"id":"doi:10.1109/codit.2019.8820575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit.2019.8820575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"},"type":"conference-paper","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/I4210090124","display_name":"Tecnol\u00f3gico Nacional de M\u00e9xico","ror":"https://ror.org/00davry38","country_code":"MX","type":"government","lineage":["https://openalex.org/I1302736544","https://openalex.org/I4210090124","https://openalex.org/I4405258672"]},{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Adolfo Perrusquia","raw_affiliation_strings":["Departamento de Control Autom??tico, National Polytechnic Institute, Mexico City, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Control Autom??tico, National Polytechnic Institute, Mexico City, Mexico","institution_ids":["https://openalex.org/I4210090124","https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008201587","display_name":"Wen Yu","orcid":"https://orcid.org/0000-0002-9540-7924"},"institutions":[{"id":"https://openalex.org/I4210090124","display_name":"Tecnol\u00f3gico Nacional de M\u00e9xico","ror":"https://ror.org/00davry38","country_code":"MX","type":"government","lineage":["https://openalex.org/I1302736544","https://openalex.org/I4210090124","https://openalex.org/I4405258672"]},{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Wen Yu","raw_affiliation_strings":["Departamento de Control Autom??tico, National Polytechnic Institute, Mexico City, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Control Autom??tico, National Polytechnic Institute, Mexico City, Mexico","institution_ids":["https://openalex.org/I4210090124","https://openalex.org/I59361560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046418413","display_name":"A. Soria","orcid":"https://orcid.org/0000-0002-6310-9527"},"institutions":[{"id":"https://openalex.org/I4210090124","display_name":"Tecnol\u00f3gico Nacional de M\u00e9xico","ror":"https://ror.org/00davry38","country_code":"MX","type":"government","lineage":["https://openalex.org/I1302736544","https://openalex.org/I4210090124","https://openalex.org/I4405258672"]},{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Alberto Soria","raw_affiliation_strings":["Departamento de Control Autom??tico, National Polytechnic Institute, Mexico City, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Control Autom??tico, National Polytechnic Institute, Mexico City, Mexico","institution_ids":["https://openalex.org/I4210090124","https://openalex.org/I59361560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9919999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7263526320457458},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.720146894454956},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.698724091053009},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.6609376668930054},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5844879746437073},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5373889803886414},{"id":"https://openalex.org/keywords/torque","display_name":"Torque","score":0.5146804451942444},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49779748916625977},{"id":"https://openalex.org/keywords/impedance-control","display_name":"Impedance control","score":0.46149858832359314},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.43040382862091064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3159635066986084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3002414405345917},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.20081835985183716},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1594357192516327},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1464938521385193}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7263526320457458},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.720146894454956},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.698724091053009},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.6609376668930054},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5844879746437073},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5373889803886414},{"id":"https://openalex.org/C144171764","wikidata":"https://www.wikidata.org/wiki/Q48103","display_name":"Torque","level":2,"score":0.5146804451942444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49779748916625977},{"id":"https://openalex.org/C2777984285","wikidata":"https://www.wikidata.org/wiki/Q17098134","display_name":"Impedance control","level":3,"score":0.46149858832359314},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.43040382862091064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3159635066986084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3002414405345917},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.20081835985183716},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1594357192516327},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1464938521385193},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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:10.1109/codit.2019.8820575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit.2019.8820575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W109339162","https://openalex.org/W1544101230","https://openalex.org/W1593932305","https://openalex.org/W1626155273","https://openalex.org/W1966086707","https://openalex.org/W1972085072","https://openalex.org/W2011430131","https://openalex.org/W2012279256","https://openalex.org/W2029234750","https://openalex.org/W2108974199","https://openalex.org/W2120982017","https://openalex.org/W2121863487","https://openalex.org/W2124815790","https://openalex.org/W2133378540","https://openalex.org/W2141103690","https://openalex.org/W2152161277","https://openalex.org/W2169982856","https://openalex.org/W2170545573","https://openalex.org/W2438255111","https://openalex.org/W2576544115","https://openalex.org/W2623785075","https://openalex.org/W2765352751","https://openalex.org/W4214717370","https://openalex.org/W4256686585","https://openalex.org/W6632725942","https://openalex.org/W6678616629","https://openalex.org/W6731815454"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"In":[0],"this":[1,93],"work":[2],"a":[3,14,61,95,111,122],"large":[4],"space":[5],"dimension":[6],"reinforcement":[7],"learning":[8],"(RL)":[9],"approximation":[10],"is":[11,32,43,79],"developed":[12],"for":[13,65],"Discrete":[15],"Impedance":[16],"Position/Force":[17],"control":[18,39],"of":[19,37,63,89,114],"robot":[20,120],"manipulators":[21],"that":[22],"interacts":[23],"with":[24],"an":[25],"unknown":[26],"environment":[27,91],"model.":[28],"The":[29,41,69],"Q-value":[30,67],"function":[31],"designed":[33],"in":[34],"the":[35,55,66,74,82,90,102],"sense":[36],"optimal":[38,75],"theory.":[40],"approximator":[42],"based":[44],"on":[45],"normalized":[46],"radial":[47],"basis":[48],"functions":[49],"(NRBFs),":[50],"and":[51,98,118,121],"are":[52,108],"built":[53],"using":[54,110],"K-means":[56],"clustering":[57],"algorithm":[58],"which":[59,78],"generates":[60],"family":[62],"approximators":[64],"function.":[68],"RL":[70],"algorithms":[71],"learn":[72],"on-line":[73],"impedance":[76],"model":[77],"equivalent":[80],"to":[81],"desired":[83],"force":[84,96],"without":[85],"any":[86],"prior":[87],"knowledge":[88],"dynamics;":[92],"feeds":[94,101],"controller":[97],"its":[99],"output":[100],"position":[103],"controller.":[104],"Real":[105],"time":[106],"experiments":[107],"shown":[109],"2":[112],"degree":[113],"freedom":[115],"(DOF)":[116],"pan":[117],"tilt":[119],"6-DOF":[123],"force/torque":[124],"(F/T)":[125],"sensor.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}