{"id":"https://openalex.org/W4226055089","doi":"https://doi.org/10.1109/robio54168.2021.9739602","title":"Swinging Up and Balancing a Pendulum on a Vertically Moving Cart Using Reinforcement Learning","display_name":"Swinging Up and Balancing a Pendulum on a Vertically Moving Cart Using Reinforcement Learning","publication_year":2021,"publication_date":"2021-12-27","ids":{"openalex":"https://openalex.org/W4226055089","doi":"https://doi.org/10.1109/robio54168.2021.9739602"},"language":"en","primary_location":{"id":"doi:10.1109/robio54168.2021.9739602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739602","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5037219597","display_name":"Poorna Hima Vamsi A","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Poorna Hima Vamsi A","raw_affiliation_strings":["Indian Institute of Technology Hyderabad,Department of Mechanical and Aerospace Engineering,Telangana,India","Department of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Telangana, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad,Department of Mechanical and Aerospace Engineering,Telangana,India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048460836","display_name":"Mangesh D. Ratolikar","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mangesh D Ratolikar","raw_affiliation_strings":["Indian Institute of Technology Hyderabad,Department of Mechanical and Aerospace Engineering,Telangana,India","Department of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Telangana, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad,Department of Mechanical and Aerospace Engineering,Telangana,India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044837841","display_name":"R. Prasanth Kumar","orcid":"https://orcid.org/0000-0002-1671-752X"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R Prasanth Kumar","raw_affiliation_strings":["Indian Institute of Technology Hyderabad,Department of Mechanical and Aerospace Engineering,Telangana,India","Department of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Telangana, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad,Department of Mechanical and Aerospace Engineering,Telangana,India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Telangana, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037219597"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":1.1531,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7675551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1668","last_page":"1673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.989300012588501,"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/T12810","display_name":"Real-time simulation and control systems","score":0.9890000224113464,"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/inverted-pendulum","display_name":"Inverted pendulum","score":0.7095850706100464},{"id":"https://openalex.org/keywords/pendulum","display_name":"Pendulum","score":0.705812931060791},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.640586256980896},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6040344834327698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5863708853721619},{"id":"https://openalex.org/keywords/cart","display_name":"Cart","score":0.5844768285751343},{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.5625506043434143},{"id":"https://openalex.org/keywords/furuta-pendulum","display_name":"Furuta pendulum","score":0.5028945803642273},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5001082420349121},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4949480891227722},{"id":"https://openalex.org/keywords/swing","display_name":"Swing","score":0.45792847871780396},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.43941420316696167},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4332343339920044},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.422810435295105},{"id":"https://openalex.org/keywords/double-inverted-pendulum","display_name":"Double inverted pendulum","score":0.40153083205223083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3745514154434204},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.27994170784950256},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2700361907482147},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.11670801043510437},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08841192722320557},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08677658438682556}],"concepts":[{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.7095850706100464},{"id":"https://openalex.org/C110639684","wikidata":"https://www.wikidata.org/wiki/Q20702","display_name":"Pendulum","level":2,"score":0.705812931060791},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.640586256980896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6040344834327698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5863708853721619},{"id":"https://openalex.org/C2777275308","wikidata":"https://www.wikidata.org/wiki/Q234668","display_name":"Cart","level":2,"score":0.5844768285751343},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.5625506043434143},{"id":"https://openalex.org/C191601290","wikidata":"https://www.wikidata.org/wiki/Q5509824","display_name":"Furuta pendulum","level":5,"score":0.5028945803642273},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5001082420349121},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4949480891227722},{"id":"https://openalex.org/C65655974","wikidata":"https://www.wikidata.org/wiki/Q14867674","display_name":"Swing","level":2,"score":0.45792847871780396},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.43941420316696167},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4332343339920044},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.422810435295105},{"id":"https://openalex.org/C102540577","wikidata":"https://www.wikidata.org/wiki/Q5300047","display_name":"Double inverted pendulum","level":4,"score":0.40153083205223083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3745514154434204},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27994170784950256},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2700361907482147},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.11670801043510437},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08841192722320557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08677658438682556},{"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},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio54168.2021.9739602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739602","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W34308023","https://openalex.org/W1509235676","https://openalex.org/W1966706206","https://openalex.org/W2061920346","https://openalex.org/W2067349577","https://openalex.org/W2115659282","https://openalex.org/W2121829700","https://openalex.org/W2145339207","https://openalex.org/W2160989584","https://openalex.org/W2165517064","https://openalex.org/W2489657534","https://openalex.org/W2621178540","https://openalex.org/W2781726626","https://openalex.org/W2888720512","https://openalex.org/W2989734230","https://openalex.org/W6747473740","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3216306759","https://openalex.org/W1994259330","https://openalex.org/W2380798744","https://openalex.org/W2655681456","https://openalex.org/W3017318039","https://openalex.org/W2912518559","https://openalex.org/W2105632075","https://openalex.org/W2041698009","https://openalex.org/W2967919033","https://openalex.org/W2082674070"],"abstract_inverted_index":{"Underactuated":[0],"systems":[1],"occur":[2],"frequently":[3],"in":[4,59,88],"robotics":[5],"and":[6,22,39,76,102,121],"legged":[7],"locomotion.":[8],"Unactuated":[9],"pendulum":[10,30,45,70],"on":[11,32,46,71],"an":[12],"actuated":[13],"cart":[14,36,49,75,109],"is":[15,37,50],"a":[16,33,65,69,72,78],"classic":[17],"example":[18],"used":[19],"for":[20,26,42,68,99,107],"designing":[21],"testing":[23],"control":[24,105],"algorithms":[25],"underactuated":[27],"systems.":[28],"While":[29],"balancing":[31,60],"horizontally":[34],"moving":[35,48,74],"popular":[38],"environments":[40],"available":[41],"reinforcement":[43,83],"learning,":[44],"vertically":[47,73],"rarely":[51],"discussed":[52],"due":[53],"to":[54,85],"relatively":[55],"higher":[56],"difficulty":[57],"level":[58],"it.":[61],"This":[62],"paper":[63],"presents":[64],"model":[66],"environment":[67],"trains":[77],"neural":[79,114],"network":[80,115],"controller":[81],"using":[82],"learning":[84],"balance":[86,122],"it":[87],"vertical":[89],"position":[90],"indefinitely":[91],"without":[92],"exceeding":[93],"the":[94,108,113,123],"displacement":[95],"limits.":[96],"Results":[97],"presented":[98],"both":[100],"con-tinuous":[101],"discrete":[103],"force":[104],"input":[106],"system":[110],"show":[111],"that":[112],"controllers":[116],"can":[117],"successfully":[118],"swing":[119],"up":[120],"pendulum.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}