{"id":"https://openalex.org/W3119331336","doi":"https://doi.org/10.1109/lars/sbr/wre51543.2020.9306967","title":"Push Recovery Strategies through Deep Reinforcement Learning","display_name":"Push Recovery Strategies through Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-11-09","ids":{"openalex":"https://openalex.org/W3119331336","doi":"https://doi.org/10.1109/lars/sbr/wre51543.2020.9306967","mag":"3119331336"},"language":"en","primary_location":{"id":"doi:10.1109/lars/sbr/wre51543.2020.9306967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lars/sbr/wre51543.2020.9306967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Latin American Robotics Symposium (LARS), 2020 Brazilian Symposium on Robotics (SBR) and 2020 Workshop on Robotics in Education (WRE)","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/A5032535477","display_name":"Dicksiano C. Melo","orcid":"https://orcid.org/0000-0003-1263-5110"},"institutions":[{"id":"https://openalex.org/I107428990","display_name":"Instituto Tecnol\u00f3gico de Aeron\u00e1utica","ror":"https://ror.org/05vh67662","country_code":"BR","type":"education","lineage":["https://openalex.org/I107428990"]},{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Dicksiano Carvalho Melo","raw_affiliation_strings":["Aeronautics Institute of Technology,,Autonomous Computational Systems Lab (LAB-SCA), Computer Science Division,S\u00e3o Jos\u00e9 dos Campos,SP,Brazil,12228-900"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aeronautics Institute of Technology,,Autonomous Computational Systems Lab (LAB-SCA), Computer Science Division,S\u00e3o Jos\u00e9 dos Campos,SP,Brazil,12228-900","institution_ids":["https://openalex.org/I107428990","https://openalex.org/I4210123805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019218502","display_name":"Marcos R. O. A. M\u00e1ximo","orcid":"https://orcid.org/0000-0003-2944-4476"},"institutions":[{"id":"https://openalex.org/I107428990","display_name":"Instituto Tecnol\u00f3gico de Aeron\u00e1utica","ror":"https://ror.org/05vh67662","country_code":"BR","type":"education","lineage":["https://openalex.org/I107428990"]},{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos R. O. A. Maximo","raw_affiliation_strings":["Aeronautics Institute of Technology,,Autonomous Computational Systems Lab (LAB-SCA), Computer Science Division,S\u00e3o Jos\u00e9 dos Campos,SP,Brazil,12228-900"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aeronautics Institute of Technology,,Autonomous Computational Systems Lab (LAB-SCA), Computer Science Division,S\u00e3o Jos\u00e9 dos Campos,SP,Brazil,12228-900","institution_ids":["https://openalex.org/I107428990","https://openalex.org/I4210123805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063426225","display_name":"Adilson Marques da Cunha","orcid":"https://orcid.org/0000-0003-2399-5066"},"institutions":[{"id":"https://openalex.org/I107428990","display_name":"Instituto Tecnol\u00f3gico de Aeron\u00e1utica","ror":"https://ror.org/05vh67662","country_code":"BR","type":"education","lineage":["https://openalex.org/I107428990"]},{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Adilson Marques da Cunha","raw_affiliation_strings":["Aeronautics Institute of Technology,Computer Science Division,S\u00e3oJos\u00e9 dos Campos,SP,Brazil,12228-900"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aeronautics Institute of Technology,Computer Science Division,S\u00e3oJos\u00e9 dos Campos,SP,Brazil,12228-900","institution_ids":["https://openalex.org/I107428990","https://openalex.org/I4210123805"]}]}],"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":10,"citation_normalized_percentile":null,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9998000264167786,"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":0.9998000264167786,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9850999712944031,"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":0.9843999743461609,"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":0.8561438918113708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7859287261962891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5548292398452759},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5136510729789734},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5124890804290771},{"id":"https://openalex.org/keywords/league","display_name":"League","score":0.48740842938423157},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.4787951409816742},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4661273956298828},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.44976645708084106},{"id":"https://openalex.org/keywords/zero-moment-point","display_name":"Zero moment point","score":0.42964646220207214},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.42370229959487915},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2237018346786499},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1273140013217926}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8561438918113708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859287261962891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5548292398452759},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5136510729789734},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5124890804290771},{"id":"https://openalex.org/C207456731","wikidata":"https://www.wikidata.org/wiki/Q660818","display_name":"League","level":2,"score":0.48740842938423157},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.4787951409816742},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4661273956298828},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.44976645708084106},{"id":"https://openalex.org/C19245436","wikidata":"https://www.wikidata.org/wiki/Q279038","display_name":"Zero moment point","level":4,"score":0.42964646220207214},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.42370229959487915},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2237018346786499},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1273140013217926},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lars/sbr/wre51543.2020.9306967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lars/sbr/wre51543.2020.9306967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Latin American Robotics Symposium (LARS), 2020 Brazilian Symposium on Robotics (SBR) and 2020 Workshop on Robotics in Education (WRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322569","display_name":"STMicroelectronics","ror":"https://ror.org/00wm3b005"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W205043379","https://openalex.org/W1807600159","https://openalex.org/W1972939092","https://openalex.org/W2013207866","https://openalex.org/W2110215557","https://openalex.org/W2112025910","https://openalex.org/W2122458271","https://openalex.org/W2132130138","https://openalex.org/W2138136244","https://openalex.org/W2152912973","https://openalex.org/W2155005770","https://openalex.org/W2168377523","https://openalex.org/W2539915646","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2784192398","https://openalex.org/W2911251203","https://openalex.org/W2931363641","https://openalex.org/W2950125763","https://openalex.org/W2964218219","https://openalex.org/W2981636907","https://openalex.org/W2990747716","https://openalex.org/W3009915523","https://openalex.org/W3101808543","https://openalex.org/W3106249594"],"related_works":["https://openalex.org/W1829175078","https://openalex.org/W2606527650","https://openalex.org/W2130383927","https://openalex.org/W2133801610","https://openalex.org/W2151003079","https://openalex.org/W2170918662","https://openalex.org/W2120357486","https://openalex.org/W2034988786","https://openalex.org/W2220923292","https://openalex.org/W2163503851"],"abstract_inverted_index":{"This":[0],"work":[1,48],"implements":[2],"a":[3,9,14,27,55,63,83,129,135],"Push":[4],"Recovery":[5],"controller":[6],"that":[7,30,85,105],"improves":[8],"walking":[10,67],"engine":[11],"used":[12,77],"by":[13,54],"humanoid":[15],"simulated":[16],"agent":[17,88,101],"from":[18],"RoboCup":[19],"3D":[20],"Soccer":[21],"Simulation":[22],"League.":[23],"Therefore,":[24],"we":[25],"achieve":[26],"movement":[28],"policy":[29],"allows":[31],"the":[32,42,74,86,93,98],"agents":[33],"to":[34,97,112,127],"re-establish":[35],"their":[36],"own":[37],"balance":[38],"when":[39],"disturbed.":[40],"Using":[41],"Proximal":[43],"Policy":[44],"Optimization":[45],"algorithm,":[46],"this":[47],"achieved":[49],"an":[50],"expert":[51],"policy,":[52],"represented":[53],"Deep":[56],"Neural":[57],"Network,":[58],"which":[59],"is":[60,78,119,125],"compatible":[61],"with":[62,71],"Zero":[64],"Moment":[65],"Point":[66],"engine.":[68],"In":[69],"contrast":[70],"other":[72],"works,":[73],"reward":[75],"signal":[76],"much":[79],"more":[80,114],"agnostic,":[81],"in":[82,110,133],"way":[84],"learning":[87],"was":[89,102],"not":[90],"aware":[91,104],"of":[92],"physical":[94],"constraints":[95],"related":[96],"problem.":[99],"The":[100,116],"just":[103,134],"it":[106,124],"should":[107],"avoid":[108],"failing":[109],"order":[111],"accumulate":[113],"reward.":[115],"proposed":[117],"method":[118],"also":[120],"sample":[121],"efficient,":[122],"as":[123],"able":[126],"learn":[128],"human":[130],"inspired":[131],"behavior":[132],"few":[136],"hours.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}