{"id":"https://openalex.org/W4296403414","doi":"https://doi.org/10.1109/icra48891.2023.10160387","title":"Enforcing the consensus between Trajectory Optimization and Policy Learning for precise robot control","display_name":"Enforcing the consensus between Trajectory Optimization and Policy Learning for precise robot control","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4296403414","doi":"https://doi.org/10.1109/icra48891.2023.10160387"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03780392v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044439834","display_name":"Quentin Le Lidec","orcid":"https://orcid.org/0000-0001-7973-1030"},"institutions":[{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI"],"is_corresponding":false,"raw_author_name":"Quentin Le Lidec","raw_affiliation_strings":["PSL Research University,Inria - Departement d&#x0027;Informatique de l&#x0027;Ecole normale sup&#x00E9;rieure"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PSL Research University,Inria - Departement d&#x0027;Informatique de l&#x0027;Ecole normale sup&#x00E9;rieure","institution_ids":["https://openalex.org/I4210103330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003770336","display_name":"Wilson Jallet","orcid":"https://orcid.org/0000-0001-8222-2739"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I190497903","display_name":"Laboratoire d'Analyse et d'Architecture des Syst\u00e8mes","ror":"https://ror.org/03vcm6439","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I190497903","https://openalex.org/I193033237","https://openalex.org/I196454796","https://openalex.org/I205747304","https://openalex.org/I4210095849","https://openalex.org/I4210152422","https://openalex.org/I4210159245","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI","FR"],"is_corresponding":false,"raw_author_name":"Wilson Jallet","raw_affiliation_strings":["PSL Research University,Inria - Departement d&#x0027;Informatique de l&#x0027;Ecole normale sup&#x00E9;rieure","LAAS-CNRS, Toulouse"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PSL Research University,Inria - Departement d&#x0027;Informatique de l&#x0027;Ecole normale sup&#x00E9;rieure","institution_ids":["https://openalex.org/I4210103330"]},{"raw_affiliation_string":"LAAS-CNRS, Toulouse","institution_ids":["https://openalex.org/I190497903","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087781064","display_name":"Ivan Laptev","orcid":"https://orcid.org/0000-0001-7072-3325"},"institutions":[{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI"],"is_corresponding":false,"raw_author_name":"Ivan Laptev","raw_affiliation_strings":["PSL Research University,Inria - Departement d&#x0027;Informatique de l&#x0027;Ecole normale sup&#x00E9;rieure"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PSL Research University,Inria - Departement d&#x0027;Informatique de l&#x0027;Ecole normale sup&#x00E9;rieure","institution_ids":["https://openalex.org/I4210103330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI"],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":["PSL Research University,Inria - Departement d&#x0027;Informatique de l&#x0027;Ecole normale sup&#x00E9;rieure"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PSL Research University,Inria - Departement d&#x0027;Informatique de l&#x0027;Ecole normale sup&#x00E9;rieure","institution_ids":["https://openalex.org/I4210103330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059986205","display_name":"Justin Carpentier","orcid":"https://orcid.org/0000-0001-6585-2894"},"institutions":[{"id":"https://openalex.org/I4210103330","display_name":"\u00c9cole Normale Sup\u00e9rieure","ror":"https://ror.org/01dp7jr64","country_code":"BI","type":"education","lineage":["https://openalex.org/I4210103330"]}],"countries":["BI"],"is_corresponding":false,"raw_author_name":"Justin Carpentier","raw_affiliation_strings":["PSL Research University,Inria - Departement d&#x0027;Informatique de l&#x0027;Ecole normale sup&#x00E9;rieure"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PSL Research University,Inria - Departement d&#x0027;Informatique de l&#x0027;Ecole normale sup&#x00E9;rieure","institution_ids":["https://openalex.org/I4210103330"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"946","last_page":"952"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9926999807357788,"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":0.8029285669326782},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7348329424858093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6939859986305237},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6268637180328369},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"Trajectory optimization","score":0.5632423758506775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5554724335670471},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5498356223106384},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5026874542236328},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46056821942329407},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4476359486579895},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.42661386728286743},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38249391317367554},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36012089252471924},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15274262428283691},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1288076937198639},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06936344504356384}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8029285669326782},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7348329424858093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6939859986305237},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6268637180328369},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.5632423758506775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5554724335670471},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5498356223106384},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5026874542236328},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46056821942329407},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4476359486579895},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.42661386728286743},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38249391317367554},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36012089252471924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15274262428283691},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1288076937198639},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06936344504356384},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra48891.2023.10160387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03780392v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03780392","pdf_url":"https://hal.science/hal-03780392v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Robotics and Automation","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03780392v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03780392","pdf_url":"https://hal.science/hal-03780392v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Robotics and Automation","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5838787665","display_name":"PaRis Artificial Intelligence Research InstitutE","funder_award_id":"ANR-19-P3IA-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296403414.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W195033972","https://openalex.org/W1522301498","https://openalex.org/W1562460111","https://openalex.org/W2042613327","https://openalex.org/W2087617385","https://openalex.org/W2119717200","https://openalex.org/W2147032798","https://openalex.org/W2155007355","https://openalex.org/W2155027007","https://openalex.org/W2158370675","https://openalex.org/W2295431040","https://openalex.org/W2626089772","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2804623852","https://openalex.org/W2890326782","https://openalex.org/W2891122218","https://openalex.org/W2899771611","https://openalex.org/W2906487027","https://openalex.org/W3081791272","https://openalex.org/W3123748881","https://openalex.org/W3135508935","https://openalex.org/W3216772467","https://openalex.org/W4200630450","https://openalex.org/W4214717370","https://openalex.org/W4225857316","https://openalex.org/W4234674466","https://openalex.org/W4292363360","https://openalex.org/W6607786297","https://openalex.org/W6631190155","https://openalex.org/W6672539821","https://openalex.org/W6675999342","https://openalex.org/W6681631837","https://openalex.org/W6682849425","https://openalex.org/W6683204974","https://openalex.org/W6739475399","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6754787993","https://openalex.org/W6756040250","https://openalex.org/W6789377880","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2003479292","https://openalex.org/W3135469233"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"and":[3,131,142],"trajectory":[4,61],"opti-mization":[5],"(TO)":[6],"present":[7],"strong":[8],"complementary":[9],"advantages.":[10],"On":[11,38],"one":[12],"hand,":[13,41],"RL":[14],"approaches":[15,77,112,162],"are":[16,44],"able":[17,45],"to":[18,32,46,53,80,90,113,136],"learn":[19,114],"global":[20,115],"control":[21,60,116],"policies":[22,117],"directly":[23],"from":[24,51,99,125],"data,":[25],"but":[26],"generally":[27],"require":[28],"large":[29],"sample":[30],"sizes":[31],"properly":[33],"converge":[34,55],"towards":[35,56],"feasible":[36],"policies.":[37],"the":[39,67,70,73,83,92,138,147,164],"other":[40],"TO":[42,126,141],"methods":[43,87,127],"exploit":[47],"gradient-based":[48],"information":[49,123],"extracted":[50],"simulators":[52],"quickly":[54],"a":[57],"locally":[58],"optimal":[59],"which":[62],"is":[63],"only":[64],"valid":[65],"within":[66],"vicinity":[68],"of":[69,86,94,102,110,149],"solution.":[71],"Over":[72],"past":[74],"decade,":[75],"several":[76,106],"have":[78],"aimed":[79],"adequately":[81],"combine":[82],"two":[84],"classes":[85],"in":[88,156,163],"order":[89],"obtain":[91],"best":[93],"both":[95],"worlds.":[96],"Following":[97],"on":[98,108,152],"this":[100],"line":[101],"research,":[103],"we":[104],"propose":[105],"improvements":[107,151],"top":[109],"these":[111,150],"quicker,":[118],"notably":[119],"by":[120],"leveraging":[121],"sensitivity":[122],"stemming":[124],"via":[128],"Sobolev":[129],"learning,":[130],"Augmented":[132],"Lagrangian":[133],"(AL)":[134],"techniques":[135],"enforce":[137],"consensus":[139],"between":[140],"policy":[143],"learning.":[144],"We":[145],"evaluate":[146],"benefits":[148],"various":[153],"classical":[154],"tasks":[155],"robotics":[157],"through":[158],"comparison":[159],"with":[160],"existing":[161],"literature.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
