{"id":"https://openalex.org/W3091686100","doi":"https://doi.org/10.1109/icra40945.2020.9196791","title":"Learning Control Policies from Optimal Trajectories","display_name":"Learning Control Policies from Optimal Trajectories","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3091686100","doi":"https://doi.org/10.1109/icra40945.2020.9196791","mag":"3091686100"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9196791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9196791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","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/A5037941134","display_name":"Christoph Zelch","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christoph Zelch","raw_affiliation_strings":["Simulation, Systems, Optimization and Robotics Group, TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Simulation, Systems, Optimization and Robotics Group, TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Intelligent Autonomous Systems Group, TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Group, TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014799780","display_name":"Oskar von Stryk","orcid":"https://orcid.org/0000-0002-2790-6115"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oskar von Stryk","raw_affiliation_strings":["Simulation, Systems, Optimization and Robotics Group, TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Simulation, Systems, Optimization and Robotics Group, TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037941134"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.2942,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56120923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"18","issue":null,"first_page":"2529","last_page":"2535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9994000196456909,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9994000196456909,"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/T11236","display_name":"Control Systems and Identification","score":0.9894999861717224,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9836999773979187,"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/control-theory","display_name":"Control theory (sociology)","score":0.6652395725250244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6435461044311523},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6432082653045654},{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.5711196660995483},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5388746857643127},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5361127257347107},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.49085646867752075},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48196837306022644},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47821518778800964},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4765127897262573},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47386693954467773},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.4660101532936096},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4632939100265503},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43681299686431885},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43029487133026123},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4140617251396179},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3831128776073456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20598334074020386},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19706812500953674},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13161414861679077}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6652395725250244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6435461044311523},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6432082653045654},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.5711196660995483},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5388746857643127},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5361127257347107},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.49085646867752075},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48196837306022644},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47821518778800964},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4765127897262573},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47386693954467773},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.4660101532936096},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4632939100265503},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43681299686431885},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43029487133026123},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4140617251396179},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3831128776073456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20598334074020386},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19706812500953674},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13161414861679077},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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":2,"locations":[{"id":"doi:10.1109/icra40945.2020.9196791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9196791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:129749","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/129749/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W98935309","https://openalex.org/W137285897","https://openalex.org/W646243098","https://openalex.org/W1495441213","https://openalex.org/W1496696381","https://openalex.org/W1746819321","https://openalex.org/W1970101292","https://openalex.org/W1979102995","https://openalex.org/W2001981441","https://openalex.org/W2004303440","https://openalex.org/W2004975435","https://openalex.org/W2007813200","https://openalex.org/W2049670620","https://openalex.org/W2057756946","https://openalex.org/W2075439537","https://openalex.org/W2099768828","https://openalex.org/W2102884619","https://openalex.org/W2104733512","https://openalex.org/W2105038027","https://openalex.org/W2113501460","https://openalex.org/W2116773335","https://openalex.org/W2126025075","https://openalex.org/W2130094217","https://openalex.org/W2148112459","https://openalex.org/W2151268438","https://openalex.org/W2154032554","https://openalex.org/W2156779957","https://openalex.org/W2162218551","https://openalex.org/W2163604872","https://openalex.org/W2244269373","https://openalex.org/W2570803472","https://openalex.org/W2902567167","https://openalex.org/W2949487378","https://openalex.org/W2949658140","https://openalex.org/W2961703895","https://openalex.org/W2970228732","https://openalex.org/W3101238199","https://openalex.org/W3101870171","https://openalex.org/W4211049957","https://openalex.org/W4285526177","https://openalex.org/W6604104294","https://openalex.org/W6605566567","https://openalex.org/W6644988060","https://openalex.org/W6674989108","https://openalex.org/W6675604983","https://openalex.org/W6675999342","https://openalex.org/W7065155401","https://openalex.org/W7066478640"],"related_works":["https://openalex.org/W3196329154","https://openalex.org/W3195232394","https://openalex.org/W2738500150","https://openalex.org/W2059875971","https://openalex.org/W2733804152","https://openalex.org/W2063198528","https://openalex.org/W2735800644","https://openalex.org/W2403551983","https://openalex.org/W1554411426","https://openalex.org/W3091686100"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,58,93,123,130,143],"optimally":[3],"control":[4,34,49,69],"robotic":[5],"systems":[6,38,52],"offers":[7],"significant":[8],"advantages":[9],"for":[10,21,36,60,98],"their":[11],"performance.":[12],"While":[13],"time-dependent":[14],"optimal":[15,32,77,103],"trajectories":[16,79,86],"can":[17],"numerically":[18],"be":[19],"computed":[20],"high":[22,125],"dimensional":[23,126],"nonlinear":[24],"system":[25],"dynamic":[26],"models,":[27],"constraints":[28],"and":[29,62,87,129,151],"objectives,":[30],"finding":[31],"feedback":[33,68],"policies":[35],"such":[37],"is":[39,42,71,91,107,120],"hard.":[40],"This":[41,105],"unfortunate,":[43],"as":[44,109],"without":[45],"a":[46,67,74,144,157],"policy,":[47],"the":[48,88,99,115,124,133],"of":[50,76,101,114,147,156],"real-world":[51],"requires":[53],"frequent":[54],"correction":[55],"or":[56],"replanning":[57],"compensate":[59],"disturbances":[61],"model":[63],"errors.In":[64],"this":[65],"paper,":[66],"policy":[70,90],"learned":[72],"from":[73,84],"set":[75],"reference":[78],"using":[80],"Gaussian":[81],"processes.":[82],"Information":[83],"existing":[85],"current":[89],"used":[92],"find":[94],"promising":[95],"start":[96],"points":[97],"computation":[100],"further":[102],"trajectories.":[104],"aspect":[106],"important":[108],"it":[110],"avoids":[111],"exhaustive":[112],"sampling":[113],"complete":[116],"state":[117,127],"space,":[118,128],"which":[119],"impractical":[121],"due":[122],"focus":[131],"on":[132],"relevant":[134],"region.The":[135],"presented":[136],"method":[137],"has":[138],"been":[139],"applied":[140],"in":[141],"simulation":[142],"swing-up":[145],"problem":[146],"an":[148,152],"underactuated":[149],"pendulum":[150],"energy-minimal":[153],"point-to-point":[154],"movement":[155],"3-DOF":[158],"industrial":[159],"robot.":[160]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}