{"id":"https://openalex.org/W4386038305","doi":"https://doi.org/10.1109/lra.2023.3307008","title":"RL + Model-Based Control: Using On-Demand Optimal Control to Learn Versatile Legged Locomotion","display_name":"RL + Model-Based Control: Using On-Demand Optimal Control to Learn Versatile Legged Locomotion","publication_year":2023,"publication_date":"2023-08-21","ids":{"openalex":"https://openalex.org/W4386038305","doi":"https://doi.org/10.1109/lra.2023.3307008"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3307008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3307008","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5102020323","display_name":"Dongho Kang","orcid":"https://orcid.org/0000-0003-2512-5849"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Dongho Kang","raw_affiliation_strings":["Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-2512-5849","affiliations":[{"raw_affiliation_string":"Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013602697","display_name":"Jin Cheng","orcid":"https://orcid.org/0000-0001-9822-3701"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jin Cheng","raw_affiliation_strings":["Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-9822-3701","affiliations":[{"raw_affiliation_string":"Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004619648","display_name":"Miguel Zamora","orcid":"https://orcid.org/0000-0001-8173-8311"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Miguel Zamora","raw_affiliation_strings":["Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8173-8311","affiliations":[{"raw_affiliation_string":"Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023737038","display_name":"Fatemeh Zargarbashi","orcid":"https://orcid.org/0009-0001-9734-2693"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fatemeh Zargarbashi","raw_affiliation_strings":["Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0001-9734-2693","affiliations":[{"raw_affiliation_string":"Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055713873","display_name":"Stelian Coros","orcid":"https://orcid.org/0000-0001-6604-4784"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Stelian Coros","raw_affiliation_strings":["Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-6604-4784","affiliations":[{"raw_affiliation_string":"Computational Robotics Lab in the Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":3.6415,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.93810216,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"8","issue":"10","first_page":"6619","last_page":"6626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9951000213623047,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9882000088691711,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7355826497077942},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6867738962173462},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6729668974876404},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.6357676386833191},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6240121126174927},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5018494129180908},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49283790588378906},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3659626245498657},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3621411919593811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3549501895904541},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.335411012172699},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16771650314331055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07151594758033752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355826497077942},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6867738962173462},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6729668974876404},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6357676386833191},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6240121126174927},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5018494129180908},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49283790588378906},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3659626245498657},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3621411919593811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3549501895904541},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.335411012172699},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16771650314331055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07151594758033752},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3307008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3307008","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2771123153","https://openalex.org/W2784947652","https://openalex.org/W2788030459","https://openalex.org/W2796290181","https://openalex.org/W2909331752","https://openalex.org/W2911087563","https://openalex.org/W2968213087","https://openalex.org/W2969111820","https://openalex.org/W2972810470","https://openalex.org/W2977527020","https://openalex.org/W3003712039","https://openalex.org/W3010519440","https://openalex.org/W3039737909","https://openalex.org/W3093922502","https://openalex.org/W3095484646","https://openalex.org/W3102994022","https://openalex.org/W3104515094","https://openalex.org/W3104876774","https://openalex.org/W3131200352","https://openalex.org/W3175254947","https://openalex.org/W3207111613","https://openalex.org/W3216772467","https://openalex.org/W4200470117","https://openalex.org/W4205430897","https://openalex.org/W4206589784","https://openalex.org/W4283787029","https://openalex.org/W4286750708","https://openalex.org/W4286963241","https://openalex.org/W4288349568","https://openalex.org/W4309805045","https://openalex.org/W4310886200","https://openalex.org/W4311486620","https://openalex.org/W4313197141","https://openalex.org/W4317987839","https://openalex.org/W4377141222","https://openalex.org/W4383108816","https://openalex.org/W6741002519","https://openalex.org/W6755667589","https://openalex.org/W6762653276","https://openalex.org/W6767349745","https://openalex.org/W6801964084","https://openalex.org/W6804601995","https://openalex.org/W6839861434","https://openalex.org/W6847063038","https://openalex.org/W6847218640","https://openalex.org/W6852997247"],"related_works":["https://openalex.org/W2036697162","https://openalex.org/W2332386680","https://openalex.org/W2248621902","https://openalex.org/W2003779889","https://openalex.org/W2561315646","https://openalex.org/W4205698120","https://openalex.org/W4239246781","https://openalex.org/W2542825942","https://openalex.org/W3201620972","https://openalex.org/W1496421768"],"abstract_inverted_index":{"This":[0],"letter":[1],"presents":[2],"a":[3,40,111],"control":[4,10,65,154],"framework":[5,109,148],"that":[6,67,79,134],"combines":[7],"model-based":[8],"optimal":[9,37],"and":[11,18,45,100,127,171],"reinforcement":[12],"learning":[13],"(RL)":[14],"to":[15,57,60,123,143],"achieve":[16],"versatile":[17],"robust":[19,64],"legged":[20],"locomotion.":[21],"Our":[22],"approach":[23],"enhances":[24],"the":[25,54,61,86,98,103,139,151,162,168],"RL":[26,55,83,104],"training":[27,105,152],"process":[28,106],"by":[29,74,93],"incorporating":[30],"on-demand":[31],"reference":[32,48,90,125],"motions":[33,49,91,126],"generated":[34],"through":[35,110],"finite-horizon":[36],"control,":[38],"covering":[39],"broad":[41],"range":[42],"of":[43,63,102,113,153],"velocities":[44],"gaits.":[46],"These":[47],"serve":[50],"as":[51],"targets":[52],"for":[53,138,156,164],"policy":[56],"imitate,":[58],"leading":[59],"development":[62],"policies":[66,155],"can":[68],"be":[69],"learned":[70],"with":[71,158],"reliability.":[72],"Furthermore,":[73],"utilizing":[75],"realistic":[76],"simulation":[77],"data":[78],"captures":[80],"whole-body":[81],"dynamics,":[82],"effectively":[84,128],"overcomes":[85],"inherent":[87],"limitations":[88],"in":[89,167],"imposed":[92],"modeling":[94],"simplifications.":[95],"We":[96],"validate":[97],"robustness":[99],"controllability":[101],"within":[107],"our":[108,118,147],"series":[112],"experiments.":[114],"In":[115],"these":[116],"experiments,":[117],"method":[119],"showcases":[120],"its":[121],"capability":[122],"generalize":[124],"handle":[129],"more":[130],"complex":[131],"locomotion":[132],"tasks":[133],"may":[135],"pose":[136],"challenges":[137],"simplified":[140],"model,":[141],"thanks":[142],"RL's":[144],"flexibility.":[145],"Additionally,":[146],"effortlessly":[149],"supports":[150],"robots":[157],"diverse":[159],"dimensions,":[160],"eliminating":[161],"necessity":[163],"robot-specific":[165],"adjustments":[166],"reward":[169],"function":[170],"hyperparameters.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}