{"id":"https://openalex.org/W7128815034","doi":"https://doi.org/10.1109/lra.2026.3664534","title":"Efficiently Learning Robust Torque-Based Locomotion Through Reinforcement With Model-Based Supervision","display_name":"Efficiently Learning Robust Torque-Based Locomotion Through Reinforcement With Model-Based Supervision","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7128815034","doi":"https://doi.org/10.1109/lra.2026.3664534"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3664534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3664534","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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/A5113085979","display_name":"Yashuai Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Yashuai Yan","raw_affiliation_strings":["Autonomous Systems Lab, TU Wien, Vienna, Austria"],"raw_orcid":"https://orcid.org/0009-0005-5489-6273","affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125897019","display_name":"Tobias Egle","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Tobias Egle","raw_affiliation_strings":["Automation and Control Institute, TU Wien, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0002-4765-2415","affiliations":[{"raw_affiliation_string":"Automation and Control Institute, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048539897","display_name":"Christian Ott","orcid":"https://orcid.org/0000-0003-0987-7493"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Christian Ott","raw_affiliation_strings":["Automation and Control Institute, TU Wien, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-0987-7493","affiliations":[{"raw_affiliation_string":"Automation and Control Institute, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121492402","display_name":"Dongheui Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dongheui Lee","raw_affiliation_strings":["Autonomous Systems Lab, TU Wien, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-1897-7664","affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":3.5068,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88607235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"11","issue":"4","first_page":"4155","last_page":"4162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.7534999847412109,"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":0.7534999847412109,"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":0.1137000024318695,"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":0.02370000071823597,"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":0.7365999817848206},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.660099983215332},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5166000127792358},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5055999755859375},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4074999988079071},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.38929998874664307},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3765000104904175},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3628000020980835},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.36230000853538513}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7365999817848206},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.660099983215332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6517000198364258},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503000020980835},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.38929998874664307},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.36230000853538513},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3337000012397766},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3151000142097473},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3046000003814697},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3664534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3664534","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":[{"id":"https://openalex.org/G4788090447","display_name":"Diffusion-Based Robot Control Policy with Safety Awareness and Generalization","funder_award_id":"ICT25-068","funder_id":"https://openalex.org/F4320321003","funder_display_name":"Vienna Science and Technology Fund"}],"funders":[{"id":"https://openalex.org/F4320321003","display_name":"Vienna Science and Technology Fund","ror":"https://ror.org/01f9mc681"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,30,33,42,45,62,74,93,124,130],"control":[3],"framework":[4],"that":[5,107],"integrates":[6],"model-based":[7,31,75],"bipedal":[8,137],"locomotion":[9],"with":[10,68],"residual":[11,63,90],"reinforcement":[12],"learning":[13],"(RL)":[14],"to":[15,82,87,102],"achieve":[16],"robust":[17],"and":[18,41,57,121],"adaptive":[19],"walking":[20],"in":[21,136],"the":[22,51,89,100],"presence":[23],"of":[24,36,53,126],"real-world":[25],"uncertainties.":[26],"Our":[27,116],"approach":[28],"leverages":[29],"controller\u2014comprising":[32],"Divergent":[34],"Component":[35],"Motion":[37],"(DCM)":[38],"trajectory":[39],"planner":[40],"whole-body":[43],"controller\u2014as":[44],"reliable":[46],"base":[47],"policy.":[48],"To":[49],"address":[50],"uncertainties":[52],"inaccurate":[54],"dynamics":[55,84],"modeling":[56],"sensor":[58],"noise,":[59],"we":[60,72],"introduce":[61],"policy":[64,91,101],"trained":[65],"through":[66],"RL":[67],"domain":[69],"randomization.":[70],"Crucially,":[71],"employ":[73],"oracle":[76],"policy,":[77],"which":[78],"has":[79],"privileged":[80],"access":[81],"ground-truth":[83],"during":[85],"training,":[86],"supervise":[88],"via":[92],"novel":[94],"supervised":[95],"loss.":[96],"This":[97],"supervision":[98],"enables":[99],"efficiently":[103],"learn":[104],"corrective":[105],"behaviors":[106],"compensate":[108],"for":[109,133],"unmodeled":[110],"effects":[111],"without":[112],"extensive":[113],"reward":[114],"shaping.":[115],"method":[117],"demonstrates":[118],"improved":[119],"robustness":[120],"generalization":[122],"across":[123],"range":[125],"randomized":[127],"conditions,":[128],"offering":[129],"scalable":[131],"solution":[132],"sim-to-real":[134],"transfer":[135],"locomotion.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-02-14T00:00:00"}