{"id":"https://openalex.org/W2964114602","doi":"https://doi.org/10.1109/iros.2018.8593722","title":"Feedback Control For Cassie With Deep Reinforcement Learning","display_name":"Feedback Control For Cassie With Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2964114602","doi":"https://doi.org/10.1109/iros.2018.8593722","mag":"2964114602"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8593722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5102887266","display_name":"Zhaoming Xie","orcid":"https://orcid.org/0000-0003-1948-1767"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zhaoming Xie","raw_affiliation_strings":["Department of Computer Science, University of British Columbia, Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045351810","display_name":"Glen Berseth","orcid":"https://orcid.org/0000-0001-7351-8028"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Glen Berseth","raw_affiliation_strings":["Department of Computer Science, University of British Columbia, Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083303761","display_name":"Patrick Clary","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Clary","raw_affiliation_strings":["Dynamic Robotics Laboratory, Oregon State University, Corvallis, OR, USA"],"affiliations":[{"raw_affiliation_string":"Dynamic Robotics Laboratory, Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026407792","display_name":"Jonathan Hurst","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Hurst","raw_affiliation_strings":["Dynamic Robotics Laboratory, Oregon State University, Corvallis, OR, USA"],"affiliations":[{"raw_affiliation_string":"Dynamic Robotics Laboratory, Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052748246","display_name":"Michiel van de Panne","orcid":"https://orcid.org/0000-0002-9123-3672"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michiel van de Panne","raw_affiliation_strings":["Department of Computer Science, University of British Columbia, Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102887266"],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":7.2088,"has_fulltext":false,"cited_by_count":187,"citation_normalized_percentile":{"value":0.97916563,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1241","last_page":"1246"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9962000250816345,"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":0.7657030820846558},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7236509323120117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.715563952922821},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5555319786071777},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5104943513870239},{"id":"https://openalex.org/keywords/feedback-linearization","display_name":"Feedback linearization","score":0.476031094789505},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.46259135007858276},{"id":"https://openalex.org/keywords/linearization","display_name":"Linearization","score":0.4620897173881531},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.45959529280662537},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.4412873685359955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43162772059440613},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4266889989376068},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.41644108295440674},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.2737535536289215},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.24104353785514832},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2098783552646637},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17653197050094604},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.13084295392036438},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08318361639976501}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7657030820846558},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7236509323120117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715563952922821},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5555319786071777},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5104943513870239},{"id":"https://openalex.org/C85736874","wikidata":"https://www.wikidata.org/wiki/Q672139","display_name":"Feedback linearization","level":3,"score":0.476031094789505},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.46259135007858276},{"id":"https://openalex.org/C11210021","wikidata":"https://www.wikidata.org/wiki/Q1520713","display_name":"Linearization","level":3,"score":0.4620897173881531},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.45959529280662537},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.4412873685359955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43162772059440613},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4266889989376068},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.41644108295440674},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2737535536289215},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.24104353785514832},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2098783552646637},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17653197050094604},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.13084295392036438},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08318361639976501},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2018.8593722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1891170951","https://openalex.org/W1984120922","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2413365548","https://openalex.org/W2413990562","https://openalex.org/W2465284394","https://openalex.org/W2546975091","https://openalex.org/W2606833507","https://openalex.org/W2726187156","https://openalex.org/W2729615412","https://openalex.org/W2735089625","https://openalex.org/W2736601468","https://openalex.org/W2739330054","https://openalex.org/W2754517384","https://openalex.org/W2784449021","https://openalex.org/W2899771611","https://openalex.org/W2962736495","https://openalex.org/W2962779270","https://openalex.org/W2964121744","https://openalex.org/W3101442004","https://openalex.org/W3105609823","https://openalex.org/W4300892751","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W1998462347","https://openalex.org/W2349527210","https://openalex.org/W1836713364","https://openalex.org/W2141603307","https://openalex.org/W4300511988","https://openalex.org/W2131265573","https://openalex.org/W2899783744","https://openalex.org/W2317650444","https://openalex.org/W130230158","https://openalex.org/W2913529325"],"abstract_inverted_index":{"Bipedal":[0],"locomotion":[1,70],"skills":[2],"are":[3,49,86,94,148,167],"challenging":[4,185],"to":[5,21,150],"develop.":[6],"Control":[7],"strategies":[8],"often":[9,33,87],"use":[10],"local":[11],"linearization":[12],"of":[13,37,120,126,174],"the":[14,30,53,76,82,118,139,175,199],"dynamics":[15],"in":[16,81],"conjunction":[17],"with":[18,160,216],"reduced-order":[19],"abstractions":[20],"yield":[22],"tractable":[23],"solutions.":[24],"In":[25,113],"these":[26],"model-based":[27],"control":[28,54,135],"strategies,":[29],"controller":[31],"is":[32,181],"not":[34,95],"fully":[35,74],"aware":[36],"many":[38],"details,":[39],"including":[40,187],"torque":[41],"limits,":[42,44],"joint":[43],"and":[45,195,210],"other":[46],"non-linearities":[47],"that":[48,93,155,211],"necessarily":[50],"excluded":[51],"from":[52],"computations":[55],"for":[56,67,142,163],"simplicity.":[57],"Deep":[58],"reinforcement":[59],"learning":[60,84],"(DRL)":[61],"offers":[62],"a":[63,123,128,133,143,157],"promising":[64],"model-free":[65],"approach":[66],"controlling":[68],"bipedal":[69,111,129],"which":[71],"can":[72,205,213],"more":[73],"exploit":[75],"dynamics.":[77],"However,":[78],"current":[79],"results":[80],"machine":[83],"literature":[85],"based":[88,96],"on":[89,97,109,192],"ad-hoc":[90],"simulation":[91],"models":[92],"corresponding":[98],"hardware.":[99],"Thus":[100],"it":[101],"remains":[102],"unclear":[103],"how":[104],"well":[105],"DRL":[106,121],"will":[107],"succeed":[108],"realizable":[110],"robots.":[112],"this":[114],"paper,":[115],"we":[116,147,204],"demonstrate":[117],"effectiveness":[119],"using":[122],"realistic":[124],"model":[125],"Cassie,":[127],"robot.":[130],"By":[131],"formulating":[132],"feedback":[134],"problem":[136],"as":[137],"finding":[138],"optimal":[140],"policy":[141],"Markov":[144],"Decision":[145],"Process,":[146],"able":[149],"learn":[151],"robust":[152],"walking":[153,165,190],"controllers":[154],"imitate":[156],"reference":[158,177],"motion":[159],"DRL.":[161],"Controllers":[162],"different":[164],"speeds":[166],"learned":[168],"by":[169],"imitating":[170],"simple":[171],"time-scaled":[172],"versions":[173],"original":[176],"motion.":[178],"Controller":[179],"robustness":[180,212],"demonstrated":[182],"through":[183],"several":[184],"tests,":[186],"sensory":[188],"delay,":[189],"blindly":[191],"irregular":[193],"terrain":[194],"unexpected":[196],"pushes":[197],"at":[198],"pelvis.":[200],"We":[201],"also":[202],"show":[203],"interpolate":[206],"between":[207],"individual":[208],"policies":[209],"be":[214],"improved":[215],"an":[217],"interpolated":[218],"policy.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}