{"id":"https://openalex.org/W3207033168","doi":"https://doi.org/10.1109/icra46639.2022.9812166","title":"Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World","display_name":"Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W3207033168","doi":"https://doi.org/10.1109/icra46639.2022.9812166","mag":"3207033168"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9812166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812166","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057441223","display_name":"Laura Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Smith","raw_affiliation_strings":["Berkeley AI Research, UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berkeley AI Research, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035286108","display_name":"J. Chase Kew","orcid":"https://orcid.org/0000-0003-2850-0894"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Chase Kew","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070606710","display_name":"Xue Bin Peng","orcid":"https://orcid.org/0000-0003-0480-7816"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xue Bin Peng","raw_affiliation_strings":["Berkeley AI Research, UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berkeley AI Research, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064581452","display_name":"Sehoon Ha","orcid":"https://orcid.org/0000-0002-1972-328X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sehoon Ha","raw_affiliation_strings":["Google Research","Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103241086","display_name":"Jie Tan","orcid":"https://orcid.org/0000-0002-7947-0333"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Tan","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["Berkeley AI Research, UC Berkeley","Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berkeley AI Research, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":43.5326,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.99943307,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1593","last_page":"1599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9937999844551086,"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/T12400","display_name":"Neurogenetic and Muscular Disorders Research","score":0.9398999810218811,"subfield":{"id":"https://openalex.org/subfields/2716","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7836858034133911},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7758381366729736},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6940315365791321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6538034677505493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6417609453201294},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.540931224822998},{"id":"https://openalex.org/keywords/evolutionary-robotics","display_name":"Evolutionary robotics","score":0.5359514355659485},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5322458744049072},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42647671699523926},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.42523130774497986},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3347601890563965},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15521085262298584},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1254676878452301}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7836858034133911},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7758381366729736},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6940315365791321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6538034677505493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6417609453201294},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.540931224822998},{"id":"https://openalex.org/C199505168","wikidata":"https://www.wikidata.org/wiki/Q3267529","display_name":"Evolutionary robotics","level":3,"score":0.5359514355659485},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5322458744049072},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42647671699523926},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.42523130774497986},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3347601890563965},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15521085262298584},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1254676878452301},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9812166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812166","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W44140225","https://openalex.org/W1522301498","https://openalex.org/W2109008048","https://openalex.org/W2139053308","https://openalex.org/W2294151168","https://openalex.org/W2549216668","https://openalex.org/W2562736583","https://openalex.org/W2565902248","https://openalex.org/W2593412525","https://openalex.org/W2726187156","https://openalex.org/W2767050701","https://openalex.org/W2781726626","https://openalex.org/W2791047073","https://openalex.org/W2796290181","https://openalex.org/W2801567109","https://openalex.org/W2811441028","https://openalex.org/W2894779868","https://openalex.org/W2907537824","https://openalex.org/W2909553221","https://openalex.org/W2911087563","https://openalex.org/W2913754617","https://openalex.org/W2919616510","https://openalex.org/W2958043083","https://openalex.org/W2962957005","https://openalex.org/W2963184939","https://openalex.org/W2964114602","https://openalex.org/W2964121744","https://openalex.org/W2967998934","https://openalex.org/W2968116426","https://openalex.org/W2968213087","https://openalex.org/W2978455699","https://openalex.org/W3003647188","https://openalex.org/W3006449166","https://openalex.org/W3007553593","https://openalex.org/W3008998212","https://openalex.org/W3029509103","https://openalex.org/W3029641972","https://openalex.org/W3039737909","https://openalex.org/W3047403664","https://openalex.org/W3093922502","https://openalex.org/W3101442004","https://openalex.org/W3104515094","https://openalex.org/W3104876774","https://openalex.org/W3124816456","https://openalex.org/W3153879297","https://openalex.org/W3162157701","https://openalex.org/W3175254947","https://openalex.org/W3176539729","https://openalex.org/W3178351738","https://openalex.org/W3207591725","https://openalex.org/W3208422024","https://openalex.org/W4250058668","https://openalex.org/W4288626282","https://openalex.org/W6601848611","https://openalex.org/W6731094094","https://openalex.org/W6740222838","https://openalex.org/W6747473740","https://openalex.org/W6753239695","https://openalex.org/W6755161045","https://openalex.org/W6757380569","https://openalex.org/W6758741661","https://openalex.org/W6765121789","https://openalex.org/W6774126978","https://openalex.org/W6776458826","https://openalex.org/W6778428183","https://openalex.org/W6789305357"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2097297620","https://openalex.org/W4244439390","https://openalex.org/W2380659006","https://openalex.org/W4251432983","https://openalex.org/W2096206748","https://openalex.org/W4381586542","https://openalex.org/W2076767946"],"abstract_inverted_index":{"Legged":[0],"robots":[1],"are":[2,17,87],"physically":[3],"capable":[4],"of":[5,10,58,83,110,117,150,176,185],"traversing":[6],"a":[7,26,55,115,130,147,162,174,183],"wide":[8],"range":[9,57,175],"challenging":[11],"environments,":[12,177],"but":[13],"designing":[14],"controllers":[15,51,85],"that":[16,86,146],"sufficiently":[18],"robust":[19,50,88],"to":[20,47,64,90,98,167],"handle":[21,91],"this":[22,160],"diversity":[23],"has":[24,44],"been":[25,45],"long-standing":[27],"challenge":[28],"in":[29,54,101,140,173],"robotics.":[30],"Reinforcement":[31],"learning":[32,113,134],"presents":[33],"an":[34,179],"appealing":[35],"approach":[36],"for":[37,136],"automating":[38],"the":[39,69,96,141],"controller":[40],"design":[41],"process":[42],"and":[43,75,122,159,182,189],"able":[46],"produce":[48],"remarkably":[49],"when":[52],"trained":[53],"suitable":[56],"environments.":[59],"However,":[60],"it":[61,104],"is":[62],"difficult":[63],"predict":[65],"all":[66],"likely":[67],"conditions":[68],"robot":[70,97,132,166],"will":[71],"encounter":[72],"during":[73,157],"deployment":[74],"enumerate":[76],"them":[77],"at":[78],"training-time.":[79],"What":[80],"if":[81],"instead":[82],"training":[84,152],"enough":[89],"any":[92,102],"eventuality,":[93],"we":[94,128],"enable":[95],"continually":[99],"learn":[100],"setting":[103],"finds":[105],"itself":[106],"in?":[107],"This":[108],"kind":[109],"real-world":[111,151],"reinforcement":[112,133],"poses":[114],"number":[116],"challenges,":[118,127],"including":[119,178],"efficiency,":[120],"safety,":[121],"autonomy.":[123],"To":[124],"address":[125],"these":[126],"propose":[129],"practical":[131],"system":[135],"fine-tuning":[137],"locomotion":[138,171],"policies":[139],"real":[142,163],"world.":[143],"We":[144],"demonstrate":[145],"modest":[148],"amount":[149],"can":[153],"substantially":[154],"improve":[155],"performance":[156],"deployment,":[158],"enables":[161],"A1":[164],"quadrupedal":[165],"autonomously":[168],"fine-tune":[169],"multiple":[170],"skills":[172],"outdoor":[180],"lawn":[181],"variety":[184],"indoor":[186],"terrains.":[187],"(Videos":[188],"code11https://sites.google.com/berkele.edu/fine-tuning-locomotion)":[190]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}