{"id":"https://openalex.org/W4389665667","doi":"https://doi.org/10.1109/iros55552.2023.10341709","title":"Learning a Single Policy for Diverse Behaviors on a Quadrupedal Robot Using Scalable Motion Imitation","display_name":"Learning a Single Policy for Diverse Behaviors on a Quadrupedal Robot Using Scalable Motion Imitation","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665667","doi":"https://doi.org/10.1109/iros55552.2023.10341709"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5047002385","display_name":"Arnaud Klipfel","orcid":null},"institutions":[{"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":"Arnaud Klipfel","raw_affiliation_strings":["School of Interactive Computing, Georgia Institute of Technology,Atlanta,GA,USA,30308"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interactive Computing, Georgia Institute of Technology,Atlanta,GA,USA,30308","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002989902","display_name":"Nitish Sontakke","orcid":null},"institutions":[{"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":"Nitish Sontakke","raw_affiliation_strings":["School of Interactive Computing, Georgia Institute of Technology,Atlanta,GA,USA,30308"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interactive Computing, Georgia Institute of Technology,Atlanta,GA,USA,30308","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008974159","display_name":"Ren Ping Liu","orcid":"https://orcid.org/0000-0001-7001-6305"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ren Liu","raw_affiliation_strings":["Meta Platforms, Inc.,USA","Meta Platforms, Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc.,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Meta Platforms, Inc., USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064581452","display_name":"Sehoon Ha","orcid":"https://orcid.org/0000-0002-1972-328X"},"institutions":[{"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":["School of Interactive Computing, Georgia Institute of Technology,Atlanta,GA,USA,30308"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interactive Computing, Georgia Institute of Technology,Atlanta,GA,USA,30308","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5614,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69177449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2768","last_page":"2775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12290","display_name":"Human Motion and Animation","score":0.9994999766349792,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.996999979019165,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7837194204330444},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7237828969955444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5946508049964905},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5675022006034851},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5373311042785645},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5237643122673035},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41362494230270386},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37398210167884827},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15523573756217957}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7837194204330444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7237828969955444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946508049964905},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5675022006034851},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5373311042785645},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5237643122673035},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41362494230270386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37398210167884827},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15523573756217957},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2137267908","https://openalex.org/W2161427949","https://openalex.org/W2593412525","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2779458783","https://openalex.org/W2788030459","https://openalex.org/W2796290181","https://openalex.org/W2801567109","https://openalex.org/W2861559353","https://openalex.org/W2909553221","https://openalex.org/W2911087563","https://openalex.org/W2972810470","https://openalex.org/W3004691725","https://openalex.org/W3039737909","https://openalex.org/W3048710353","https://openalex.org/W3093922502","https://openalex.org/W3104515094","https://openalex.org/W3104876774","https://openalex.org/W3108521017","https://openalex.org/W3111294788","https://openalex.org/W3147968035","https://openalex.org/W3175254947","https://openalex.org/W3181074849","https://openalex.org/W3184085787","https://openalex.org/W4205430897","https://openalex.org/W4226143977","https://openalex.org/W4229044820","https://openalex.org/W4283787029","https://openalex.org/W4309303752","https://openalex.org/W4312900898","https://openalex.org/W4380551489","https://openalex.org/W4381662572","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6767349745","https://openalex.org/W6773029903","https://openalex.org/W6801964084"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2389214306","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3213722473","https://openalex.org/W2110944602"],"abstract_inverted_index":{"Learning":[0],"various":[1],"motor":[2,121],"skills":[3,122],"for":[4],"quadrupedal":[5],"robots":[6],"is":[7],"a":[8,29,39,95,104],"challenging":[9,120],"problem":[10],"that":[11,129],"requires":[12],"careful":[13],"design":[14,64],"of":[15,42,55,79,87,154],"task-specific":[16],"mathematical":[17],"models":[18],"or":[19],"reward":[20,73],"descriptions.":[21],"In":[22,91],"this":[23],"work,":[24],"we":[25,61,93],"propose":[26],"to":[27,75,117],"learn":[28],"single":[30],"capable":[31],"policy":[32,132],"using":[33],"deep":[34],"reinforcement":[35],"learning":[36,81,115,157],"by":[37,139,165],"imitating":[38],"large":[40],"number":[41],"reference":[43],"motions,":[44],"including":[45],"walking,":[46],"turning,":[47],"pacing,":[48],"jumping,":[49],"sitting,":[50],"and":[51,71,108,123,146,159],"lying.":[52],"On":[53],"top":[54],"the":[56,65,68,72,77,80,85,88,114,130,143,152,155,160],"existing":[57],"motion":[58,98,162],"imitation":[59],"framework,":[60],"first":[62],"carefully":[63],"observation":[66],"space,":[67,70],"action":[69],"function":[74],"improve":[76],"scalability":[78],"as":[82,84],"well":[83],"robustness":[86],"final":[89],"policy.":[90],"addition,":[92],"adopt":[94],"novel":[96],"adaptive":[97,161],"sampling":[99,163],"(AMS)":[100],"method,":[101],"which":[102],"maintains":[103],"balance":[105],"between":[106],"successful":[107],"unsuccessful":[109],"behaviors.":[110],"This":[111],"technique":[112],"allows":[113],"algorithm":[116],"focus":[118],"on":[119],"avoid":[124],"catastrophic":[125],"forgetting.":[126],"We":[127,149],"demonstrate":[128],"learned":[131],"can":[133],"exhibit":[134],"diverse":[135],"behaviors":[136],"in":[137],"simulation":[138],"successfully":[140],"tracking":[141],"both":[142],"training":[144],"dataset":[145],"out-of-distribution":[147],"trajectories.":[148],"also":[150],"validate":[151],"importance":[153],"proposed":[156],"formulation":[158],"scheme":[164],"conducting":[166],"experiments.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}