{"id":"https://openalex.org/W4416748706","doi":"https://doi.org/10.1109/iros60139.2025.11246873","title":"LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots","display_name":"LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748706","doi":"https://doi.org/10.1109/iros60139.2025.11246873"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5101947561","display_name":"Pei\u2010Lin Wu","orcid":"https://orcid.org/0009-0000-1447-220X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peilin Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104253488","display_name":"Weiji Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiji Xie","raw_affiliation_strings":["Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015422529","display_name":"Jiahang Cao","orcid":"https://orcid.org/0000-0003-4338-4414"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahang Cao","raw_affiliation_strings":["Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789061","display_name":"Hang Lai","orcid":"https://orcid.org/0000-0003-1000-3232"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Lai","raw_affiliation_strings":["Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102020194","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0001-5893-1543"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Dept. of Computer Sci. and Eng.,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101947561"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35080725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5649","last_page":"5656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9746000170707703,"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":0.9746000170707703,"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/T12290","display_name":"Human Motion and Animation","score":0.005100000184029341,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7258999943733215},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6743999719619751},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5245000123977661},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45570001006126404},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.43630000948905945},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.43320000171661377},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4101000130176544},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4047999978065491},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3278999924659729}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7258999943733215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247999906539917},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6743999719619751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5942000150680542},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5357999801635742},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5245000123977661},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.27309998869895935},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2100483895","https://openalex.org/W2151554678","https://openalex.org/W2158782408","https://openalex.org/W2163922914","https://openalex.org/W2605102758","https://openalex.org/W2736601468","https://openalex.org/W2767050701","https://openalex.org/W2790924949","https://openalex.org/W2946165673","https://openalex.org/W2963184939","https://openalex.org/W2964048876","https://openalex.org/W2964262254","https://openalex.org/W3093922502","https://openalex.org/W3096655658","https://openalex.org/W3171007011","https://openalex.org/W3175254947","https://openalex.org/W3204973825","https://openalex.org/W3207033168","https://openalex.org/W4229044820","https://openalex.org/W4252189904","https://openalex.org/W4252279978","https://openalex.org/W4312900898","https://openalex.org/W4382365373","https://openalex.org/W4383108274","https://openalex.org/W4383112908","https://openalex.org/W4385430550","https://openalex.org/W4393160024","https://openalex.org/W4401413712","https://openalex.org/W4405786844"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"shown":[4],"its":[5],"remarkable":[6],"and":[7,87,101,160],"generalizable":[8],"capability":[9],"in":[10,38,70,157],"legged":[11],"locomotion":[12],"through":[13],"sim-to-real":[14,161],"transfer.":[15],"However,":[16],"while":[17],"adaptive":[18],"methods":[19,104],"like":[20],"domain":[21],"randomization":[22],"are":[23,105,119],"expected":[24],"to":[25,43,48,79,107],"enhance":[26,108],"policy":[27,62],"robustness":[28],"across":[29],"diverse":[30],"environments,":[31],"they":[32],"potentially":[33],"compromise":[34],"the":[35,49,71,93,126],"policy\u2019s":[36],"performance":[37,153],"any":[39],"specific":[40],"environment,":[41],"leading":[42],"suboptimal":[44],"real-world":[45,81,112],"deployment":[46],"due":[47],"No":[50],"Free":[51],"Lunch":[52],"Theorem.":[53],"To":[54],"address":[55],"this,":[56],"we":[57],"propose":[58],"LoopSR,":[59],"a":[60,76,84,89,132],"lifelong":[61],"adaptation":[63],"framework":[64],"that":[65],"continuously":[66],"refines":[67],"RL":[68],"policies":[69],"post-deployment":[72],"stage.":[73],"LoopSR":[74,142],"employs":[75],"transformer-based":[77],"encoder":[78],"map":[80],"trajectories":[82],"into":[83],"latent":[85],"space":[86],"reconstruct":[88],"digital":[90],"twin":[91],"of":[92,111],"real":[94],"world":[95],"for":[96,116],"further":[97],"improvement.":[98],"Autoencoder":[99],"architecture":[100],"contrastive":[102],"learning":[103],"adopted":[106],"feature":[109],"extraction":[110],"dynamics.":[113],"Simulation":[114],"parameters":[115,130],"continual":[117,140],"training":[118],"derived":[120],"by":[121],"combining":[122],"predicted":[123],"values":[124],"from":[125,131],"decoder":[127],"with":[128,148,154],"retrieved":[129],"pre-collected":[133],"simulation":[134],"trajectory":[135],"dataset.":[136],"By":[137],"leveraging":[138],"simulated":[139],"training,":[141],"achieves":[143],"superior":[144],"data":[145,156],"efficiency":[146],"compared":[147],"strong":[149],"baselines,":[150],"yielding":[151],"eminent":[152],"limited":[155],"both":[158],"sim-to-sim":[159],"experiments.":[162]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}