{"id":"https://openalex.org/W3091471537","doi":"https://doi.org/10.1109/icra40945.2020.9197326","title":"Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulation","display_name":"Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulation","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3091471537","doi":"https://doi.org/10.1109/icra40945.2020.9197326","mag":"3091471537"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","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/A5079341248","display_name":"Rae Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Rae Jeong","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056410851","display_name":"Yusuf Aytar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yusuf Aytar","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038223239","display_name":"David Khosid","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Khosid","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102005803","display_name":"Yuxiang Zhou","orcid":"https://orcid.org/0000-0002-6484-745X"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuxiang Zhou","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052060244","display_name":"Jackie Kay","orcid":"https://orcid.org/0000-0001-9593-695X"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jackie Kay","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054636066","display_name":"Thomas Lampe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Lampe","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079462322","display_name":"Konstantinos Bousmalis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Konstantinos Bousmalis","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063532849","display_name":"Francesco Nori","orcid":"https://orcid.org/0000-0003-3763-6873"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francesco Nori","raw_affiliation_strings":["DeepMind, London, UK"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5079341248"],"corresponding_institution_ids":["https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":5.5038,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.96383943,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2718","last_page":"2724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9987000226974487,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976999759674072,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9954000115394592,"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":0.817245364189148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8030840754508972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7162995934486389},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5601577162742615},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5308875441551208},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4925878643989563},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4515508711338043},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.41996991634368896}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.817245364189148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030840754508972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7162995934486389},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5601577162742615},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5308875441551208},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4925878643989563},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4515508711338043},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.41996991634368896},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra40945.2020.9197326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","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":74,"referenced_works":["https://openalex.org/W1560270123","https://openalex.org/W1631623342","https://openalex.org/W1731081199","https://openalex.org/W1892837366","https://openalex.org/W1981667747","https://openalex.org/W2036637075","https://openalex.org/W2138621090","https://openalex.org/W2140173255","https://openalex.org/W2157364932","https://openalex.org/W2158782408","https://openalex.org/W2209762605","https://openalex.org/W2487442924","https://openalex.org/W2511131004","https://openalex.org/W2546190447","https://openalex.org/W2550462002","https://openalex.org/W2555897561","https://openalex.org/W2560647685","https://openalex.org/W2584009249","https://openalex.org/W2590953969","https://openalex.org/W2600030077","https://openalex.org/W2605102758","https://openalex.org/W2609990452","https://openalex.org/W2741122588","https://openalex.org/W2751276040","https://openalex.org/W2756073160","https://openalex.org/W2781585732","https://openalex.org/W2785738552","https://openalex.org/W2788781499","https://openalex.org/W2799087757","https://openalex.org/W2810785043","https://openalex.org/W2842511635","https://openalex.org/W2914688076","https://openalex.org/W2950069298","https://openalex.org/W2953127297","https://openalex.org/W2962715211","https://openalex.org/W2962736495","https://openalex.org/W2962787403","https://openalex.org/W2962899390","https://openalex.org/W2962957005","https://openalex.org/W2963027561","https://openalex.org/W2963099939","https://openalex.org/W2963390419","https://openalex.org/W2963484919","https://openalex.org/W2963713397","https://openalex.org/W2963740289","https://openalex.org/W2963884015","https://openalex.org/W2964118020","https://openalex.org/W2964127152","https://openalex.org/W2968116426","https://openalex.org/W2990747716","https://openalex.org/W2998115938","https://openalex.org/W3101442004","https://openalex.org/W3112422759","https://openalex.org/W4297808394","https://openalex.org/W4300198501","https://openalex.org/W6637618735","https://openalex.org/W6697071109","https://openalex.org/W6722416126","https://openalex.org/W6725448924","https://openalex.org/W6728854242","https://openalex.org/W6730323794","https://openalex.org/W6742461812","https://openalex.org/W6744354654","https://openalex.org/W6744564315","https://openalex.org/W6747387971","https://openalex.org/W6747924173","https://openalex.org/W6748523217","https://openalex.org/W6751955673","https://openalex.org/W6753243525","https://openalex.org/W6755561334","https://openalex.org/W6757358677","https://openalex.org/W6770858630","https://openalex.org/W6844194202","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2110944602","https://openalex.org/W3213722473"],"abstract_inverted_index":{"Collecting":[0],"and":[1,23,63,76,81,102,134,142,154,198,249],"automatically":[2],"obtaining":[3],"reward":[4],"signals":[5],"from":[6,49,184],"real":[7,71,108,112,143,156,207,237],"robotic":[8,38],"visual":[9,251],"data":[10,29,239],"for":[11,26,61,223,240,255],"the":[12,43,79,107,128,140,165,202,211],"purposes":[13],"of":[14,45,83,131,149,213,235],"training":[15,217],"reinforcement":[16,98,220],"learning":[17,99,174,221],"algorithms":[18],"can":[19,30,135,187],"be":[20,136,188],"quite":[21],"challenging":[22],"time-consuming.":[24],"Methods":[25],"utilizing":[27],"unlabeled":[28,111,155,236],"have":[31],"a":[32,91,161,193,206,218,243],"huge":[33],"potential":[34],"to":[35,106,117,190,199],"further":[36,159],"accelerate":[37],"learning.":[39],"We":[40,115,158,209],"consider":[41],"here":[42],"problem":[44],"performing":[46],"manipulation":[47,194],"tasks":[48],"pixels.":[50],"In":[51,86],"such":[52,163],"tasks,":[53],"choosing":[54],"an":[55],"appropriate":[56],"state":[57,84,93,180],"representation":[58,94,181],"is":[59,66],"crucial":[60],"planning":[62],"control.":[64],"This":[65],"even":[67],"more":[68],"relevant":[69],"with":[70,96,175,228],"images":[72],"where":[73],"noise,":[74],"occlusions":[75],"resolution":[77],"affect":[78],"accuracy":[80],"reliability":[82],"estimation.":[85],"this":[87],"work,":[88],"we":[89],"learn":[90],"latent":[92],"implicitly":[95],"deep":[97],"in":[100,138,152,196],"simulation,":[101],"then":[103],"adapt":[104],"it":[105],"domain":[109,247,252],"using":[110,231],"robot":[113,132,238],"data.":[114],"propose":[116,160],"do":[118],"so":[119],"by":[120,216],"optimizing":[121],"sequence-based":[122],"self-":[123],"supervised":[124],"objectives.":[125],"These":[126],"use":[127],"temporal":[129],"nature":[130],"experience,":[133],"common":[137],"both":[139],"simulated":[141,153],"domains,":[144],"without":[145],"assuming":[146],"any":[147],"alignment":[148],"underlying":[150],"states":[151],"images.":[157],"novel":[162],"objective,":[164],"Contrastive":[166],"Forward":[167],"Dynamics":[168],"loss,":[169],"which":[170],"combines":[171],"dynamics":[172],"model":[173],"time-contrastive":[176],"techniques.":[177],"The":[178],"learned":[179,203],"that":[182],"results":[183],"our":[185,214,229],"methods":[186],"used":[189],"robustly":[191],"solve":[192],"task":[195],"simulation":[197],"successfully":[200],"transfer":[201],"skill":[204],"on":[205],"system.":[208],"demonstrate":[210],"effectiveness":[212],"approaches":[215],"vision-based":[219],"agent":[222],"cube":[224],"stacking.":[225],"Agents":[226],"trained":[227],"method,":[230],"only":[232],"5":[233],"hours":[234],"adaptation,":[241],"shows":[242],"clear":[244],"improvement":[245],"over":[246],"randomization,":[248],"standard":[250],"adaptation":[253],"techniques":[254],"sim-to-real":[256],"transfer.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":8}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}