{"id":"https://openalex.org/W7138851455","doi":"https://doi.org/10.1109/lra.2026.3675962","title":"Cosmos-Surg-DVRK: World Foundation Model-Based Automated Online Evaluation of Surgical Robot Policy Learning","display_name":"Cosmos-Surg-DVRK: World Foundation Model-Based Automated Online Evaluation of Surgical Robot Policy Learning","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7138851455","doi":"https://doi.org/10.1109/lra.2026.3675962"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3675962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3675962","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5027911708","display_name":"Lukas Zbinden","orcid":"https://orcid.org/0000-0003-0681-6476"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lukas Zbinden","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0681-6476","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077018822","display_name":"Nigel Nelson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nigel Nelson","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015249061","display_name":"Juo-Tung Chen","orcid":"https://orcid.org/0009-0002-5118-6610"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juo-Tung Chen","raw_affiliation_strings":["Department of Mechanical Engineering and the Laboratory of Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0009-0002-5118-6610","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering and the Laboratory of Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129911972","display_name":"Xinhao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinhao Chen","raw_affiliation_strings":["Department of Mechanical Engineering and the Laboratory of Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0009-0007-7381-4127","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering and the Laboratory of Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129759158","display_name":"Ji Woong Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji Woong Kim","raw_affiliation_strings":["Department of Mechanical Engineering and the Laboratory of Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-8669-205X","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering and the Laboratory of Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129795659","display_name":"Mahdi Azizian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahdi Azizian","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129875490","display_name":"Axel Krieger","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Axel Krieger","raw_affiliation_strings":["Department of Mechanical Engineering and the Laboratory of Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-8169-075X","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering and the Laboratory of Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046621825","display_name":"Sean D. Huver","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Huver","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0048-3669","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5027911708"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":24.5726,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99140676,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"11","issue":"5","first_page":"5978","last_page":"5985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.6491000056266785,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.6491000056266785,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.24609999358654022,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01489999983459711,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7045000195503235},{"id":"https://openalex.org/keywords/surgical-robot","display_name":"Surgical robot","score":0.5680000185966492},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5361999869346619},{"id":"https://openalex.org/keywords/surgical-planning","display_name":"Surgical planning","score":0.4154999852180481},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.412200003862381},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3939000070095062},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.38609999418258667},{"id":"https://openalex.org/keywords/robotic-surgery","display_name":"Robotic surgery","score":0.3662000000476837}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7045000195503235},{"id":"https://openalex.org/C3017684034","wikidata":"https://www.wikidata.org/wiki/Q942348","display_name":"Surgical robot","level":3,"score":0.5680000185966492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5582000017166138},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5361999869346619},{"id":"https://openalex.org/C2779370443","wikidata":"https://www.wikidata.org/wiki/Q1776627","display_name":"Surgical planning","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40290001034736633},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C103203806","wikidata":"https://www.wikidata.org/wiki/Q942348","display_name":"Robotic surgery","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C3019611579","wikidata":"https://www.wikidata.org/wiki/Q6641956","display_name":"Surgical procedures","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3555999994277954},{"id":"https://openalex.org/C3018608816","wikidata":"https://www.wikidata.org/wiki/Q195818","display_name":"Surgical simulation","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C152086174","wikidata":"https://www.wikidata.org/wiki/Q3030571","display_name":"Haptic technology","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2779891985","wikidata":"https://www.wikidata.org/wiki/Q46994","display_name":"Telemedicine","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C2777327002","wikidata":"https://www.wikidata.org/wiki/Q2865760","display_name":"Fibrous joint","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3675962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3675962","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rise":[1],"of":[2,76,86,104],"robot-assisted":[3],"surgery":[4],"and":[5,16,46,102,135,152,177],"vision":[6],"language-action":[7],"models":[8,52],"has":[9],"accelerated":[10],"progress":[11],"in":[12,48,133],"autonomous":[13],"surgical":[14,65,84,105,117,165,188],"policies":[15,23],"efficient":[17],"assessment":[18],"strategies.":[19],"However,":[20],"evaluating":[21],"these":[22],"directly":[24],"on":[25,138],"physical":[26,55],"robotic":[27],"platforms":[28],"such":[29,67],"as":[30,68,144,146],"the":[31,87,124,139,153,162,182],"da":[32],"Vinci":[33],"Research":[34],"Kit":[35],"(dVRK)":[36],"remains":[37],"hindered":[38],"by":[39],"high":[40,74],"costs,":[41],"time":[42],"demands,":[43],"reproducibility":[44],"challenges,":[45],"variability":[47],"execution.":[49],"World":[50],"foundation":[51],"(WFM)":[53],"for":[54,167,185],"AI":[56],"offer":[57],"a":[58,73,83,93],"transformative":[59],"approach":[60],"to":[61],"simulate":[62],"complex":[63,187],"real-world":[64,178],"tasks,":[66,123],"soft":[69],"tissue":[70],"deformation,":[71],"with":[72,92],"degree":[75],"realism.":[77],"This":[78],"work":[79],"introduces":[80],"Cosmos-Surg":[81],"dVRK,":[82],"finetune":[85],"Cosmos":[88],"WFM,":[89],"which,":[90],"together":[91],"trained":[94],"video":[95,156],"classifier,":[96],"enables":[97],"fully":[98],"automated":[99,125],"online":[100,131],"evaluation":[101],"benchmarking":[103],"policies.":[106],"We":[107],"evaluate":[108],"Cosmos-Surg-dVRK":[109,134,176],"using":[110,161],"two":[111],"independent,":[112],"teleoperated,":[113],"real":[114,140],"world":[115],"dVRK":[116,141,179],"datasets.":[118],"On":[119],"tabletop":[120],"suture":[121],"pad":[122],"pipeline":[126],"achieves":[127],"strong":[128],"correlation":[129],"between":[130,149,175],"rollouts":[132],"policy":[136,166],"outcomes":[137],"Si":[142],"platform,":[143],"well":[145],"good":[147],"agreement":[148],"human":[150],"labelers":[151],"V-JEPA":[154],"2-derived":[155],"classifier.":[157],"Additionally,":[158],"preliminary":[159],"experiments":[160],"state-of-the-art":[163],"SRT-H":[164],"ex-vivo":[168],"porcine":[169],"cholecystectomy":[170],"tasks":[171],"demonstrate":[172],"promising":[173],"alignment":[174],"evaluations,":[180],"highlighting":[181],"platform's":[183],"potential":[184],"more":[186],"procedures.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2026-03-20T00:00:00"}