{"id":"https://openalex.org/W4416749952","doi":"https://doi.org/10.1109/iros60139.2025.11247723","title":"Towards Surgical Task Automation: Actor-Critic Models Meet Self-Supervised Imitation Learning <sup>*</sup>","display_name":"Towards Surgical Task Automation: Actor-Critic Models Meet Self-Supervised Imitation Learning <sup>*</sup>","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749952","doi":"https://doi.org/10.1109/iros60139.2025.11247723"},"language":"en","primary_location":{"id":"doi:10.1109/iros60139.2025.11247723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247723","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":"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/A5061256870","display_name":"Jingshuai Liu","orcid":"https://orcid.org/0009-0003-3104-3775"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingshuai Liu","raw_affiliation_strings":["the National Elite Institute of Engineering, Chongqing University,Embodied Intelligence Lab,Chongqing,China,401135"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"the National Elite Institute of Engineering, Chongqing University,Embodied Intelligence Lab,Chongqing,China,401135","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082466907","display_name":"Alain Andr\u00e9s","orcid":"https://orcid.org/0000-0002-4688-1304"},"institutions":[{"id":"https://openalex.org/I4210113430","display_name":"Tecnalia","ror":"https://ror.org/02fv8hj62","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210113430"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alain Andres","raw_affiliation_strings":["TECNALIA, Basque Research and Technology Alliance (BRTA),Donostia-San Sebastian,Spain,20009"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TECNALIA, Basque Research and Technology Alliance (BRTA),Donostia-San Sebastian,Spain,20009","institution_ids":["https://openalex.org/I4210113430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101486729","display_name":"Yonghang Jiang","orcid":"https://orcid.org/0000-0002-7823-0792"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yonghang Jiang","raw_affiliation_strings":["University of Strathclyde,Centre for Precision Manufacturing,Department of Design, Manufacturing and Engineering Management,Glasgow,U.K.,G1 1XJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Strathclyde,Centre for Precision Manufacturing,Department of Design, Manufacturing and Engineering Management,Glasgow,U.K.,G1 1XJ","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010944460","display_name":"Yuning Du","orcid":"https://orcid.org/0009-0007-4995-5472"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuning Du","raw_affiliation_strings":["University of Edinburgh,Institute for Imaging, Data and Communications, School of Engineering,Edinburgh,U.K.,EH9 3JE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Institute for Imaging, Data and Communications, School of Engineering,Edinburgh,U.K.,EH9 3JE","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054438489","display_name":"Xichun Luo","orcid":"https://orcid.org/0000-0002-5024-7058"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xichun Luo","raw_affiliation_strings":["University of Strathclyde,Centre for Precision Manufacturing,Department of Design, Manufacturing and Engineering Management,Glasgow,U.K.,G1 1XJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Strathclyde,Centre for Precision Manufacturing,Department of Design, Manufacturing and Engineering Management,Glasgow,U.K.,G1 1XJ","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048761326","display_name":"Wenmiao Shu","orcid":"https://orcid.org/0000-0002-1220-361X"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenmiao Shu","raw_affiliation_strings":["University of Strathclyde,Department of Biomedical Engineering,Glasgow,U.K.,G4 0NW"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Strathclyde,Department of Biomedical Engineering,Glasgow,U.K.,G4 0NW","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018304039","display_name":"Can Pu","orcid":"https://orcid.org/0000-0003-2758-4205"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Pu","raw_affiliation_strings":["the National Elite Institute of Engineering, Chongqing University,Embodied Intelligence Lab,Chongqing,China,401135"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"the National Elite Institute of Engineering, Chongqing University,Embodied Intelligence Lab,Chongqing,China,401135","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054437456","display_name":"Sotirios A. Tsaftaris","orcid":"https://orcid.org/0000-0002-8795-9294"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sotirios Tsaftaris","raw_affiliation_strings":["University of Edinburgh,Institute for Imaging, Data and Communications, School of Engineering,Edinburgh,U.K.,EH9 3JE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Institute for Imaging, Data and Communications, School of Engineering,Edinburgh,U.K.,EH9 3JE","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7981","last_page":"7988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.31200000643730164,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.31200000643730164,"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/T10916","display_name":"Surgical Simulation and Training","score":0.1492999941110611,"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":0.09369999915361404,"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/leverage","display_name":"Leverage (statistics)","score":0.6477000117301941},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5666000247001648},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5134999752044678},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49410000443458557},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4514000117778778},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4000999927520752},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.3515999913215637},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.3334999978542328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6990000009536743},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6477000117301941},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6434000134468079},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3398999869823456},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.3109000027179718},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros60139.2025.11247723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247723","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"},{"id":"pmh:oai:dsp.tecnalia.com:11556/11283","is_oa":false,"landing_page_url":"https://hdl.handle.net/11556/11283","pdf_url":null,"source":{"id":"https://openalex.org/S4306402037","display_name":"TECNALIA Publications (Fundaci\u00f3n TECNALIA Research & Innovation)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210113430","host_organization_name":"Tecnalia","host_organization_lineage":["https://openalex.org/I4210113430"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference output"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W1986014385","https://openalex.org/W2604382266","https://openalex.org/W2746553466","https://openalex.org/W2794908222","https://openalex.org/W2910913210","https://openalex.org/W2962787969","https://openalex.org/W2963099939","https://openalex.org/W2964460729","https://openalex.org/W2979863294","https://openalex.org/W3021855334","https://openalex.org/W3035073080","https://openalex.org/W3091703975","https://openalex.org/W3120101765","https://openalex.org/W3138516171","https://openalex.org/W3147968035","https://openalex.org/W3162578993","https://openalex.org/W3196757288","https://openalex.org/W3196843855","https://openalex.org/W3207864249","https://openalex.org/W3216656735","https://openalex.org/W4200553277","https://openalex.org/W4210909794","https://openalex.org/W4225306887","https://openalex.org/W4225379958","https://openalex.org/W4226092483","https://openalex.org/W4293363567","https://openalex.org/W4312578227","https://openalex.org/W4323914534","https://openalex.org/W4365421136","https://openalex.org/W4378191992","https://openalex.org/W4379931844","https://openalex.org/W4383097529","https://openalex.org/W4389665396","https://openalex.org/W4403984627","https://openalex.org/W4405145750"],"related_works":[],"abstract_inverted_index":{"Surgical":[0],"robot":[1],"task":[2],"automation":[3],"has":[4],"recently":[5],"attracted":[6],"great":[7],"attention":[8],"due":[9],"to":[10,13,28,46,76,86,128,149,174],"its":[11,206],"potential":[12,248],"benefit":[14],"both":[15,65],"surgeons":[16],"and":[17,67,125,193,204,234,247],"patients.":[18],"Reinforcement":[19],"learning":[20,49,53,155,255],"(RL)":[21],"based":[22,240],"approaches":[23],"have":[24],"demonstrated":[25],"promising":[26],"ability":[27],"perform":[29],"automated":[30],"surgical":[31,105,221],"manipulations":[32],"on":[33,64,218],"various":[34],"tasks.":[35],"To":[36],"address":[37],"the":[38,48,57,87,186,190,195,211,231,245],"exploration":[39],"challenge,":[40],"expert":[41,90,93,130,164,177,253],"demonstrations":[42,159,185],"can":[43,73],"be":[44,74,259],"utilized":[45],"enhance":[47],"efficiency":[50],"via":[51],"imitation":[52],"(IL)":[54],"approaches.":[55],"However,":[56],"successes":[58],"of":[59,133,153,189,197,249],"such":[60],"methods":[61],"normally":[62],"rely":[63],"states":[66,135,178],"action":[68,71,239],"labels.":[69],"Unfortunately,":[70],"labels":[72,99],"hard":[75],"capture":[77],"or":[78,97],"their":[79],"manual":[80],"annotation":[81],"is":[82],"prohibitively":[83],"expensive":[84],"owing":[85],"requirement":[88],"for":[89,252],"knowledge.":[91],"Emulating":[92],"behaviour":[94],"using":[95],"noisy":[96],"inaccurate":[98],"poses":[100],"significant":[101],"risks,":[102],"including":[103],"unintended":[104],"errors":[106],"that":[107,224],"may":[108],"result":[109],"in":[110,114],"patient":[111],"discomfort":[112],"or,":[113],"more":[115],"severe":[116],"cases,":[117],"tissue":[118],"damage.":[119],"It":[120,166,200],"therefore":[121],"remains":[122],"an":[123,143,162,219],"appealing":[124],"open":[126],"problem":[127],"leverage":[129],"data":[131],"composed":[132],"pure":[134],"into":[136,179],"RL.":[137],"In":[138],"this":[139,151],"work,":[140],"we":[141],"present":[142],"actor-critic":[144],"RL":[145,180,232],"framework,":[146],"termed":[147],"AC-SSIL,":[148],"overcome":[150],"challenge":[152],"improving":[154],"process":[156],"with":[157,210],"state-only":[158],"collected":[160],"by":[161,182],"unknown":[163],"policy.":[165],"adopts":[167],"a":[168],"self-supervised":[169],"IL":[170,241],"method,":[171],"dubbed":[172],"SSIL,":[173],"effectively":[175],"incorporate":[176],"paradigms":[181],"retrieving":[183],"from":[184],"nearest":[187],"neighbours":[188],"query":[191],"state":[192],"utilizing":[194],"bootstrapping":[196],"actor":[198,212],"networks.":[199],"applies":[201],"similarity-based":[202],"regularization":[203],"improves":[205],"prediction":[207],"capacity":[208],"jointly":[209],"network.":[213],"We":[214],"showcase":[215],"through":[216],"experiments":[217],"open-source":[220],"simulation":[222],"platform":[223],"our":[225,250],"method":[226,251],"delivers":[227],"remarkable":[228],"improvements":[229],"over":[230],"baseline":[233],"exhibits":[235],"comparable":[236],"performance":[237],"against":[238],"methods,":[242],"which":[243],"implies":[244],"efficacy":[246],"demonstration-guided":[254],"scenarios.":[256],"Code":[257],"will":[258],"made":[260],"publicly":[261],"available":[262],"at":[263],"https://github.com/Jingshuai-cqu/AC-SSIL.":[264]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}