{"id":"https://openalex.org/W4390730760","doi":"https://doi.org/10.1109/tai.2024.3351797","title":"Learn From Safe Experience: Safe Reinforcement Learning for Task Automation of Surgical Robot","display_name":"Learn From Safe Experience: Safe Reinforcement Learning for Task Automation of Surgical Robot","publication_year":2024,"publication_date":"2024-01-09","ids":{"openalex":"https://openalex.org/W4390730760","doi":"https://doi.org/10.1109/tai.2024.3351797"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2024.3351797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3351797","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Transactions on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://re.public.polimi.it/bitstream/11311/1276402/2/Learn_From_Safe_Experience_Safe_Reinforcement_Learning_for_Task_Automation_of_Surgical_Robot%20%281%29.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051129466","display_name":"Ke Fan","orcid":"https://orcid.org/0009-0007-1718-9312"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Ke Fan","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324492","display_name":"Ziyang Chen","orcid":"https://orcid.org/0000-0003-3077-822X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ziyang Chen","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045080493","display_name":"Giancarlo Ferrigno","orcid":"https://orcid.org/0000-0001-5913-9451"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giancarlo Ferrigno","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083795699","display_name":"Elena De Momi","orcid":"https://orcid.org/0000-0002-8819-2734"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elena De Momi","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051129466"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":12.6509,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.99064259,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"5","issue":"7","first_page":"3374","last_page":"3383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11773","display_name":"Healthcare Operations and Scheduling Optimization","score":0.9624000191688538,"subfield":{"id":"https://openalex.org/subfields/3604","display_name":"Emergency Medical Services"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11773","display_name":"Healthcare Operations and Scheduling Optimization","score":0.9624000191688538,"subfield":{"id":"https://openalex.org/subfields/3604","display_name":"Emergency Medical Services"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10916","display_name":"Surgical Simulation and Training","score":0.9605000019073486,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8055051565170288},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6545959115028381},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6234859228134155},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.6016486287117004},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.597038745880127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5258289575576782},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5122867822647095},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36120784282684326},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3503198027610779},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18119555711746216},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09229734539985657}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8055051565170288},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6545959115028381},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6234859228134155},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.6016486287117004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.597038745880127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5258289575576782},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5122867822647095},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36120784282684326},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3503198027610779},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18119555711746216},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09229734539985657},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tai.2024.3351797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3351797","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Transactions on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1276402","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1276402","pdf_url":"https://re.public.polimi.it/bitstream/11311/1276402/2/Learn_From_Safe_Experience_Safe_Reinforcement_Learning_for_Task_Automation_of_Surgical_Robot%20%281%29.pdf","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:re.public.polimi.it:11311/1276402","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1276402","pdf_url":"https://re.public.polimi.it/bitstream/11311/1276402/2/Learn_From_Safe_Experience_Safe_Reinforcement_Learning_for_Task_Automation_of_Surgical_Robot%20%281%29.pdf","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390730760.pdf","grobid_xml":"https://content.openalex.org/works/W4390730760.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W2089145243","https://openalex.org/W2736601468","https://openalex.org/W2784465508","https://openalex.org/W2892521964","https://openalex.org/W2911024029","https://openalex.org/W2913300629","https://openalex.org/W2923090615","https://openalex.org/W2941276819","https://openalex.org/W2962872206","https://openalex.org/W2963293747","https://openalex.org/W2963525569","https://openalex.org/W2968547875","https://openalex.org/W2973815009","https://openalex.org/W2991391803","https://openalex.org/W3009198376","https://openalex.org/W3038822267","https://openalex.org/W3090211586","https://openalex.org/W3091691175","https://openalex.org/W3094103188","https://openalex.org/W3103266692","https://openalex.org/W3117330837","https://openalex.org/W3126321819","https://openalex.org/W3150718622","https://openalex.org/W3162439934","https://openalex.org/W3195968524","https://openalex.org/W3198013102","https://openalex.org/W4281480521","https://openalex.org/W4285076891","https://openalex.org/W4293049973","https://openalex.org/W4317038451","https://openalex.org/W4317794519","https://openalex.org/W4361855665","https://openalex.org/W4382119111","https://openalex.org/W4382317755","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6747790125","https://openalex.org/W6751535212","https://openalex.org/W6758924645","https://openalex.org/W6760425463","https://openalex.org/W6801971982","https://openalex.org/W6838701874"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2992534160","https://openalex.org/W1595058678","https://openalex.org/W3022812046","https://openalex.org/W2745830841","https://openalex.org/W2110944602","https://openalex.org/W3213722473","https://openalex.org/W3112082055"],"abstract_inverted_index":{"Surgical":[0],"task":[1,142,186],"automation":[2],"in":[3,26,30,49,109,143,185],"robotics":[4],"can":[5,66],"improve":[6],"the":[7,75,80,96,100,106,110,114,148,160],"outcomes,":[8],"reduce":[9],"quality-of-care":[10],"variance":[11],"among":[12],"surgeons":[13],"and":[14,78,138,167,182],"relieve":[15],"surgeons\u2019":[16],"fatigue.":[17],"Reinforcement":[18],"learning":[19],"(RL)":[20],"methods":[21,163],"have":[22],"shown":[23],"considerable":[24],"performance":[25,184],"robot":[27],"autonomous":[28],"control":[29],"complex":[31],"environments.":[32],"However,":[33],"existing":[34],"RL":[35,72,150,162],"algorithms":[36],"for":[37,120],"surgical":[38,51,132],"robots":[39],"do":[40],"not":[41],"consider":[42],"any":[43,70],"safety":[44],"requirements,":[45],"which":[46,103],"is":[47,88,108],"unacceptable":[48],"automating":[50],"tasks.":[52],"In":[53],"this":[54],"work,":[55],"we":[56],"propose":[57],"an":[58,92],"approach":[59],"called":[60],"Safe":[61],"Experience":[62],"Reshaping":[63],"(SER)":[64],"that":[65,105,128,172],"be":[67],"integrated":[68],"into":[69],"offline":[71],"algorithm.":[73],"Firstly,":[74],"method":[76],"identifies":[77],"learns":[79],"geometry":[81],"of":[82,99,159,179],"constraints.":[83],"Secondly,":[84],"a":[85,139,176,190],"safe":[86,111,116,121,149],"experience":[87],"obtained":[89],"by":[90],"projecting":[91],"unsafe":[93],"action":[94,107],"to":[95,146,156],"tangent":[97],"space":[98,145],"learned":[101],"geometry,":[102],"means":[104],"space.":[112],"Then,":[113],"collected":[115],"experiences":[117],"are":[118],"used":[119],"policy":[122],"training.":[123],"We":[124,152],"designed":[125],"3":[126],"tasks":[127,133,137],"closely":[129],"resemble":[130],"real":[131],"including":[134,164],"2D":[135],"cutting":[136],"contact-rich":[140],"debridement":[141],"3D":[144],"evaluate":[147],"framework.":[151],"compare":[153],"our":[154,173],"framework":[155,174],"5":[157],"state":[158],"art":[161],"reward":[165],"penalty":[166],"primal-dual":[168],"methods.":[169],"Results":[170],"show":[171],"gets":[175],"lower":[177],"rate":[178],"constraint":[180],"violations":[181],"better":[183],"success,":[187],"especially":[188],"with":[189],"higher":[191],"convergence":[192],"speed.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}