{"id":"https://openalex.org/W4378191992","doi":"https://doi.org/10.1109/ismr57123.2023.10130214","title":"Towards Safe and Efficient Reinforcement Learning for Surgical Robots Using Real-Time Human Supervision and Demonstration","display_name":"Towards Safe and Efficient Reinforcement Learning for Surgical Robots Using Real-Time Human Supervision and Demonstration","publication_year":2023,"publication_date":"2023-04-19","ids":{"openalex":"https://openalex.org/W4378191992","doi":"https://doi.org/10.1109/ismr57123.2023.10130214"},"language":"en","primary_location":{"id":"doi:10.1109/ismr57123.2023.10130214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismr57123.2023.10130214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Symposium on Medical Robotics (ISMR)","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/A5023350625","display_name":"Yafei Ou","orcid":"https://orcid.org/0000-0002-2989-9991"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yafei Ou","raw_affiliation_strings":["University of Alberta,Department of Electrical and Computer Engineering,Edmonton,Alberta,Canada","Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Electrical and Computer Engineering,Edmonton,Alberta,Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018636421","display_name":"Mahdi Tavakoli","orcid":"https://orcid.org/0000-0002-7427-6961"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mahdi Tavakoli","raw_affiliation_strings":["University of Alberta,Department of Electrical and Computer Engineering,Edmonton,Alberta,Canada","Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Electrical and Computer Engineering,Edmonton,Alberta,Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":3.9236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.94160296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9961000084877014,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9961000084877014,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958999752998352,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/teleoperation","display_name":"Teleoperation","score":0.8381587266921997},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7294288277626038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6953521966934204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.661473274230957},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.622353732585907},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6108561158180237},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5015377998352051},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5003550052642822},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4549923837184906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44756758213043213},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44721415638923645},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42031794786453247},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.17254361510276794}],"concepts":[{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.8381587266921997},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7294288277626038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6953521966934204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.661473274230957},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.622353732585907},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6108561158180237},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5015377998352051},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5003550052642822},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4549923837184906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44756758213043213},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44721415638923645},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42031794786453247},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.17254361510276794},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ismr57123.2023.10130214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismr57123.2023.10130214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Symposium on Medical Robotics (ISMR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2061417916","https://openalex.org/W2098441518","https://openalex.org/W2294663507","https://openalex.org/W2569211358","https://openalex.org/W2736629007","https://openalex.org/W2771846824","https://openalex.org/W2904246096","https://openalex.org/W2908355393","https://openalex.org/W2923090615","https://openalex.org/W2946088430","https://openalex.org/W2963277051","https://openalex.org/W2963489214","https://openalex.org/W2965413745","https://openalex.org/W2969201578","https://openalex.org/W3000681444","https://openalex.org/W3133389372","https://openalex.org/W3150718622","https://openalex.org/W3189250457","https://openalex.org/W3196757288","https://openalex.org/W3205960420","https://openalex.org/W4223568377","https://openalex.org/W4224864419","https://openalex.org/W4225515713","https://openalex.org/W4226137952","https://openalex.org/W4282944694","https://openalex.org/W4283694278","https://openalex.org/W6674812091","https://openalex.org/W6683397050","https://openalex.org/W6718092244","https://openalex.org/W6756482612","https://openalex.org/W6757592117","https://openalex.org/W6760425463","https://openalex.org/W6840338355"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W3119422923"],"abstract_inverted_index":{"Recent":[0],"research":[1],"in":[2,13,30],"surgical":[3,33,58,78],"robotics":[4],"has":[5,26],"focused":[6],"on":[7,94],"increasing":[8],"the":[9,17,51,74,95],"level":[10],"of":[11,19,43,97],"autonomy":[12],"order":[14],"to":[15,36,57,81,107],"reduce":[16],"workload":[18],"surgeons.":[20],"While":[21],"deep":[22],"reinforcement":[23],"learning":[24,48,80,103,110],"(DRL)":[25],"shown":[27],"promising":[28],"results":[29],"automating":[31],"some":[32],"subtasks,":[34],"due":[35],"its":[37],"demand":[38],"for":[39,77],"a":[40,66],"large":[41],"number":[42],"random":[44],"explorations,":[45],"safety":[46],"and":[47,85,99,140,144],"efficiency":[49,111],"remain":[50],"primary":[52],"challenges":[53],"when":[54],"applying":[55],"it":[56],"robot":[59,79],"learning.":[60,146],"In":[61],"this":[62],"work,":[63],"we":[64],"present":[65],"DRL":[67,98],"framework":[68],"with":[69],"real-time":[70],"human":[71,114,126],"supervision":[72],"during":[73],"training":[75,91],"process":[76],"avoid":[82],"significant":[83],"failures":[84],"speed":[86],"up":[87],"training.":[88],"A":[89],"novel":[90],"methodology":[92],"based":[93],"combination":[96],"generative":[100],"adversarial":[101],"imitation":[102],"(GAIL)":[104],"is":[105,119,128],"proposed":[106,117],"further":[108],"improve":[109],"by":[112],"imitating":[113],"behaviors.":[115],"The":[116],"method":[118,136],"validated":[120],"using":[121],"two":[122],"simulated":[123],"environments,":[124],"where":[125],"intervention":[127],"performed":[129],"via":[130],"teleoperation.":[131],"Results":[132],"show":[133],"that":[134],"our":[135],"outperforms":[137],"baseline":[138],"algorithms":[139],"can":[141],"achieve":[142],"safe":[143],"efficient":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}