{"id":"https://openalex.org/W4400579720","doi":"https://doi.org/10.1109/ismr63436.2024.10585785","title":"Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery","display_name":"Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4400579720","doi":"https://doi.org/10.1109/ismr63436.2024.10585785"},"language":"en","primary_location":{"id":"doi:10.1109/ismr63436.2024.10585785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismr63436.2024.10585785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Symposium on Medical Robotics (ISMR)","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/A5095375482","display_name":"Zohre Karimi","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zohre Karimi","raw_affiliation_strings":["Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112"],"affiliations":[{"raw_affiliation_string":"Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111255293","display_name":"Shing-Hei Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shing-Hei Ho","raw_affiliation_strings":["Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112"],"affiliations":[{"raw_affiliation_string":"Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085696250","display_name":"Bao Thach","orcid":"https://orcid.org/0009-0000-1128-8933"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bao Thach","raw_affiliation_strings":["Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112"],"affiliations":[{"raw_affiliation_string":"Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068912132","display_name":"Alan Kuntz","orcid":"https://orcid.org/0000-0003-0017-3932"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Kuntz","raw_affiliation_strings":["Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112"],"affiliations":[{"raw_affiliation_string":"Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103065575","display_name":"Daniel S. Brown","orcid":"https://orcid.org/0000-0002-9570-1832"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S. Brown","raw_affiliation_strings":["Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112"],"affiliations":[{"raw_affiliation_string":"Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5095375482"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":3.4759,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93157924,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"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/T10320","display_name":"Neural Networks and Applications","score":0.5548999905586243,"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/T10320","display_name":"Neural Networks and Applications","score":0.5548999905586243,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.5180000066757202,"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/computer-science","display_name":"Computer science","score":0.5833322405815125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5833322405815125}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ismr63436.2024.10585785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismr63436.2024.10585785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Symposium on Medical Robotics (ISMR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3621613035","display_name":null,"funder_award_id":"2133027","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W52153049","https://openalex.org/W1968067754","https://openalex.org/W1986014385","https://openalex.org/W2058990466","https://openalex.org/W2061417916","https://openalex.org/W2079017518","https://openalex.org/W2100790457","https://openalex.org/W2129741456","https://openalex.org/W2167224731","https://openalex.org/W2188053957","https://openalex.org/W2736410800","https://openalex.org/W2736601468","https://openalex.org/W2736750746","https://openalex.org/W2883140436","https://openalex.org/W2994446013","https://openalex.org/W3005496249","https://openalex.org/W3006334608","https://openalex.org/W3016521739","https://openalex.org/W3085438050","https://openalex.org/W3096597946","https://openalex.org/W3118688377","https://openalex.org/W3130448017","https://openalex.org/W3138984732","https://openalex.org/W3198013102","https://openalex.org/W3200480656","https://openalex.org/W3205960420","https://openalex.org/W3207352324","https://openalex.org/W3214314028","https://openalex.org/W3216057396","https://openalex.org/W4226137952","https://openalex.org/W4226278401","https://openalex.org/W4285808854","https://openalex.org/W4313598235","https://openalex.org/W4321392130","https://openalex.org/W4383066631","https://openalex.org/W6679159026","https://openalex.org/W6684338915","https://openalex.org/W6739585900","https://openalex.org/W6741002519","https://openalex.org/W6748210908","https://openalex.org/W6755437240","https://openalex.org/W6755946096","https://openalex.org/W6761908843","https://openalex.org/W6769174716","https://openalex.org/W6778229956","https://openalex.org/W6796210719","https://openalex.org/W6804126621","https://openalex.org/W6805042473","https://openalex.org/W6810339684","https://openalex.org/W6810738896","https://openalex.org/W6848774067"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Automating":[0],"robotic":[1],"surgery":[2],"via":[3],"learning":[4,94],"from":[5,66],"demonstration":[6],"(LfD)":[7],"techniques":[8],"is":[9,13,108],"extremely":[10],"challenging.":[11],"This":[12,54],"because":[14],"surgical":[15,122],"tasks":[16],"often":[17],"involve":[18],"sequential":[19],"decision-making":[20],"processes":[21],"with":[22],"complex":[23],"interactions":[24],"of":[25,70,75],"physical":[26,121],"objects":[27],"and":[28,43,125,140,148],"have":[29],"low":[30],"tolerance":[31],"for":[32],"mistakes.":[33],"Prior":[34],"works":[35],"assume":[36],"that":[37,60,98,127],"all":[38],"demonstrations":[39,73,137],"are":[40,138,143],"fully":[41],"observable":[42],"optimal,":[44],"which":[45],"might":[46],"not":[47],"be":[48],"practical":[49],"in":[50],"the":[51,88,135,141],"real":[52],"world.":[53],"paper":[55],"introduces":[56],"a":[57,62,67,84,100,106,120],"sample-efficient":[58],"method":[59,81,129],"learns":[61,83],"robust":[63,110],"reward":[64,90,102],"function":[65,91,103],"limited":[68],"amount":[69],"ranked":[71],"suboptimal":[72,139],"consisting":[74],"partial-view":[76],"point":[77,145],"cloud":[78],"observations.":[79],"The":[80],"then":[82],"policy":[85,107],"by":[86],"optimizing":[87],"learned":[89,101],"using":[92,99],"reinforcement":[93],"(RL).":[95],"We":[96,115],"show":[97],"to":[104],"obtain":[105],"more":[109],"than":[111],"pure":[112],"imitation":[113],"learning.":[114],"apply":[116],"our":[117,128],"approach":[118],"on":[119],"electrocautery":[123],"task":[124],"demonstrate":[126],"can":[130],"perform":[131],"well":[132],"even":[133],"when":[134],"provided":[136],"observations":[142],"high-dimensional":[144],"clouds.":[146],"Code":[147],"videos":[149],"available":[150],"here:":[151],"https://sites.google.com/viewllfdinelectrocautery":[152]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2024-07-13T00:00:00"}