{"id":"https://openalex.org/W4383097529","doi":"https://doi.org/10.1109/icra48891.2023.10160327","title":"Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot","display_name":"Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383097529","doi":"https://doi.org/10.1109/icra48891.2023.10160327"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5068307801","display_name":"Tao Huang","orcid":"https://orcid.org/0000-0002-5504-7848"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tao Huang","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Computer Science and Engineering","Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437922","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-5727-385X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Computer Science and Engineering","Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365257","display_name":"Bin Li","orcid":"https://orcid.org/0000-0003-1684-8869"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering","Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707660","display_name":"Yunhui Liu","orcid":"https://orcid.org/0000-0002-3625-6679"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yun-Hui Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering","Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Mechanical and Automation Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090516040","display_name":"Qi Dou","orcid":"https://orcid.org/0000-0002-3416-9950"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qi Dou","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Computer Science and Engineering","Department of Computer Science and Engineering, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4640","last_page":"4647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9970999956130981,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9854000210762024,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9837999939918518,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7980777025222778},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.7849093675613403},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7345384955406189},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7149631977081299},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7040572166442871},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6273521184921265},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5096759796142578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5022614002227783},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46459531784057617},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4138169586658478},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.35774677991867065},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.14778923988342285},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14052528142929077},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10470607876777649},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0771310031414032}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7980777025222778},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.7849093675613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7345384955406189},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7149631977081299},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7040572166442871},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6273521184921265},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5096759796142578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022614002227783},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46459531784057617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4138169586658478},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.35774677991867065},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.14778923988342285},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14052528142929077},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10470607876777649},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0771310031414032},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2657083500","display_name":null,"funder_award_id":"ITS/237/21FP","funder_id":"https://openalex.org/F4320322942","funder_display_name":"Chinese University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":84,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1584687743","https://openalex.org/W1986014385","https://openalex.org/W2001104271","https://openalex.org/W2098774185","https://openalex.org/W2125511732","https://openalex.org/W2174803659","https://openalex.org/W2502094132","https://openalex.org/W2735048916","https://openalex.org/W2736750746","https://openalex.org/W2741122588","https://openalex.org/W2746553466","https://openalex.org/W2788862220","https://openalex.org/W2794908222","https://openalex.org/W2796290181","https://openalex.org/W2904246096","https://openalex.org/W2905225265","https://openalex.org/W2910913210","https://openalex.org/W2911024029","https://openalex.org/W2963099939","https://openalex.org/W2963277051","https://openalex.org/W2963411833","https://openalex.org/W2963713397","https://openalex.org/W2963946413","https://openalex.org/W2968340082","https://openalex.org/W2970377754","https://openalex.org/W2973815009","https://openalex.org/W2991355586","https://openalex.org/W3015437096","https://openalex.org/W3016327299","https://openalex.org/W3047314733","https://openalex.org/W3090835024","https://openalex.org/W3091703975","https://openalex.org/W3094103188","https://openalex.org/W3103266692","https://openalex.org/W3104515094","https://openalex.org/W3126321819","https://openalex.org/W3133389372","https://openalex.org/W3147968035","https://openalex.org/W3155981689","https://openalex.org/W3158372357","https://openalex.org/W3181074849","https://openalex.org/W3196757288","https://openalex.org/W3198013102","https://openalex.org/W3200480656","https://openalex.org/W3205960420","https://openalex.org/W3206820790","https://openalex.org/W3207864249","https://openalex.org/W3214952050","https://openalex.org/W4200553277","https://openalex.org/W4210656949","https://openalex.org/W4210969899","https://openalex.org/W4225379958","https://openalex.org/W4226137952","https://openalex.org/W4287018575","https://openalex.org/W4287756699","https://openalex.org/W4293363567","https://openalex.org/W4296437449","https://openalex.org/W4300799055","https://openalex.org/W4313303836","https://openalex.org/W4383108491","https://openalex.org/W6674884181","https://openalex.org/W6675999342","https://openalex.org/W6684921986","https://openalex.org/W6718092244","https://openalex.org/W6740801417","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6754484421","https://openalex.org/W6757469721","https://openalex.org/W6765008394","https://openalex.org/W6768425981","https://openalex.org/W6768977950","https://openalex.org/W6771270455","https://openalex.org/W6779656125","https://openalex.org/W6787713516","https://openalex.org/W6792049622","https://openalex.org/W6794580195","https://openalex.org/W6796613488","https://openalex.org/W6798852845","https://openalex.org/W6800570120","https://openalex.org/W6804531982","https://openalex.org/W6810342052"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Task":[0],"automation":[1],"of":[2,66,159],"surgical":[3,10,22,102,138,145],"robot":[4],"has":[5],"the":[6,45,95,152,166,170,179,182],"potentials":[7],"to":[8,21,30,56,62,69,93,116,124,169,177],"improve":[9,70],"efficiency.":[11],"Recent":[12],"reinforcement":[13,88],"learning":[14,89],"(RL)":[15],"based":[16],"approaches":[17],"provide":[18],"scalable":[19],"solutions":[20],"automation,":[23],"but":[24],"typically":[25],"require":[26],"extensive":[27],"data":[28,68],"collection":[29],"solve":[31],"a":[32,143],"task":[33,156],"if":[34],"no":[35],"prior":[36],"knowledge":[37],"is":[38,42,186],"given.":[39],"This":[40],"issue":[41],"known":[43],"as":[44],"exploration":[46,71,96,153],"challenge,":[47],"which":[48],"can":[49],"be":[50],"alleviated":[51],"by":[52],"providing":[53],"expert":[54,99],"demonstrations":[55,100],"an":[57,75,86],"RL":[58],"agent.":[59],"Yet,":[60],"how":[61],"make":[63],"effective":[64],"use":[65],"demonstration":[67,132],"efficiency":[72,154],"still":[73],"remains":[74],"open":[76],"challenge.":[77],"In":[78],"this":[79],"work,":[80],"we":[81,163],"introduce":[82],"Demonstration-guided":[83],"EXploration":[84],"(DEX),":[85],"efficient":[87],"algorithm":[90],"that":[91],"aims":[92],"overcome":[94],"problem":[97],"with":[98,113],"for":[101],"automation.":[103],"To":[104],"effectively":[105],"exploit":[106],"demonstrations,":[107],"our":[108,160],"method":[109],"estimates":[110],"expert-like":[111],"behaviors":[112],"higher":[114],"values":[115],"facilitate":[117],"productive":[118],"interactions,":[119],"and":[120,155],"adopts":[121],"non-parametric":[122],"regression":[123],"enable":[125],"such":[126],"guidance":[127],"at":[128,188],"states":[129],"unobserved":[130],"in":[131,151],"data.":[133],"Extensive":[134],"experiments":[135],"on":[136,181],"10":[137],"manipulation":[139],"tasks":[140],"from":[141],"SurRoL,":[142],"comprehensive":[144],"simulation":[146],"platform,":[147],"demonstrate":[148],"significant":[149],"improvements":[150],"success":[157],"rates":[158],"method.":[161],"Moreover,":[162],"also":[164],"deploy":[165],"learned":[167],"policies":[168],"da":[171],"Vinci":[172],"Research":[173],"Kit":[174],"(dVRK)":[175],"platform":[176],"show":[178],"effectiveness":[180],"real":[183],"robot.":[184],"Code":[185],"available":[187],"https://github.com/med-air/DEX.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}