{"id":"https://openalex.org/W4399504148","doi":"https://doi.org/10.1142/s2424905x24400105","title":"Autonomous Soft-Tissue Needle Steering Using Reinforcement Learning Guided by Human Input","display_name":"Autonomous Soft-Tissue Needle Steering Using Reinforcement Learning Guided by Human Input","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4399504148","doi":"https://doi.org/10.1142/s2424905x24400105"},"language":"en","primary_location":{"id":"doi:10.1142/s2424905x24400105","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s2424905x24400105","pdf_url":null,"source":{"id":"https://openalex.org/S4210232911","display_name":"Journal of Medical Robotics Research","issn_l":"2424-905X","issn":["2424-905X","2424-9068"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Medical Robotics Research","raw_type":"journal-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/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":true,"raw_author_name":"Yafei Ou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Alberta, 9211-116 Street NW, Edmonton, AB, T6G 1H9, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2989-9991","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, 9211-116 Street NW, Edmonton, AB, T6G 1H9, 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":["Department of Electrical and Computer Engineering, University of Alberta, 9211-116 Street NW, Edmonton, AB, T6G 1H9, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7427-6961","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Alberta, 9211-116 Street NW, Edmonton, AB, T6G 1H9, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023350625"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10540328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"09","issue":"03n04","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10510","display_name":"Stroke Rehabilitation and Recovery","score":0.8166000247001648,"subfield":{"id":"https://openalex.org/subfields/2742","display_name":"Rehabilitation"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10510","display_name":"Stroke Rehabilitation and Recovery","score":0.8166000247001648,"subfield":{"id":"https://openalex.org/subfields/2742","display_name":"Rehabilitation"},"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":0.5603207945823669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48394066095352173},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.46067437529563904},{"id":"https://openalex.org/keywords/soft-robotics","display_name":"Soft robotics","score":0.45120418071746826},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44100216031074524},{"id":"https://openalex.org/keywords/biomedical-engineering","display_name":"Biomedical engineering","score":0.36693572998046875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35358864068984985},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3238326907157898},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.29010865092277527},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.07830998301506042},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0734076201915741}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5603207945823669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48394066095352173},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46067437529563904},{"id":"https://openalex.org/C2776058767","wikidata":"https://www.wikidata.org/wiki/Q24327151","display_name":"Soft robotics","level":3,"score":0.45120418071746826},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44100216031074524},{"id":"https://openalex.org/C136229726","wikidata":"https://www.wikidata.org/wiki/Q327092","display_name":"Biomedical engineering","level":1,"score":0.36693572998046875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35358864068984985},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3238326907157898},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29010865092277527},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.07830998301506042},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0734076201915741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s2424905x24400105","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s2424905x24400105","pdf_url":null,"source":{"id":"https://openalex.org/S4210232911","display_name":"Journal of Medical Robotics Research","issn_l":"2424-905X","issn":["2424-905X","2424-9068"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Medical Robotics Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319952","display_name":"Canada Foundation for Innovation","ror":"https://ror.org/000az4664"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334506","display_name":"Canadian Institutes of Health Research","ror":"https://ror.org/01gavpb45"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1975059652","https://openalex.org/W2081984806","https://openalex.org/W2093664976","https://openalex.org/W2107550832","https://openalex.org/W2323973715","https://openalex.org/W2327864658","https://openalex.org/W2560102456","https://openalex.org/W2565234518","https://openalex.org/W2601771264","https://openalex.org/W2754300823","https://openalex.org/W2789767748","https://openalex.org/W2905545599","https://openalex.org/W2991355332","https://openalex.org/W3035756007","https://openalex.org/W3127265496","https://openalex.org/W3205960420","https://openalex.org/W3207132575","https://openalex.org/W4282944694","https://openalex.org/W4286253093","https://openalex.org/W4313166209","https://openalex.org/W4323914534","https://openalex.org/W4378191992","https://openalex.org/W4387641544"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Soft-tissue":[0],"needle":[1,6,48,72,139],"steering,":[2],"where":[3],"a":[4,17,21,61,78,108,134,145,195],"deformable":[5],"is":[7,20,101,130],"inserted":[8],"into":[9],"the":[10,38,47,50,54,117,125,150,163,167,183],"tissue":[11,35,51],"to":[12,16,69,89,115,119,144,192],"guide":[13],"its":[14],"tip":[15],"desired":[18],"position,":[19],"common":[22],"minimally":[23],"invasive":[24],"surgery":[25],"(MIS)":[26],"procedure.":[27],"The":[28],"diverse":[29],"types":[30],"of":[31,40,46,194],"needles":[32],"and":[33,49,92,141,172],"complex":[34,184],"dynamics":[36],"limit":[37],"use":[39],"existing":[41],"approaches":[42,171],"that":[43,159,193],"utilize":[44],"models":[45],"for":[52,112,138],"automating":[53],"task.":[55],"In":[56],"this":[57],"work,":[58],"we":[59],"employ":[60],"data-driven":[62],"approach":[63],"using":[64],"deep":[65],"reinforcement":[66,80],"learning":[67,81,91,99],"(DRL)":[68],"achieve":[70,174],"autonomous":[71],"steering":[73,140],"by":[74,106],"viewing":[75],"it":[76],"as":[77,149],"multi-goal":[79],"problem.":[82],"Human":[83],"interventions":[84,114],"are":[85],"incorporated":[86],"during":[87],"training":[88,180],"accelerate":[90],"reduce":[93],"catastrophic":[94],"failures.":[95],"Generative":[96],"adversarial":[97],"imitation":[98],"(GAIL)":[100],"combined":[102],"with":[103,153,160,177],"regular":[104],"DRL":[105,170],"utilizing":[107],"hindsight":[109],"relabeling":[110],"scheme":[111],"human":[113,121,161],"encourage":[116],"agent":[118,129,197],"imitate":[120],"behavior.":[122],"To":[123],"emulate":[124],"sim-to-real":[126],"process,":[127],"an":[128,188],"first":[131],"trained":[132,198],"in":[133,182],"simplistic":[135],"simulation":[136,185],"environment":[137],"then":[142],"transferred":[143],"sophisticated":[146],"one":[147],"considered":[148],"real":[151],"world":[152],"fine-tuning":[154],"(sim-to-sim).":[155],"Experimental":[156],"results":[157],"show":[158],"interventions,":[162],"proposed":[164],"method":[165],"outperforms":[166],"other":[168],"compared":[169],"can":[173],"good":[175],"performance":[176],"only":[178],"2,000":[179],"steps":[181],"environment,":[186],"achieving":[187],"average":[189],"return":[190],"comparable":[191],"55,000-step":[196],"from":[199],"scratch.":[200]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}