{"id":"https://openalex.org/W4365421136","doi":"https://doi.org/10.1109/lra.2023.3266720","title":"Learning Needle Pick-and-Place Without Expert Demonstrations","display_name":"Learning Needle Pick-and-Place Without Expert Demonstrations","publication_year":2023,"publication_date":"2023-04-12","ids":{"openalex":"https://openalex.org/W4365421136","doi":"https://doi.org/10.1109/lra.2023.3266720"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3266720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3266720","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://discovery.ucl.ac.uk/10168660/1/Learning_Needle_Pick-And-Place_without_expert_demonstrations.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079414600","display_name":"Rokas Bendikas","orcid":"https://orcid.org/0000-0002-2801-1743"},"institutions":[{"id":"https://openalex.org/I4210122016","display_name":"Wellcome / EPSRC Centre for Interventional and Surgical Sciences","ror":"https://ror.org/03r42r570","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I1299528221","https://openalex.org/I4210087105","https://openalex.org/I4210122016","https://openalex.org/I45129253","https://openalex.org/I87048295"]},{"id":"https://openalex.org/I4210142635","display_name":"PATH To Reading","ror":"https://ror.org/0482xmh13","country_code":"US","type":"other","lineage":["https://openalex.org/I4210142635"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Rokas Bendikas","raw_affiliation_strings":["Surgical Robot Vision Group, WEISS, Department of Computer Science, University College London, London, U.K","Robot Perception and Learning Lab, Department of Computer Science, University College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Surgical Robot Vision Group, WEISS, Department of Computer Science, University College London, London, U.K","institution_ids":["https://openalex.org/I4210122016","https://openalex.org/I45129253"]},{"raw_affiliation_string":"Robot Perception and Learning Lab, Department of Computer Science, University College London, London, U.K","institution_ids":["https://openalex.org/I4210142635","https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091705160","display_name":"Valerio Modugno","orcid":"https://orcid.org/0000-0002-5177-428X"},"institutions":[{"id":"https://openalex.org/I4210142635","display_name":"PATH To Reading","ror":"https://ror.org/0482xmh13","country_code":"US","type":"other","lineage":["https://openalex.org/I4210142635"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Valerio Modugno","raw_affiliation_strings":["Robot Perception and Learning Lab, Department of Computer Science, University College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Robot Perception and Learning Lab, Department of Computer Science, University College London, London, U.K","institution_ids":["https://openalex.org/I4210142635","https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048122691","display_name":"Dimitrios Kanoulas","orcid":"https://orcid.org/0000-0002-3684-1472"},"institutions":[{"id":"https://openalex.org/I4210142635","display_name":"PATH To Reading","ror":"https://ror.org/0482xmh13","country_code":"US","type":"other","lineage":["https://openalex.org/I4210142635"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Dimitrios Kanoulas","raw_affiliation_strings":["Robot Perception and Learning Lab, Department of Computer Science, University College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Robot Perception and Learning Lab, Department of Computer Science, University College London, London, U.K","institution_ids":["https://openalex.org/I4210142635","https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068825369","display_name":"Francisco Vasconcelos","orcid":"https://orcid.org/0000-0002-4609-1177"},"institutions":[{"id":"https://openalex.org/I4210122016","display_name":"Wellcome / EPSRC Centre for Interventional and Surgical Sciences","ror":"https://ror.org/03r42r570","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I1299528221","https://openalex.org/I4210087105","https://openalex.org/I4210122016","https://openalex.org/I45129253","https://openalex.org/I87048295"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francisco Vasconcelos","raw_affiliation_strings":["Surgical Robot Vision Group, WEISS, Department of Computer Science, University College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Surgical Robot Vision Group, WEISS, Department of Computer Science, University College London, London, U.K","institution_ids":["https://openalex.org/I4210122016","https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077630267","display_name":"Danail Stoyanov","orcid":"https://orcid.org/0000-0002-0980-3227"},"institutions":[{"id":"https://openalex.org/I4210122016","display_name":"Wellcome / EPSRC Centre for Interventional and Surgical Sciences","ror":"https://ror.org/03r42r570","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I1299528221","https://openalex.org/I4210087105","https://openalex.org/I4210122016","https://openalex.org/I45129253","https://openalex.org/I87048295"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Danail Stoyanov","raw_affiliation_strings":["Surgical Robot Vision Group, WEISS, Department of Computer Science, University College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Surgical Robot Vision Group, WEISS, Department of Computer Science, University College London, London, U.K","institution_ids":["https://openalex.org/I4210122016","https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079414600"],"corresponding_institution_ids":["https://openalex.org/I4210122016","https://openalex.org/I4210142635","https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":2.7318,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90050054,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"8","issue":"6","first_page":"3326","last_page":"3333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9987999796867371,"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":0.9987999796867371,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9975000023841858,"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/T10916","display_name":"Surgical Simulation and Training","score":0.9609000086784363,"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/task","display_name":"Task (project management)","score":0.7142176628112793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6996399164199829},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6571367383003235},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5822792649269104},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.518393337726593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5040971040725708},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.463955819606781},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4175558090209961},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.41332685947418213},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21624064445495605},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10837256908416748},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10387128591537476}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7142176628112793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6996399164199829},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6571367383003235},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5822792649269104},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.518393337726593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5040971040725708},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.463955819606781},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4175558090209961},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.41332685947418213},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21624064445495605},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10837256908416748},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10387128591537476},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2023.3266720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3266720","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10168660","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10168660/","pdf_url":"https://discovery.ucl.ac.uk/10168660/1/Learning_Needle_Pick-And-Place_without_expert_demonstrations.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"   IEEE Robotics and Automation Letters       (2023)     (In press).  ","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10168660","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10168660/","pdf_url":"https://discovery.ucl.ac.uk/10168660/1/Learning_Needle_Pick-And-Place_without_expert_demonstrations.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"   IEEE Robotics and Automation Letters       (2023)     (In press).  ","raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1320193412","display_name":"Robotic Assisted Imaging","funder_award_id":"EP/P012841/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1737217355","display_name":null,"funder_award_id":"EP/P012841/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4583412171","display_name":null,"funder_award_id":"EP/S021566/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5935547209","display_name":null,"funder_award_id":"203145/Z/16/Z","funder_id":"https://openalex.org/F4320330765","funder_display_name":"Wellcome / EPSRC Centre for Interventional and Surgical Sciences"}],"funders":[{"id":"https://openalex.org/F4320330765","display_name":"Wellcome / EPSRC Centre for Interventional and Surgical Sciences","ror":"https://ror.org/03r42r570"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4365421136.pdf","grobid_xml":"https://content.openalex.org/works/W4365421136.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1556824961","https://openalex.org/W2097381042","https://openalex.org/W2123995443","https://openalex.org/W2155007355","https://openalex.org/W2296073425","https://openalex.org/W2735048916","https://openalex.org/W2738671059","https://openalex.org/W2886885155","https://openalex.org/W2895806276","https://openalex.org/W2940581269","https://openalex.org/W2944149534","https://openalex.org/W2944620216","https://openalex.org/W2964067969","https://openalex.org/W2964118482","https://openalex.org/W2980897231","https://openalex.org/W3005431655","https://openalex.org/W3007769740","https://openalex.org/W3047403664","https://openalex.org/W3089353688","https://openalex.org/W3094103188","https://openalex.org/W3096597946","https://openalex.org/W3097968638","https://openalex.org/W3119552806","https://openalex.org/W3123742938","https://openalex.org/W3155981689","https://openalex.org/W3168892396","https://openalex.org/W3196757288","https://openalex.org/W3200480656","https://openalex.org/W3205960420","https://openalex.org/W3206787706","https://openalex.org/W4200633290","https://openalex.org/W4285309763","https://openalex.org/W4300799055","https://openalex.org/W4311404181","https://openalex.org/W4383097529","https://openalex.org/W6665489231","https://openalex.org/W6674600207","https://openalex.org/W6677258307","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6732837357","https://openalex.org/W6740801417","https://openalex.org/W6754615820","https://openalex.org/W6768844577","https://openalex.org/W6776458826","https://openalex.org/W6801964084"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2366903352"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,7,32,40,65,84,118],"novel":[3],"approach":[4],"for":[5,14,72,86],"learning":[6],"complex":[8,74],"multi-stage":[9],"needle":[10,88],"pick-and-place":[11,89],"manipulation":[12],"task":[13,38],"surgical":[15],"applications":[16],"using":[17],"Reinforcement":[18],"Learning":[19],"without":[20,101],"expert":[21,67,105],"demonstrations":[22],"or":[23],"explicit":[24],"curriculum.":[25],"The":[26],"proposed":[27],"method":[28,80,95,112],"is":[29,96],"based":[30],"on":[31],"recursive":[33],"decomposition":[34],"of":[35,42,104],"the":[36,87,92,102,114],"original":[37],"into":[39,76],"sequence":[41],"sub-tasks":[43],"with":[44,52,117],"increasing":[45],"complexity":[46],"and":[47],"utilizes":[48],"an":[49],"actor-critic":[50],"algorithm":[51],"deterministic":[53],"policy":[54,85],"output.":[55],"In":[56],"this":[57],"work,":[58],"exploratory":[59],"bottlenecks":[60],"have":[61],"been":[62],"used":[63],"by":[64],"human":[66],"as":[68],"convenient":[69],"boundary":[70],"points":[71],"partitioning":[73],"tasks":[75],"simpler":[77],"subunits.":[78],"Our":[79],"has":[81],"successfully":[82],"learnt":[83],"task,":[90],"whereas":[91],"state-of-the-art":[93],"TD3+HER":[94],"unable":[97],"to":[98],"achieve":[99],"success":[100,121],"help":[103],"demonstrations.":[106],"Comparison":[107],"results":[108],"show":[109],"that":[110],"our":[111],"achieves":[113],"highest":[115],"performance":[116],"91%":[119],"average":[120],"rate.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}