{"id":"https://openalex.org/W3207245229","doi":"https://doi.org/10.1109/icra48506.2021.9561620","title":"Deep Reinforcement Learning for Concentric Tube Robot Control with a Goal-Based Curriculum","display_name":"Deep Reinforcement Learning for Concentric Tube Robot Control with a Goal-Based Curriculum","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3207245229","doi":"https://doi.org/10.1109/icra48506.2021.9561620","mag":"3207245229"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://discovery.ucl.ac.uk/10132537/1/ICRA_2021_Submission.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058162940","display_name":"Keshav Iyengar","orcid":"https://orcid.org/0000-0001-7020-9537"},"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":"Keshav Iyengar","raw_affiliation_strings":["Wellcome/ EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wellcome/ EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK","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":["Wellcome/ EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wellcome/ EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK","institution_ids":["https://openalex.org/I4210122016","https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1459","last_page":"1465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9952999949455261,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9861000180244446,"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":0.6899571418762207},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6465203762054443},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5598292350769043},{"id":"https://openalex.org/keywords/robot-end-effector","display_name":"Robot end effector","score":0.4903903007507324},{"id":"https://openalex.org/keywords/cartesian-coordinate-system","display_name":"Cartesian coordinate system","score":0.48449084162712097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48262104392051697},{"id":"https://openalex.org/keywords/concentric","display_name":"Concentric","score":0.48202192783355713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41742339730262756},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3794623613357544},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.33903664350509644},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26736724376678467},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.18335318565368652},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1670181155204773},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.13075989484786987},{"id":"https://openalex.org/keywords/classical-mechanics","display_name":"Classical mechanics","score":0.07184267044067383}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6899571418762207},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6465203762054443},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5598292350769043},{"id":"https://openalex.org/C8652668","wikidata":"https://www.wikidata.org/wiki/Q1340324","display_name":"Robot end effector","level":3,"score":0.4903903007507324},{"id":"https://openalex.org/C16038011","wikidata":"https://www.wikidata.org/wiki/Q62912","display_name":"Cartesian coordinate system","level":2,"score":0.48449084162712097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48262104392051697},{"id":"https://openalex.org/C90296322","wikidata":"https://www.wikidata.org/wiki/Q619776","display_name":"Concentric","level":2,"score":0.48202192783355713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41742339730262756},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3794623613357544},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.33903664350509644},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26736724376678467},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.18335318565368652},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1670181155204773},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.13075989484786987},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.07184267044067383}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra48506.2021.9561620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10132537","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10132537/","pdf_url":"https://discovery.ucl.ac.uk/10132537/1/ICRA_2021_Submission.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  IEEE International Conference on Robotics and Automation (ICRA) 2021.    IEEE (2021)     ","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10132537","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10132537/","pdf_url":"https://discovery.ucl.ac.uk/10132537/1/ICRA_2021_Submission.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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:  IEEE International Conference on Robotics and Automation (ICRA) 2021.    IEEE (2021)     ","raw_type":"Proceedings paper"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G6923427940","display_name":null,"funder_award_id":"EP/R004080/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"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/W3207245229.pdf","grobid_xml":"https://content.openalex.org/works/W3207245229.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1499925623","https://openalex.org/W1979286982","https://openalex.org/W2050268494","https://openalex.org/W2131150943","https://openalex.org/W2138564331","https://openalex.org/W2164013717","https://openalex.org/W2173248099","https://openalex.org/W2184993170","https://openalex.org/W2294964503","https://openalex.org/W2317436702","https://openalex.org/W2462654948","https://openalex.org/W2593483954","https://openalex.org/W2729615412","https://openalex.org/W2754517384","https://openalex.org/W2910440184","https://openalex.org/W2963460823","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2968516533","https://openalex.org/W3007380892","https://openalex.org/W3026465055","https://openalex.org/W3033727525","https://openalex.org/W3036619998","https://openalex.org/W4300799055","https://openalex.org/W6684921986","https://openalex.org/W6697547461","https://openalex.org/W6740801417","https://openalex.org/W6741010574","https://openalex.org/W6744123322","https://openalex.org/W6910476156"],"related_works":["https://openalex.org/W2032745795","https://openalex.org/W4241659117","https://openalex.org/W2042569643","https://openalex.org/W4252230788","https://openalex.org/W2254998354","https://openalex.org/W4235256213","https://openalex.org/W2048369647","https://openalex.org/W2391000165","https://openalex.org/W2801692647","https://openalex.org/W2611960376"],"abstract_inverted_index":{"Concentric":[0],"Tube":[1],"Robots":[2],"(CTRs),":[3],"a":[4,10,54,58,70,77,109,138,142,148,160,174,180,195],"type":[5],"of":[6,12,17,40,86,111,121,170,177,191,208,215],"continuum":[7,216],"robot,":[8],"are":[9,115,126],"collection":[11],"concentric,":[13],"pre-curved":[14],"tubes":[15,33],"composed":[16],"super":[18],"elastic":[19],"nickel":[20],"titanium":[21],"alloy.":[22],"CTRs":[23,219],"can":[24],"bend":[25],"and":[26,37,98,104,123,128,158,173,218],"twist":[27],"from":[28],"the":[29,35,41,84,90,129,206],"interactions":[30],"between":[31],"neighboring":[32],"causing":[34],"kinematics":[36],"therefore":[38],"control":[39,55,214],"end-effector":[42,60],"to":[43,47,147],"be":[44],"very":[45],"challenging":[46],"model.":[48],"In":[49,184],"this":[50],"paper,":[51],"we":[52,187],"develop":[53],"scheme":[56],"for":[57,119,136],"CTR":[59],"in":[61,141,194,201,211,220],"Cartesian":[62,168],"space":[63],"with":[64,76,95,179],"no":[65],"prior":[66],"kinematic":[67],"model":[68,212],"using":[69,209],"deep":[71],"reinforcement":[72],"learning":[73],"(DRL)":[74],"approach":[75,133],"goal-based":[78],"curriculum":[79],"reward":[80],"strategy.":[81],"We":[82,165],"explore":[83],"use":[85],"curricula":[87,122],"by":[88],"changing":[89],"goal":[91],"tolerance":[92],"through":[93],"training":[94,113,137,156],"constant,":[96],"linear":[97],"exponential":[99,130],"decay":[100,131,182],"functions.":[101],"Also,":[102],"relative":[103,132,181],"absolute":[105],"joint":[106,124],"representations":[107,125],"as":[108],"way":[110],"improving":[112],"convergence":[114],"explored.":[116],"Quantitative":[117],"comparisons":[118],"combinations":[120],"performed":[127],"is":[134],"used":[135],"robust":[139],"policy":[140],"noise-induced":[143,196],"simulation":[144,163],"environment.":[145,164],"Compared":[146],"previous":[149],"DRL":[150,210],"approach,":[151],"our":[152],"new":[153],"method":[154],"reduces":[155],"time":[157],"employs":[159],"more":[161],"complex":[162],"report":[166,188],"mean":[167,189],"errors":[169,190],"1.29":[171],"mm":[172,193],"success":[175],"rate":[176],"0.93":[178],"curriculum.":[183],"path":[185,197],"following,":[186],"1.37":[192],"following":[198],"task.":[199],"Albeit":[200],"simulation,":[202],"these":[203],"results":[204],"indicate":[205],"promise":[207],"free":[213],"robots":[217],"particular.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}