{"id":"https://openalex.org/W3189250457","doi":"https://doi.org/10.1109/lra.2021.3097660","title":"Towards Safe Control of Continuum Manipulator Using Shielded Multiagent Reinforcement Learning","display_name":"Towards Safe Control of Continuum Manipulator Using Shielded Multiagent Reinforcement Learning","publication_year":2021,"publication_date":"2021-08-03","ids":{"openalex":"https://openalex.org/W3189250457","doi":"https://doi.org/10.1109/lra.2021.3097660","mag":"3189250457"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3097660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3097660","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045394226","display_name":"Guanglin Ji","orcid":"https://orcid.org/0000-0003-1188-086X"},"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":"Guanglin Ji","raw_affiliation_strings":["CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044404474","display_name":"Junyan Yan","orcid":"https://orcid.org/0000-0001-6271-5819"},"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":"Junyan Yan","raw_affiliation_strings":["CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-6271-5819","affiliations":[{"raw_affiliation_string":"CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048702203","display_name":"Jingxin Du","orcid":null},"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":"Jingxin Du","raw_affiliation_strings":["CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055423430","display_name":"Wanquan Yan","orcid":"https://orcid.org/0000-0002-9207-6613"},"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":"Wanquan Yan","raw_affiliation_strings":["CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-9207-6613","affiliations":[{"raw_affiliation_string":"CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070244905","display_name":"Jibiao Chen","orcid":"https://orcid.org/0000-0002-8177-7465"},"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":"Jibiao Chen","raw_affiliation_strings":["CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-8177-7465","affiliations":[{"raw_affiliation_string":"CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061148194","display_name":"Yongkang Lu","orcid":"https://orcid.org/0000-0002-2906-5591"},"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":"Yongkang Lu","raw_affiliation_strings":["CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060257108","display_name":"Juan Rojas","orcid":"https://orcid.org/0000-0002-6552-4572"},"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":"Juan Rojas","raw_affiliation_strings":["CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-6552-4572","affiliations":[{"raw_affiliation_string":"CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072251844","display_name":"Shing Shin Cheng","orcid":"https://orcid.org/0000-0002-9386-5497"},"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":"Shing Shin Cheng","raw_affiliation_strings":["CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","Shun Hing Institute of Advanced Engineering and Multi-Scale Medical Robotics Center, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-9386-5497","affiliations":[{"raw_affiliation_string":"CUHK T Stone Robotics Institute and Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shun Hing Institute of Advanced Engineering and Multi-Scale Medical Robotics Center, The Chinese University of Hong Kong, 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":2.1512,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.87086119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"6","issue":"4","first_page":"7461","last_page":"7468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9878000020980835,"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":0.9855999946594238,"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":0.7565629482269287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5336974859237671},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5279801487922668},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5144944190979004},{"id":"https://openalex.org/keywords/payload","display_name":"Payload (computing)","score":0.4851123094558716},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.47366863489151},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.42282834649086},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3866793215274811},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3457377254962921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33671027421951294},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3090057969093323},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.24392199516296387},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1428019404411316}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7565629482269287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5336974859237671},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5279801487922668},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5144944190979004},{"id":"https://openalex.org/C134066672","wikidata":"https://www.wikidata.org/wiki/Q1424639","display_name":"Payload (computing)","level":3,"score":0.4851123094558716},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.47366863489151},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.42282834649086},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3866793215274811},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3457377254962921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33671027421951294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3090057969093323},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24392199516296387},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1428019404411316},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3097660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3097660","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3182787842","display_name":"An MRI-compatible Robotic Cannula for Intracerebral Hemorrhage Evacuation","funder_award_id":"ITS/226/19","funder_id":"https://openalex.org/F4320321920","funder_display_name":"Innovation and Technology Commission"},{"id":"https://openalex.org/G7026413499","display_name":"Development of an Ultrasound-Guided Robotic Steerable Catheter for Pericardiocentesis","funder_award_id":"ITS/389/18","funder_id":"https://openalex.org/F4320321920","funder_display_name":"Innovation and Technology Commission"},{"id":"https://openalex.org/G8178918150","display_name":"A Flexible Endoscope For The Robot-Assisted Bimanual Functional Endoscopic Sinus Surgery","funder_award_id":"ITS/136/20","funder_id":"https://openalex.org/F4320321920","funder_display_name":"Innovation and Technology Commission"}],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320335138","display_name":"Shun Hing Institute of Advanced Engineering","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W206679605","https://openalex.org/W1757796397","https://openalex.org/W1988003703","https://openalex.org/W2101667962","https://openalex.org/W2121863487","https://openalex.org/W2160279098","https://openalex.org/W2173248099","https://openalex.org/W2184993170","https://openalex.org/W2490314460","https://openalex.org/W2523642729","https://openalex.org/W2544641369","https://openalex.org/W2739636222","https://openalex.org/W2745494968","https://openalex.org/W2770049904","https://openalex.org/W2775361682","https://openalex.org/W2783268317","https://openalex.org/W2893591777","https://openalex.org/W2901112449","https://openalex.org/W2946872323","https://openalex.org/W2963575966","https://openalex.org/W2963864421","https://openalex.org/W2967429195","https://openalex.org/W3035790680","https://openalex.org/W3042045548","https://openalex.org/W3081954207","https://openalex.org/W3109589982","https://openalex.org/W3125605919","https://openalex.org/W3128238597","https://openalex.org/W3187004032","https://openalex.org/W3206421940","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6684921986","https://openalex.org/W6743563064","https://openalex.org/W6762863022","https://openalex.org/W6802647171"],"related_works":["https://openalex.org/W1535080110","https://openalex.org/W306312984","https://openalex.org/W857189463","https://openalex.org/W4288094128","https://openalex.org/W2979675132","https://openalex.org/W2790520092","https://openalex.org/W4379531983","https://openalex.org/W2294241086","https://openalex.org/W2903025760","https://openalex.org/W4289147272"],"abstract_inverted_index":{"Continuum":[0],"robotic":[1],"manipulators":[2],"are":[3,137],"increasingly":[4],"adopted":[5],"in":[6,77,153],"minimal":[7],"invasive":[8],"surgery.":[9],"However,":[10],"their":[11],"nonlinear":[12],"behavior":[13],"is":[14,68],"challenging":[15],"to":[16,22,27,52,81,102,116,150],"model":[17],"accurately,":[18],"especially":[19],"when":[20],"subject":[21],"external":[23,129,169],"interaction,":[24],"potentially":[25],"leading":[26],"poor":[28],"control":[29,53,64,107],"performance.":[30],"In":[31],"this":[32],"letter,":[33],"we":[34],"investigate":[35],"the":[36,66,78,83,96,109,114],"feasibility":[37],"of":[38,56,65,95,108],"adopting":[39],"a":[40,54,71,88,154],"model-free":[41],"multiagent":[42,47],"reinforcement":[43],"learning":[44,84],"(RL),":[45],"namely":[46],"deep":[48],"Q":[49],"network":[50],"(MADQN),":[51],"2-degree":[55],"freedom":[57],"(DoF)":[58],"cable-driven":[59],"continuum":[60,156],"surgical":[61,143],"manipulator.":[62],"The":[63,145],"robot":[67,115,157],"formulated":[69],"as":[70],"one":[72,74],"DoF,":[73],"agent":[75],"problem":[76],"MADQN":[79,100,112],"framework":[80],"improve":[82],"efficiency.":[85],"Combined":[86],"with":[87,122,158,165],"shielding":[89],"scheme":[90],"that":[91],"enables":[92],"dynamic":[93],"variation":[94],"action":[97],"set":[98],"boundary,":[99],"leads":[101],"efficient":[103],"and":[104,119,133],"importantly":[105],"safer":[106],"robot.":[110],"Shielded":[111],"enabled":[113],"perform":[117],"point":[118],"trajectory":[120,163],"tracking":[121,164],"submillimeter":[123,166],"root":[124],"mean":[125],"square":[126],"errors":[127],"under":[128,168],"loads,":[130],"soft":[131],"obstacles,":[132],"rigid":[134],"collision,":[135],"which":[136],"common":[138],"interaction":[139],"scenarios":[140],"encountered":[141],"by":[142],"manipulators.":[144],"controller":[146],"was":[147],"further":[148],"proven":[149],"be":[151],"effective":[152],"miniature":[155],"high":[159],"structural":[160],"nonlinearitiy,":[161],"achieving":[162],"accuracy":[167],"payload.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":13}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
