{"id":"https://openalex.org/W4312503073","doi":"https://doi.org/10.1109/iros47612.2022.9981335","title":"Towards Adaptive Continuous Control of Soft Robotic Manipulator using Reinforcement Learning","display_name":"Towards Adaptive Continuous Control of Soft Robotic Manipulator using Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312503073","doi":"https://doi.org/10.1109/iros47612.2022.9981335"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981335","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5100611349","display_name":"Yingqi Li","orcid":"https://orcid.org/0000-0002-6730-4338"},"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yingqi Li","raw_affiliation_strings":["The University of Hong Kong,Department of Mechanical Engineering,Hong Kong","Department of Mechanical Engineering, The University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Mechanical Engineering,Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Mechanical Engineering, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457096","display_name":"Xiaomei Wang","orcid":"https://orcid.org/0000-0003-4569-6948"},"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaomei Wang","raw_affiliation_strings":["The University of Hong Kong,Department of Mechanical Engineering,Hong Kong","Multi-scale Medical Robotics Center (MRC) Limited","Department of Mechanical Engineering, The University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Mechanical Engineering,Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Multi-scale Medical Robotics Center (MRC) Limited","institution_ids":[]},{"raw_affiliation_string":"Department of Mechanical Engineering, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049212334","display_name":"Ka\u2010Wai Kwok","orcid":"https://orcid.org/0000-0003-1879-9730"},"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ka-Wai Kwok","raw_affiliation_strings":["The University of Hong Kong,Department of Mechanical Engineering,Hong Kong","Department of Mechanical Engineering, The University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Department of Mechanical Engineering,Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Mechanical Engineering, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"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":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7074","last_page":"7081"},"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":0.9871000051498413,"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":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8288143873214722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7262277007102966},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5997287034988403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5170767307281494},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5094936490058899},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4917936623096466},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.48457419872283936},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4388331174850464},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.41304218769073486},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.40760600566864014},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3218337297439575},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.23715609312057495},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16264104843139648}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8288143873214722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262277007102966},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5997287034988403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5170767307281494},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5094936490058899},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4917936623096466},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.48457419872283936},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4388331174850464},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.41304218769073486},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.40760600566864014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3218337297439575},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.23715609312057495},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16264104843139648},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981335","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4799852396","display_name":"Multi-stage Soft Robotic Assistant for Intra-operative MRI-guided Stereotactic Brain Biopsy and Neurosurgery","funder_award_id":"MRP/029/20X","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1608646964","https://openalex.org/W1977655452","https://openalex.org/W2063507564","https://openalex.org/W2101667962","https://openalex.org/W2745494968","https://openalex.org/W2775361682","https://openalex.org/W2802271488","https://openalex.org/W2893591777","https://openalex.org/W2895773960","https://openalex.org/W2908901353","https://openalex.org/W2910273746","https://openalex.org/W2963864421","https://openalex.org/W2965407115","https://openalex.org/W2967429195","https://openalex.org/W2980980233","https://openalex.org/W2982962963","https://openalex.org/W2990747716","https://openalex.org/W3032958018","https://openalex.org/W3035790680","https://openalex.org/W3041885040","https://openalex.org/W3046419021","https://openalex.org/W3088310808","https://openalex.org/W3120158198","https://openalex.org/W3120778962","https://openalex.org/W3125605919","https://openalex.org/W3179364417","https://openalex.org/W3194607169","https://openalex.org/W3202992521","https://openalex.org/W3205607220","https://openalex.org/W4206107294","https://openalex.org/W4226420450","https://openalex.org/W4285108893","https://openalex.org/W4321770324","https://openalex.org/W6684921986","https://openalex.org/W6781494318"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W2250140200","https://openalex.org/W3121791438"],"abstract_inverted_index":{"Although":[0],"the":[1,59,85,95,125],"soft":[2,64],"robot":[3],"is":[4,16,31,68,81,148,156],"gaining":[5],"considerable":[6],"popularity":[7],"in":[8,70,133,166],"dexterous":[9],"and":[10,110,129,171],"safe":[11],"manipulation,":[12],"accurate":[13],"motion":[14],"control":[15,56],"still":[17],"an":[18,77],"open":[19],"problem":[20],"to":[21,83,112],"be":[22],"explored.":[23],"Recent":[24],"investigations":[25],"suggest":[26],"that":[27,94,144,154],"reinforcement":[28],"learning":[29,152],"(RL)":[30],"a":[32,50,101],"promising":[33],"solution":[34],"but":[35],"lacks":[36],"efficient":[37],"adaptability":[38],"for":[39,58,72,88,150,162],"Sim2Real":[40],"transfer":[41],"or":[42],"environment":[43],"variations.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"present":[49],"deep":[51],"deterministic":[52],"policy":[53],"gradient":[54],"(DDPG)-based":[55],"system":[57],"continuous":[60],"task-space":[61],"manipulation":[62],"of":[63,107,159],"robots.":[65],"Domain":[66],"randomization":[67],"adopted":[69],"simulation":[71],"fast":[73],"control-policy":[74],"initialization,":[75],"while":[76],"offline":[78],"retraining":[79],"strategy":[80],"utilized":[82],"update":[84],"controller":[86,98,128],"parameters":[87],"incremental":[89],"learning.":[90],"The":[91,141],"experiments":[92],"demonstrate":[93],"proposed":[96,126],"RL":[97,127,146],"can":[99],"track":[100],"moving":[102],"target":[103],"accurately":[104],"(with":[105,117],"RMSE":[106,119],"1.26":[108],"mm),":[109],"accommodate":[111],"external":[113,169],"varying":[114],"load":[115,137],"effectively":[116],"~30%":[118],"reduction":[120],"after":[121],"retraining).":[122],"Comparisons":[123],"among":[124],"other":[130],"supervised-learning-based":[131],"controllers":[132],"handling":[134],"additional":[135],"tip":[136],"were":[138],"also":[139],"conducted.":[140],"results":[142],"support":[143],"our":[145],"method":[147],"appropriate":[149],"automatic":[151],"such":[153],"there":[155],"no":[157],"need":[158],"manual":[160],"interference":[161],"data":[163],"processing,":[164],"particularly":[165],"cases":[167],"with":[168],"disturbances":[170],"actuation":[172],"redundancy.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}