{"id":"https://openalex.org/W7160413210","doi":"https://doi.org/10.1109/access.2026.3690990","title":"A Systematic Benchmark of Reinforcement Learning Formulations for Tendon-Driven Continuum Robot Control","display_name":"A Systematic Benchmark of Reinforcement Learning Formulations for Tendon-Driven Continuum Robot Control","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160413210","doi":"https://doi.org/10.1109/access.2026.3690990"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3690990","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3690990","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3690990","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093387082","display_name":"D\u00e1rius Rusi\u0148\u00e1k","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153238","display_name":"Icelandic Heart Association","ror":"https://ror.org/051snsd81","country_code":"IS","type":"nonprofit","lineage":["https://openalex.org/I4210153238"]}],"countries":["IS"],"is_corresponding":false,"raw_author_name":"Darius Rusinak","raw_affiliation_strings":["Technical University of Ko&#x0161;ice, Ko&#x0161;ice, Slovakia"],"raw_orcid":"https://orcid.org/0009-0001-0383-2457","affiliations":[{"raw_affiliation_string":"Technical University of Ko&#x0161;ice, Ko&#x0161;ice, Slovakia","institution_ids":["https://openalex.org/I4210153238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056615264","display_name":"Michal Kelemen","orcid":"https://orcid.org/0000-0003-2274-3828"},"institutions":[{"id":"https://openalex.org/I4210153238","display_name":"Icelandic Heart Association","ror":"https://ror.org/051snsd81","country_code":"IS","type":"nonprofit","lineage":["https://openalex.org/I4210153238"]}],"countries":["IS"],"is_corresponding":false,"raw_author_name":"Michal Kelemen","raw_affiliation_strings":["Technical University of Ko&#x0161;ice, Ko&#x0161;ice, Slovakia"],"raw_orcid":"https://orcid.org/0000-0003-2274-3828","affiliations":[{"raw_affiliation_string":"Technical University of Ko&#x0161;ice, Ko&#x0161;ice, Slovakia","institution_ids":["https://openalex.org/I4210153238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030237725","display_name":"Ivan Virgala","orcid":"https://orcid.org/0000-0001-8273-2384"},"institutions":[{"id":"https://openalex.org/I4210153238","display_name":"Icelandic Heart Association","ror":"https://ror.org/051snsd81","country_code":"IS","type":"nonprofit","lineage":["https://openalex.org/I4210153238"]}],"countries":["IS"],"is_corresponding":false,"raw_author_name":"Ivan Virgala","raw_affiliation_strings":["Technical University of Ko&#x0161;ice, Ko&#x0161;ice, Slovakia"],"raw_orcid":"https://orcid.org/0000-0001-8273-2384","affiliations":[{"raw_affiliation_string":"Technical University of Ko&#x0161;ice, Ko&#x0161;ice, Slovakia","institution_ids":["https://openalex.org/I4210153238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67397973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"69907","last_page":"69922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11394","display_name":"Dynamics and Control of Mechanical Systems","score":0.38179999589920044,"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/T11394","display_name":"Dynamics and Control of Mechanical Systems","score":0.38179999589920044,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.13259999454021454,"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":0.07410000264644623,"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":0.6621000170707703},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6132000088691711},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5386999845504761},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.48570001125335693},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4009999930858612},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.3361999988555908},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.33180001378059387},{"id":"https://openalex.org/keywords/robot-kinematics","display_name":"Robot kinematics","score":0.33090001344680786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6998000144958496},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6621000170707703},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6132000088691711},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.48570001125335693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47130000591278076},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4009999930858612},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.364300012588501},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.33090001344680786},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.32339999079704285},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.3025999963283539},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3690990","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3690990","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f6f460c09c1f46b782f29aa293e0e058","is_oa":true,"landing_page_url":"https://doaj.org/article/f6f460c09c1f46b782f29aa293e0e058","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 69907-69922 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3690990","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3690990","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1432207446","display_name":null,"funder_award_id":"VEGA 1/0409/25","funder_id":"https://openalex.org/F4320321779","funder_display_name":"Ministerstvo \u0161kolstva, vedy, v\u00fdskumu a \u0161portu Slovenskej republiky"},{"id":"https://openalex.org/G8776747544","display_name":null,"funder_award_id":"KEGA 008TUKE-4/2024","funder_id":"https://openalex.org/F4320321779","funder_display_name":"Ministerstvo \u0161kolstva, vedy, v\u00fdskumu a \u0161portu Slovenskej republiky"}],"funders":[{"id":"https://openalex.org/F4320321779","display_name":"Ministerstvo \u0161kolstva, vedy, v\u00fdskumu a \u0161portu Slovenskej republiky","ror":"https://ror.org/044gwpv05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Continuum":[0],"robots":[1],"are":[2,23],"well":[3],"suited":[4],"to":[5,60],"confined":[6],"and":[7,20,89,99,105,113,130,157],"contact-rich":[8],"environments,":[9],"but":[10],"their":[11],"control":[12,40],"remains":[13],"challenging":[14],"because":[15],"modeling":[16],"fidelity,":[17],"computational":[18],"cost,":[19],"real-time":[21],"feasibility":[22],"often":[24,114],"in":[25],"tension.":[26],"This":[27],"work":[28],"benchmarks":[29],"reinforcement":[30],"learning":[31,154],"(RL)":[32],"formulation":[33],"choices":[34],"for":[35],"tendon-driven":[36],"continuum":[37],"robot":[38],"tip":[39,160],"under":[41,103],"controlled":[42,144],"conditions.":[43],"A":[44],"fixed":[45],"data-driven":[46],"kinematic":[47],"surrogate,":[48],"learned":[49],"from":[50],"motion-capture":[51],"data":[52],"collected":[53],"on":[54,95],"a":[55,76,85],"physical":[56],"prototype,":[57],"was":[58],"used":[59],"evaluate":[61],"five":[62],"RL":[63,149],"algorithms":[64],"across":[65],"24":[66],"state\u2013reward":[67],"configurations,":[68],"yielding":[69],"120":[70],"algorithm\u2013configuration":[71],"pairs.":[72],"The":[73],"benchmark":[74],"followed":[75],"two-phase":[77],"protocol:":[78],"Phase":[79,90],"I":[80],"screened":[81],"unstable":[82],"policies":[83,94],"using":[84],"sustained":[86],"convergence":[87],"criterion,":[88],"II":[91],"evaluated":[92],"retained":[93],"held-out":[96],"point":[97],"reaching":[98],"sequential":[100],"waypoint-following":[101],"tasks":[102],"deterministic":[104],"stochastic":[106],"execution.":[107],"Simpler":[108],"formulations,":[109],"particularly":[110],"error-based":[111],"states":[112],"those":[115],"without":[116],"actuator":[117],"augmentation,":[118],"were":[119],"the":[120,134,140],"most":[121],"consistently":[122],"effective.":[123],"Composite-augmented":[124],"reward":[125],"designs":[126],"improved":[127],"screening":[128],"stability,":[129],"soft":[131],"actor-critic":[132],"provided":[133],"strongest":[135],"average":[136],"downstream":[137],"profile.":[138],"Overall,":[139],"results":[141],"show":[142],"that":[143,151],"multi-stage":[145],"benchmarking":[146],"can":[147],"identify":[148],"formulations":[150],"combine":[152],"stable":[153],"with":[155],"accurate":[156],"reliable":[158],"continuum-robot":[159],"control.":[161]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-07T00:00:00"}
