{"id":"https://openalex.org/W4416748686","doi":"https://doi.org/10.1109/iros60139.2025.11247575","title":"Jacobian Exploratory Dual-Phase Reinforcement Learning for Dynamic Endoluminal Navigation of Deformable Continuum Robots","display_name":"Jacobian Exploratory Dual-Phase Reinforcement Learning for Dynamic Endoluminal Navigation of Deformable Continuum Robots","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748686","doi":"https://doi.org/10.1109/iros60139.2025.11247575"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5101688184","display_name":"Yu Tian","orcid":"https://orcid.org/0000-0002-6972-2605"},"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":"Yu Tian","raw_affiliation_strings":["The Chinese University of Hong Kong,Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Electronic Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113395493","display_name":"Chi Kit Ng","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":"Chi Kit Ng","raw_affiliation_strings":["The Chinese University of Hong Kong,Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Electronic Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032340829","display_name":"Hongliang Ren","orcid":"https://orcid.org/0000-0002-6488-1551"},"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":"Hongliang Ren","raw_affiliation_strings":["The Chinese University of Hong Kong,Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Electronic Engineering","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21559","last_page":"21565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9496999979019165,"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":0.9496999979019165,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.010300000198185444,"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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.0071000000461936,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/jacobian-matrix-and-determinant","display_name":"Jacobian matrix and determinant","score":0.9273999929428101},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7042999863624573},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5410000085830688},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5034000277519226},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46810001134872437},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4401000142097473},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.39100000262260437},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.35749998688697815}],"concepts":[{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.9273999929428101},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7042999863624573},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5410000085830688},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4945000112056732},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.39100000262260437},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35830000042915344},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.35749998688697815},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3474000096321106},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31119999289512634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29750001430511475},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.25690001249313354},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C129537906","wikidata":"https://www.wikidata.org/wiki/Q7603913","display_name":"State variable","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2053614949","https://openalex.org/W2073677587","https://openalex.org/W2101667962","https://openalex.org/W2184993170","https://openalex.org/W2575705757","https://openalex.org/W2741086304","https://openalex.org/W2901112449","https://openalex.org/W2951360122","https://openalex.org/W2962872206"],"related_works":[],"abstract_inverted_index":{"Deformable":[0],"continuum":[1],"robots":[2],"(DCRs)":[3],"present":[4],"unique":[5],"planning":[6,62],"challenges":[7],"due":[8],"to":[9,39,81,95,129],"nonlinear":[10],"deformation":[11,48,84],"mechanics":[12],"and":[13,46,67,133,145],"partial":[14],"state":[15,90],"observability,":[16],"violating":[17],"the":[18,83,89,131,155],"Markov":[19],"assumptions":[20],"of":[21],"conventional":[22],"reinforcement":[23],"learning":[24],"(RL)":[25],"methods.":[26],"While":[27],"Jacobian-Based":[28],"approaches":[29],"offer":[30],"theoretical":[31],"foundations":[32],"for":[33],"rigid":[34],"manipulators,":[35],"their":[36],"direct":[37],"application":[38],"DCRs":[40],"remains":[41],"limited":[42],"by":[43],"time-varying":[44],"kinematics":[45],"underactuated":[47],"dynamics.":[49],"This":[50],"paper":[51],"proposes":[52],"Jacobian":[53,65,85,93],"Exploratory":[54],"Dual-Phase":[55],"RL":[56],"(JEDP-RL),":[57],"a":[58],"framework":[59],"that":[60],"decomposes":[61],"into":[63],"phased":[64],"estimation":[66],"policy":[68,111,120],"execution.":[69],"During":[70],"each":[71],"training":[72],"step,":[73],"we":[74],"first":[75],"perform":[76],"small-scale":[77],"local":[78],"exploratory":[79],"actions":[80],"estimate":[82],"matrix,":[86],"then":[87],"augment":[88],"representation":[91],"with":[92],"features":[94],"restore":[96],"approximate":[97],"Markovianity.":[98],"Extensive":[99],"SOFA":[100],"surgical":[101],"dynamic":[102],"simulations":[103],"demonstrate":[104],"JEDP-RL\u2019s":[105],"three":[106],"key":[107],"advantages":[108],"over":[109],"proximal":[110],"optimization":[112],"(PPO)":[113],"baselines:":[114],"1)":[115],"Convergence":[116],"speed:":[117],"3.2\u00d7":[118],"faster":[119],"convergence,":[121],"2)":[122],"Navigation":[123],"efficiency:":[124],"requires":[125],"25%":[126],"fewer":[127],"steps":[128],"reach":[130],"target,":[132],"3)":[134],"Generalization":[135],"ability:":[136],"achieve":[137,146],"92%":[138],"success":[139,152],"rate":[140,153],"under":[141],"material":[142],"property":[143],"variations":[144],"83%":[147],"(33%":[148],"higher":[149],"than":[150],"PPO)":[151],"in":[154],"unseen":[156],"tissue":[157],"environment.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}