{"id":"https://openalex.org/W4416750519","doi":"https://doi.org/10.1109/iros60139.2025.11246890","title":"CapsDT: Diffusion-Transformer for Capsule Robot Manipulation","display_name":"CapsDT: Diffusion-Transformer for Capsule Robot Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750519","doi":"https://doi.org/10.1109/iros60139.2025.11246890"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246890","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":"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/A5080642124","display_name":"Xin\u2010Tao He","orcid":"https://orcid.org/0000-0003-0454-1050"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiting He","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK),Department of Electronic Engineering,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK),Department of Electronic Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083339136","display_name":"Mu\u2010Chun Su","orcid":"https://orcid.org/0000-0003-1263-9912"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingwu Su","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK),Department of Electronic Engineering,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK),Department of Electronic Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074958556","display_name":"Xinqi Jiang","orcid":"https://orcid.org/0009-0002-7503-0231"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinqi Jiang","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK),Department of Electronic Engineering,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK),Department of Electronic Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101434323","display_name":"Long Bai","orcid":"https://orcid.org/0000-0003-2671-3298"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Bai","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK),Department of Electronic Engineering,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK),Department of Electronic Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033084136","display_name":"Hongliang Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongliang Ren","raw_affiliation_strings":["The Chinese University of Hong Kong (CUHK),Department of Electronic Engineering,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong (CUHK),Department of Electronic Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080642124"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35217017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"414","last_page":"419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.4165000021457672,"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":0.4165000021457672,"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/T11378","display_name":"Gastrointestinal Bleeding Diagnosis and Treatment","score":0.36550000309944153,"subfield":{"id":"https://openalex.org/subfields/2715","display_name":"Gastroenterology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.049800001084804535,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/capsule-endoscopy","display_name":"Capsule endoscopy","score":0.758400022983551},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7195000052452087},{"id":"https://openalex.org/keywords/endoscopy","display_name":"Endoscopy","score":0.5048999786376953},{"id":"https://openalex.org/keywords/robot-manipulator","display_name":"Robot manipulator","score":0.4050000011920929},{"id":"https://openalex.org/keywords/robotic-surgery","display_name":"Robotic surgery","score":0.3668999969959259},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.33230000734329224}],"concepts":[{"id":"https://openalex.org/C2777333622","wikidata":"https://www.wikidata.org/wiki/Q116753","display_name":"Capsule endoscopy","level":2,"score":0.758400022983551},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7195000052452087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5436000227928162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5148000121116638},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5073000192642212},{"id":"https://openalex.org/C2778451229","wikidata":"https://www.wikidata.org/wiki/Q212809","display_name":"Endoscopy","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.4050000011920929},{"id":"https://openalex.org/C103203806","wikidata":"https://www.wikidata.org/wiki/Q942348","display_name":"Robotic surgery","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.2964000105857849},{"id":"https://openalex.org/C2985005502","wikidata":"https://www.wikidata.org/wiki/Q6806593","display_name":"Medical robotics","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2623000144958496},{"id":"https://openalex.org/C3017684034","wikidata":"https://www.wikidata.org/wiki/Q942348","display_name":"Surgical robot","level":3,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246890","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":[{"id":"https://openalex.org/F4320307285","display_name":"Impact Fund","ror":"https://ror.org/00jb20j87"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1650175677","https://openalex.org/W1993086849","https://openalex.org/W2161804549","https://openalex.org/W2889420236","https://openalex.org/W2947016327","https://openalex.org/W3034999214","https://openalex.org/W3208656753","https://openalex.org/W4210305352","https://openalex.org/W4223560790","https://openalex.org/W4304782238","https://openalex.org/W4382463287","https://openalex.org/W4386280212","https://openalex.org/W4401325787","https://openalex.org/W4406457529","https://openalex.org/W4411528087"],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2,41],"have":[3],"emerged":[4],"as":[5,146],"a":[6,14,70,104,109,114,147,162],"prominent":[7],"research":[8],"area,":[9],"showcasing":[10],"significant":[11],"potential":[12],"across":[13],"variety":[15],"of":[16,39,121,157],"applications.":[17],"However,":[18],"their":[19],"performance":[20,153],"in":[21,78,154,166],"endoscopy":[22,25,43,98,106,123,158],"robotics,":[23],"particularly":[24],"capsule":[26,75,105,110,128],"robots":[27,44],"that":[28,142],"perform":[29],"actions":[30],"within":[31,131],"the":[32,79,132],"digestive":[33],"system,":[34,108],"remains":[35],"unexplored.":[36],"The":[37],"integration":[38],"VLA":[40],"into":[42],"allows":[45],"more":[46],"intuitive":[47],"and":[48,54,61,86,125],"efficient":[49],"interactions":[50],"between":[51],"human":[52],"operators":[53],"medical":[55],"devices,":[56],"improving":[57],"both":[58],"diagnostic":[59],"accuracy":[60],"treatment":[62],"outcomes.":[63],"In":[64,100],"this":[65],"work,":[66],"we":[67,102],"design":[68],"CapsDT,":[69],"Diffusion":[71],"Transformer":[72],"model":[73],"for":[74],"robot":[76,107,111,129],"manipulation":[77],"stomach.":[80],"By":[81],"processing":[82],"interleaved":[83],"visual":[84],"inputs,":[85],"textual":[87],"instructions,":[88],"CapsDT":[89,143],"can":[90,144],"infer":[91],"corresponding":[92,127],"robotic":[93,115,139],"control":[94],"signals":[95],"to":[96],"facilitate":[97],"tasks.":[99],"addition,":[101],"developed":[103],"controlled":[112],"by":[113],"arm-held":[116],"magnet,":[117],"addressing":[118],"different":[119],"levels":[120,156],"four":[122],"tasks":[124,140,159],"creating":[126],"datasets":[130],"stomach":[133],"simulator.":[134],"Comprehensive":[135],"evaluations":[136],"on":[137],"various":[138,155],"indicate":[141],"serve":[145],"robust":[148],"vision-language":[149],"generalist,":[150],"achieving":[151,161],"state-of-the-art":[152],"while":[160],"26.25%":[163],"success":[164],"rate":[165],"real-world":[167],"simulation":[168],"manipulation.":[169]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}
