{"id":"https://openalex.org/W4415748017","doi":"https://doi.org/10.1109/lra.2025.3627381","title":"VLM-SFD: VLM-Assisted Siamese Flow Diffusion Framework for Dual-Arm Cooperative Manipulation","display_name":"VLM-SFD: VLM-Assisted Siamese Flow Diffusion Framework for Dual-Arm Cooperative Manipulation","publication_year":2025,"publication_date":"2025-10-31","ids":{"openalex":"https://openalex.org/W4415748017","doi":"https://doi.org/10.1109/lra.2025.3627381"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3627381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3627381","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/A5100712713","display_name":"Jiaming Chen","orcid":"https://orcid.org/0000-0003-2235-4101"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiaming Chen","raw_affiliation_strings":["Department of Computer Science, The University of Manchester, Manchester, U.K","Department of Computer Science, The University of Manchester, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-2235-4101","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014709095","display_name":"Yiyu Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yiyu Jiang","raw_affiliation_strings":["Department of Computer Science, The University of Manchester, Manchester, U.K","Department of Computer Science, The University of Manchester, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0001-0012-6880","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040619149","display_name":"Aoshen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoshen Huang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0005-1020-2874","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Li","orcid":"https://orcid.org/0009-0002-7073-9698"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["Department of Computer Science, The University of Manchester, Manchester, U.K","Department of Computer Science, The University of Manchester, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0002-7073-9698","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wei Pan","orcid":"https://orcid.org/0000-0003-1121-9879"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Pan","raw_affiliation_strings":["Department of Computer Science, The University of Manchester, Manchester, U.K","Department of Computer Science, The University of Manchester, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1121-9879","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9042,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79870733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"11","issue":"1","first_page":"306","last_page":"313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9781000018119812,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9781000018119812,"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":0.005499999970197678,"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"}},{"id":"https://openalex.org/T10982","display_name":"Motor Control and Adaptation","score":0.005100000184029341,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7179999947547913},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6481000185012817},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5256999731063843},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.49950000643730164},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43549999594688416},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.34689998626708984},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3312999904155731}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7179999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087000012397766},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6481000185012817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5598000288009644},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3154999911785126},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2025.3627381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3627381","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"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/2dbef58a-acdf-4430-bb3a-c703a33f9ce9","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/2dbef58a-acdf-4430-bb3a-c703a33f9ce9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chen, J, Jiang, Y, Huang, A, Li, Y & Pan, W 2025, 'VLM-SFD: VLM-Assisted Siamese Flow Diffusion Framework for Dual-Arm Cooperative Manipulation', IEEE Robotics and Automation Letters. https://doi.org/10.1109/LRA.2025.3627381","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1994305306","https://openalex.org/W2760798180","https://openalex.org/W2800788658","https://openalex.org/W2898545349","https://openalex.org/W2900805829","https://openalex.org/W3043921574","https://openalex.org/W4206900136","https://openalex.org/W4220668453","https://openalex.org/W4226287632","https://openalex.org/W4307216775","https://openalex.org/W4362663195","https://openalex.org/W4383066296","https://openalex.org/W4385245566","https://openalex.org/W4385430674","https://openalex.org/W4389352485","https://openalex.org/W4390871749","https://openalex.org/W4392207798","https://openalex.org/W4402354026","https://openalex.org/W4402354112","https://openalex.org/W4402354127","https://openalex.org/W4403337227","https://openalex.org/W4403888324","https://openalex.org/W4404612908","https://openalex.org/W4405786709","https://openalex.org/W4407690624","https://openalex.org/W4409365031"],"related_works":[],"abstract_inverted_index":{"Dual-arm":[0],"cooperative":[1,76],"manipulation":[2,32,199],"holds":[3],"great":[4],"promise":[5],"for":[6,70],"tackling":[7],"complex":[8],"real-world":[9,96],"tasks":[10,33,97,200],"that":[11,142,154],"demand":[12],"seamless":[13],"coordination":[14],"and":[15,34,53,92,165,205],"adaptive":[16],"dynamics.":[17],"Despite":[18],"substantial":[19],"progress":[20],"in":[21,41,74],"learning-based":[22],"motion":[23,140,160,177],"planning,":[24],"most":[25],"approaches":[26],"struggle":[27],"to":[28,36,89,94,120,172,178,195,197],"generalize":[29,93,196],"across":[30],"diverse":[31,95,198],"adapt":[35,91],"dynamic,":[37],"unstructured":[38],"environments,":[39],"particularly":[40],"scenarios":[42],"involving":[43],"interactions":[44],"between":[45],"two":[46,122],"objects":[47,124],"such":[48],"as":[49],"assembly,":[50],"tool":[51],"use,":[52],"bimanual":[54],"grasping.":[55],"To":[56],"address":[57],"these":[58],"challenges,":[59],"we":[60,107],"introduce":[61],"a":[62,100,109,116,126,131,149,167],"novel":[63],"VLM-Assisted":[64],"Siamese":[65,110,118],"Flow":[66,111],"Diffusion":[67,112],"(VLM-SFD)":[68],"framework":[69,81],"efficient":[71],"imitation":[72],"learning":[73],"dual-arm":[75,144],"manipulation.":[77],"The":[78],"proposed":[79,190],"VLM-SFD":[80],"exhibits":[82],"outstanding":[83],"adaptability,":[84],"significantly":[85],"enhancing":[86],"the":[87,157,175,186,189],"ability":[88,194],"rapidly":[90],"from":[98],"only":[99],"minimal":[101],"number":[102],"of":[103,188],"human":[104],"demonstrations.":[105],"Specifically,":[106],"propose":[108],"Network":[113],"(SFDNet)":[114],"employs":[115],"dual-encoder-decoder":[117],"architecture":[119],"embed":[121],"target":[123],"into":[125,162],"shared":[127],"latent":[128],"space,":[129],"while":[130,201],"diffusion-based":[132],"conditioning":[133],"process-conditioned":[134],"by":[135],"task":[136,151],"instructions-generates":[137],"two-stream":[138],"object-centric":[139],"flows":[141,161],"guide":[143],"coordination.":[145],"We":[146],"further":[147],"design":[148],"dynamic":[150],"assignment":[152],"strategy":[153],"seamlessly":[155],"maps":[156],"predicted":[158],"2D":[159],"3D":[163],"space":[164],"incorporates":[166],"pre-trained":[168],"vision-language":[169],"model":[170],"(VLM)":[171],"adaptively":[173],"assign":[174],"optimal":[176],"each":[179],"robotic":[180],"arm":[181],"over":[182],"time.":[183],"Experiments":[184],"validate":[185],"effectiveness":[187],"method,":[191],"demonstrating":[192],"its":[193],"maintaining":[202],"high":[203],"efficiency":[204],"adaptability.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-31T00:00:00"}
