{"id":"https://openalex.org/W7125782092","doi":"https://doi.org/10.1016/j.rcim.2026.103244","title":"VL-GRiP3: A hierarchical pipeline leveraging vision-language models for autonomous robotic 3D grasping","display_name":"VL-GRiP3: A hierarchical pipeline leveraging vision-language models for autonomous robotic 3D grasping","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125782092","doi":"https://doi.org/10.1016/j.rcim.2026.103244"},"language":"en","primary_location":{"id":"doi:10.1016/j.rcim.2026.103244","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.rcim.2026.103244","pdf_url":null,"source":{"id":"https://openalex.org/S118216261","display_name":"Robotics and Computer-Integrated Manufacturing","issn_l":"0736-5845","issn":["0736-5845","1879-2537"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Computer-Integrated Manufacturing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.rcim.2026.103244","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124026569","display_name":"Mirco Polonara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mirco Polonara","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-5229-8920","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123942014","display_name":"Xingyu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086638747","display_name":"Luca Carbonari","orcid":"https://orcid.org/0000-0003-4342-3751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luca Carbonari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124013584","display_name":"Xuping Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuping Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":4240,"currency":"USD","value_usd":4240},"apc_paid":{"value":4240,"currency":"USD","value_usd":4240},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08863756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"100","issue":null,"first_page":"103244","last_page":"103244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8098999857902527,"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":0.8098999857902527,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.026100000366568565,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.018300000578165054,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/grasp","display_name":"GRASP","score":0.777899980545044},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.650600016117096},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6294999718666077},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.619700014591217},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5424000024795532},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5167999863624573},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.40059998631477356},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3871000111103058}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.777899980545044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6704000234603882},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.650600016117096},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6294999718666077},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49059998989105225},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.40059998631477356},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.301800012588501},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C17511633","wikidata":"https://www.wikidata.org/wiki/Q830694","display_name":"SMT placement equipment","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C2776126113","wikidata":"https://www.wikidata.org/wiki/Q1128980","display_name":"Industrial robot","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2676999866962433}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.rcim.2026.103244","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.rcim.2026.103244","pdf_url":null,"source":{"id":"https://openalex.org/S118216261","display_name":"Robotics and Computer-Integrated Manufacturing","issn_l":"0736-5845","issn":["0736-5845","1879-2537"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Computer-Integrated Manufacturing","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/b63ca405-bc42-431b-9cef-1b429cee2117","is_oa":true,"landing_page_url":"https://pure.au.dk/portal/en/publications/b63ca405-bc42-431b-9cef-1b429cee2117","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Polonara, M, Yang, X, Carbonari, L & Zhang, X 2026, 'VL-GRiP3 : A hierarchical pipeline leveraging vision-language models for autonomous robotic 3D grasping', Robotics and Computer-Integrated Manufacturing, vol. 100, 103244. https://doi.org/10.1016/j.rcim.2026.103244","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.univpm.it:11566/358013","is_oa":true,"landing_page_url":"https://hdl.handle.net/11566/358013","pdf_url":null,"source":{"id":"https://openalex.org/S4306402571","display_name":"Universit\u00e0 Politecnica delle Marche (Universit\u00e0 Politecnica delle Marche)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122534668","host_organization_name":"Marche Polytechnic University","host_organization_lineage":["https://openalex.org/I122534668"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.rcim.2026.103244","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.rcim.2026.103244","pdf_url":null,"source":{"id":"https://openalex.org/S118216261","display_name":"Robotics and Computer-Integrated Manufacturing","issn_l":"0736-5845","issn":["0736-5845","1879-2537"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics and Computer-Integrated Manufacturing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2005824379","https://openalex.org/W2036637075","https://openalex.org/W2085949256","https://openalex.org/W2896348597","https://openalex.org/W2963341956","https://openalex.org/W2968635090","https://openalex.org/W3035198432","https://openalex.org/W3088158297","https://openalex.org/W3177280664","https://openalex.org/W3194737599","https://openalex.org/W4324259511","https://openalex.org/W4362561002","https://openalex.org/W4387431644","https://openalex.org/W4392916039","https://openalex.org/W4402272838","https://openalex.org/W4407598244","https://openalex.org/W4413491481"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"grasping":[1,87,203],"has":[2],"long":[3],"been":[4],"a":[5,77,110,121,196],"central":[6],"topic":[7],"in":[8,12,66,97,109,142],"robotics,":[9],"yet":[10,57],"deployment":[11],"small":[13],"and":[14,25,46,54,93,106,116,131,151,193,228],"medium-sized":[15],"enterprises":[16],"(SMEs)":[17],"is":[18],"still":[19,50],"hindered":[20],"by":[21],"low-level":[22],"robot":[23],"programming":[24],"the":[26,169],"lack":[27],"of":[28,176],"natural":[29,40,90,126],"language":[30,41,91,103,127],"interaction.":[31],"Recent":[32],"Vision-Language-Action":[33],"models":[34],"(VLAs)":[35],"allow":[36],"robots":[37],"to":[38,60,191],"interpret":[39],"commands":[42],"for":[43,83,164,231],"intuitive":[44],"interaction":[45,92],"control,":[47],"but":[48],"they":[49],"exhibit":[51],"output":[52],"uncertainty":[53],"are":[55],"not":[56],"well":[58],"suited":[59],"directly":[61],"generating":[62],"reliable,":[63],"precise":[64],"actions":[65],"safety-critical":[67],"industrial":[68,178],"contexts.":[69],"To":[70],"address":[71],"this":[72,119],"gap,":[73],"we":[74],"present":[75],"VL-GRiP3,":[76],"hierarchical":[78],"Vision-Language":[79],"model":[80],"(VLM)-enabled":[81],"pipeline":[82],"autonomous":[84],"3D":[85,158,221],"robotic":[86],"that":[88,161,182,214],"bridges":[89],"accurate,":[94],"reliable":[95,174,227],"manipulation":[96,175],"SME":[98,232],"settings.":[99],"The":[100],"framework":[101],"decomposes":[102],"understanding,":[104],"perception,":[105,130],"action":[107,133],"planning":[108],"transparent":[111],"modular":[112],"architecture,":[113,120],"improving":[114],"flexibility":[115],"interpretability.":[117],"Within":[118],"single":[122,143],"VLM":[123,185],"backbone":[124],"handles":[125],"interpretation,":[128],"target":[129],"high-level":[132],"planning.":[134],"CAD-augmented":[135,217],"point":[136,171],"cloud":[137],"registration":[138],"then":[139],"mitigates":[140],"occlusions":[141],"RGB-D":[144],"views":[145],"while":[146],"keeping":[147],"hardware":[148],"cost":[149],"low,":[150],"an":[152],"M2T2-based":[153],"grasp":[154,159,222],"planner":[155],"predicts":[156],"accurate":[157],"poses":[160],"explicitly":[162],"account":[163],"complex":[165],"object":[166],"geometry":[167],"from":[168],"augmented":[170],"cloud,":[172],"enabling":[173],"irregular":[177],"parts.":[179],"Experiments":[180],"show":[181],"our":[183,215],"fine-tuned":[184],"modules":[186],"achieve":[187],"segmentation":[188],"performance":[189],"comparable":[190],"YOLOv8n,":[192],"VL-GRiP3":[194],"attains":[195],"94.67%":[197],"success":[198],"rate":[199],"over":[200],"150":[201],"randomized":[202],"trials.":[204],"A":[205],"comparative":[206],"evaluation":[207],"against":[208],"state-of-the-art":[209],"end-to-end":[210],"VLAs":[211],"further":[212],"indicates":[213],"modular,":[216],"design":[218],"with":[219],"explicit":[220],"pose":[223],"prediction":[224],"yields":[225],"more":[226],"controllable":[229],"behavior":[230],"manufacturing":[233],"applications.":[234]},"counts_by_year":[],"updated_date":"2026-01-28T23:18:48.515280","created_date":"2026-01-28T00:00:00"}