{"id":"https://openalex.org/W7131067306","doi":"https://doi.org/10.1109/robio66223.2025.11375938","title":"Multimodal-Driven Intelligent Grasping Decision System: A Semantic-Visual-Physical End-to-End Collaborative Architecture","display_name":"Multimodal-Driven Intelligent Grasping Decision System: A Semantic-Visual-Physical End-to-End Collaborative Architecture","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7131067306","doi":"https://doi.org/10.1109/robio66223.2025.11375938"},"language":null,"primary_location":{"id":"doi:10.1109/robio66223.2025.11375938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11375938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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/A5108750593","display_name":"Songtao Ding","orcid":"https://orcid.org/0000-0002-5439-1508"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Songtao Ding","raw_affiliation_strings":["Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126657958","display_name":"Zhen Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Fang","raw_affiliation_strings":["Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422649","display_name":"Hongyu Wang","orcid":"https://orcid.org/0000-0002-5063-9166"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Wang","raw_affiliation_strings":["Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123993946","display_name":"Mengsen Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengsen Zhao","raw_affiliation_strings":["Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Posts & Telecommunications,Embodied intelligent laboratory,Xi'an,China,710000","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108750593"],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88494999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1227","last_page":"1232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.12970000505447388,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.12970000505447388,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1251000016927719,"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"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.04270000010728836,"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/ambiguity","display_name":"Ambiguity","score":0.7857999801635742},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.7635999917984009},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6069999933242798},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.439300000667572},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.43220001459121704},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41040000319480896},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4034999907016754},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.38040000200271606},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3644999861717224}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7857999801635742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7702999711036682},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7635999917984009},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6069999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5570999979972839},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38769999146461487},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C95203288","wikidata":"https://www.wikidata.org/wiki/Q221682","display_name":"Semaphore","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio66223.2025.11375938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11375938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2489434015","https://openalex.org/W3035198432","https://openalex.org/W3204876017","https://openalex.org/W3207187156","https://openalex.org/W4205569741","https://openalex.org/W4312920279","https://openalex.org/W4383108836","https://openalex.org/W4385430679","https://openalex.org/W4387092545","https://openalex.org/W4389667112","https://openalex.org/W4391594284","https://openalex.org/W4401416671","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"To":[0],"address":[1],"challenges":[2],"in":[3,90],"robotic":[4],"grasping,":[5],"such":[6],"as":[7],"multi-instance":[8],"ambiguity":[9,40],"and":[10,26,68,86],"implicit":[11],"instruction":[12],"understanding,":[13],"this":[14],"paper":[15],"proposes":[16],"an":[17,102],"intelligent":[18],"framework":[19],"integrating":[20],"multimodal":[21],"interaction,":[22],"multi-view":[23,51],"3D":[24,61],"modeling,":[25],"collisionaware":[27],"optimization.":[28],"Key":[29],"innovations":[30],"include:":[31],"1)":[32],"A":[33,50,70],"GPT-4obased":[34],"interactive":[35],"module":[36],"that":[37,75],"resolves":[38],"target":[39],"via":[41],"natural":[42],"language":[43],"queries":[44],"for":[45],"precise":[46],"instance-level":[47],"localization;":[48],"2)":[49],"point":[52],"cloud":[53],"fusion":[54],"network":[55],"with":[56,93],"LangSAM":[57],"to":[58],"build":[59],"accurate":[60],"geometric":[62],"representations,":[63],"enhancing":[64],"grasp":[65,77],"pose":[66],"accuracy;":[67],"3)":[69],"bounding":[71],"box-based":[72],"filtering":[73],"mechanism":[74],"optimizes":[76],"strategies":[78],"through":[79],"a":[80],"dynamic":[81],"weighting":[82],"of":[83],"reachability,":[84],"stability,":[85],"collision":[87],"risk.":[88],"Experiments":[89],"complex":[91],"scenarios":[92],"over":[94],"10":[95],"similar":[96],"objects":[97],"show":[98],"our":[99],"method":[100],"achieves":[101],"82.7":[103],"%":[104],"average":[105],"success":[106],"rate,":[107],"outperforming":[108],"the":[109],"state-of-the-art":[110],"(ThinkGrasp)":[111],"by":[112],"7.9":[113],"%.":[114]},"counts_by_year":[],"updated_date":"2026-02-25T06:17:34.324206","created_date":"2026-02-24T00:00:00"}