{"id":"https://openalex.org/W7131132180","doi":"https://doi.org/10.1109/robio66223.2025.11375936","title":"From Speech to Action: Design and Implementation of a Multimodal Robotic Grasping System Driven by Large Language Models","display_name":"From Speech to Action: Design and Implementation of a Multimodal Robotic Grasping System Driven by Large Language Models","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7131132180","doi":"https://doi.org/10.1109/robio66223.2025.11375936"},"language":null,"primary_location":{"id":"doi:10.1109/robio66223.2025.11375936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11375936","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/A5126616056","display_name":"Songji Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songji Chen","raw_affiliation_strings":["School of Electromechanical Engineering, Guangdong University of Technology,Biomimetic and Intelligent Robotics Lab (BIRL),Guangzhou,China,510006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electromechanical Engineering, Guangdong University of Technology,Biomimetic and Intelligent Robotics Lab (BIRL),Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009951648","display_name":"Qiaowen Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaowen Wu","raw_affiliation_strings":["School of Electromechanical Engineering, Guangdong University of Technology,Biomimetic and Intelligent Robotics Lab (BIRL),Guangzhou,China,510006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electromechanical Engineering, Guangdong University of Technology,Biomimetic and Intelligent Robotics Lab (BIRL),Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072422893","display_name":"Li Luo","orcid":"https://orcid.org/0000-0001-7975-0012"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Luo","raw_affiliation_strings":["School of Electromechanical Engineering, Guangdong University of Technology,Biomimetic and Intelligent Robotics Lab (BIRL),Guangzhou,China,510006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electromechanical Engineering, Guangdong University of Technology,Biomimetic and Intelligent Robotics Lab (BIRL),Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019083089","display_name":"Huan Xin Peng","orcid":"https://orcid.org/0000-0001-6648-9353"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Peng","raw_affiliation_strings":["School of Electromechanical Engineering, Guangdong University of Technology,Biomimetic and Intelligent Robotics Lab (BIRL),Guangzhou,China,510006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electromechanical Engineering, Guangdong University of Technology,Biomimetic and Intelligent Robotics Lab (BIRL),Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126587648","display_name":"Yisheng Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisheng Guan","raw_affiliation_strings":["School of Electromechanical Engineering, Guangdong University of Technology,Biomimetic and Intelligent Robotics Lab (BIRL),Guangzhou,China,510006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electromechanical Engineering, Guangdong University of Technology,Biomimetic and Intelligent Robotics Lab (BIRL),Guangzhou,China,510006","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81929943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1642","last_page":"1647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.508400022983551,"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":0.508400022983551,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.08190000057220459,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07970000058412552,"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/task","display_name":"Task (project management)","score":0.6518999934196472},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.6349999904632568},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5336999893188477},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4884999990463257},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4814000129699707},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4377000033855438},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.40869998931884766},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.40220001339912415},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.36039999127388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874000072479248},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6518999934196472},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.6349999904632568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5888000130653381},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5336999893188477},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5031999945640564},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4814000129699707},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.40869998931884766},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio66223.2025.11375936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio66223.2025.11375936","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2962737955","https://openalex.org/W3035198432","https://openalex.org/W3130885760","https://openalex.org/W4390874280","https://openalex.org/W4391053641","https://openalex.org/W4402890475","https://openalex.org/W4408807651"],"related_works":[],"abstract_inverted_index":{"Achieving":[0],"robotic":[1],"generalized":[2],"grasping":[3,29,65],"in":[4,135,173],"complex":[5,136],"or":[6],"unknown":[7],"environments":[8],"remains":[9],"a":[10,62,87],"major":[11],"challenge,":[12],"especially":[13],"when":[14],"tasks":[15],"involve":[16],"understanding":[17,182],"abstract":[18],"spatial":[19],"concepts":[20],"and":[21,35,46,82,85,111,118,147,170,176,183],"goal-oriented":[22],"instructions":[23],"expressed":[24],"through":[25],"natural":[26],"language.":[27],"Traditional":[28],"methods":[30],"rely":[31],"on":[32],"predefined":[33],"rules":[34],"large-scale":[36],"training":[37],"data,":[38],"limiting":[39],"their":[40],"ability":[41],"to":[42,59,98],"interpret":[43],"user":[44],"intent":[45],"support":[47],"effective":[48],"human-robot":[49],"interaction.":[50],"To":[51],"address":[52],"these":[53],"limitations,":[54],"we":[55],"propose":[56],"From":[57],"Speech":[58],"Action":[60],"(FSA),":[61],"hierarchical":[63],"multimodal":[64],"framework":[66],"that":[67,123,165],"leverages":[68],"the":[69,113,159],"semantic":[70],"reasoning":[71,89,149],"capability":[72],"of":[73,95,132],"large":[74],"language":[75],"models":[76],"(LLMs).":[77],"FSA":[78,124,166],"integrates":[79],"speech,":[80],"text,":[81],"visual":[83],"inputs,":[84],"introduces":[86],"novel":[88],"mechanism,":[90],"Task":[91],"Tree":[92],"with":[93,103,158],"Chain":[94],"Thought":[96],"(T-CoT),":[97],"build":[99],"an":[100,126],"intelligent":[101,184],"agent":[102,114],"human-like":[104],"cognitive":[105],"abilities.":[106],"By":[107],"simulating":[108],"human":[109],"observation":[110],"reasoning,":[112],"enables":[115],"more":[116,153],"adaptive":[117],"proactive":[119],"grasping.":[120],"Experiments":[121],"show":[122],"achieves":[125],"average":[127],"grasp":[128],"success":[129],"rate":[130],"(GSR)":[131],"85":[133],"%":[134,156],"scenarios,":[137],"improving":[138],"performance":[139],"by":[140,152],"over":[141],"<tex":[142],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[143],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{1":[144],"3}":[145],"\\%$</tex>":[146],"reducing":[148],"time":[150],"(RT)":[151],"than":[154],"25":[155],"compared":[157],"No-TCoT":[160],"baseline.":[161],"These":[162],"results":[163],"confirm":[164],"enhances":[167],"accuracy,":[168],"robustness,":[169],"task":[171],"adaptability":[172],"both":[174],"single-object":[175],"cluttered":[177],"multi-object":[178],"settings,":[179],"advancing":[180],"semantic-level":[181],"manipulation.":[185]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-24T00:00:00"}
