{"id":"https://openalex.org/W4417149628","doi":"https://doi.org/10.1109/tase.2026.3695438","title":"FAM-HRI: Foundation-Model Assisted Multimodal Human\u2013Robot Interaction Combining Gaze and Speech","display_name":"FAM-HRI: Foundation-Model Assisted Multimodal Human\u2013Robot Interaction Combining Gaze and Speech","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417149628","doi":"https://doi.org/10.1109/tase.2026.3695438"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2026.3695438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3695438","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Transactions on Automation Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.16492","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002297490","display_name":"Yuzhi Lai","orcid":"https://orcid.org/0009-0002-9976-7422"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yuzhi Lai","raw_affiliation_strings":["University of T&#x00FC;bingen, T&#x00FC;bingen, Germany"],"raw_orcid":"https://orcid.org/0009-0002-9976-7422","affiliations":[{"raw_affiliation_string":"University of T&#x00FC;bingen, T&#x00FC;bingen, Germany","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050656216","display_name":"Shenghai Yuan","orcid":"https://orcid.org/0009-0000-4850-2278"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shenghai Yuan","raw_affiliation_strings":["Nanyang Technological University, Nanyang Ave, Singapore"],"raw_orcid":"https://orcid.org/0009-0003-1887-6342","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Nanyang Ave, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108148711","display_name":"Peizheng Li","orcid":"https://orcid.org/0009-0006-8194-2770"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peizheng Li","raw_affiliation_strings":["University of T&#x00FC;bingen, T&#x00FC;bingen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2140-4357","affiliations":[{"raw_affiliation_string":"University of T&#x00FC;bingen, T&#x00FC;bingen, Germany","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100609044","display_name":"Boya Zhang","orcid":"https://orcid.org/0000-0001-8079-1364"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Boya Zhang","raw_affiliation_strings":["University of T&#x00FC;bingen, T&#x00FC;bingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T&#x00FC;bingen, T&#x00FC;bingen, Germany","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047571567","display_name":"Benjamin Kiefer","orcid":null},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Kiefer","raw_affiliation_strings":["University of T&#x00FC;bingen, T&#x00FC;bingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T&#x00FC;bingen, T&#x00FC;bingen, Germany","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078717226","display_name":"Tianchen Deng","orcid":"https://orcid.org/0000-0002-4368-7936"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianchen Deng","raw_affiliation_strings":["Nanyang Technological University, Nanyang Ave, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Nanyang Ave, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004958444","display_name":"Andreas Zell","orcid":"https://orcid.org/0000-0003-3299-2211"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Zell","raw_affiliation_strings":["University of T&#x00FC;bingen, T&#x00FC;bingen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3299-2211","affiliations":[{"raw_affiliation_string":"University of T&#x00FC;bingen, T&#x00FC;bingen, Germany","institution_ids":["https://openalex.org/I143910747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":24.0563,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98571077,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"23","issue":null,"first_page":"10521","last_page":"10534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.5742999911308289,"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"}},"topics":[{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.5742999911308289,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.22439999878406525,"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":0.07039999961853027,"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/gaze","display_name":"Gaze","score":0.7027000188827515},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.631600022315979},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6312999725341797},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5091000199317932},{"id":"https://openalex.org/keywords/fixation","display_name":"Fixation (population genetics)","score":0.5027999877929688},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4932999908924103},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4860999882221222},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.47690001130104065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305999994277954},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.7174999713897705},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7027000188827515},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.631600022315979},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6312999725341797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5163000226020813},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5091000199317932},{"id":"https://openalex.org/C146249460","wikidata":"https://www.wikidata.org/wiki/Q2914991","display_name":"Fixation (population genetics)","level":3,"score":0.5027999877929688},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4932999908924103},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.43130001425743103},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.3292999863624573},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3095000088214874},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C121449826","wikidata":"https://www.wikidata.org/wiki/Q864114","display_name":"Input device","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C62402345","wikidata":"https://www.wikidata.org/wiki/Q18921192","display_name":"Interaction technique","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tase.2026.3695438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3695438","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Transactions on Automation Science and Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2503.16492","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.16492","pdf_url":"https://arxiv.org/pdf/2503.16492","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.16492","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16492","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.16492","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.16492","pdf_url":"https://arxiv.org/pdf/2503.16492","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319290","display_name":"Meta","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Effective":[0],"Human-Robot":[1],"Interaction":[2],"(HRI)":[3],"is":[4],"crucial":[5],"for":[6,31,46,128],"enhancing":[7],"accessibility":[8],"and":[9,28,51,69,84,148],"usability":[10],"in":[11,115],"real-world":[12],"robotics":[13],"applications.":[14],"However,":[15],"existing":[16],"solutions":[17,149],"often":[18],"rely":[19],"on":[20],"gesture-only":[21],"or":[22,134],"language-only":[23],"commands,":[24],"making":[25],"interaction":[26,122],"inefficient":[27],"ambiguous,":[29],"particularly":[30],"users":[32],"with":[33,79,130],"physical":[34,132],"impairments.":[35,136],"In":[36],"this":[37],"paper,":[38],"we":[39,141],"introduce":[40],"FAM-HRI,":[41],"an":[42],"efficient":[43],"multimodal":[44,67],"framework":[45],"HRI":[47],"that":[48,108],"integrates":[49],"language":[50,72],"gaze":[52,93,102],"inputs":[53],"via":[54],"foundation":[55],"models.":[56],"By":[57],"leveraging":[58],"lightweight":[59],"Meta":[60],"ARIA":[61],"glasses,":[62],"our":[63,144],"system":[64,145],"captures":[65],"real-time":[66],"signals":[68],"utilizes":[70],"large":[71],"models":[73],"(LLMs)":[74],"to":[75],"fuse":[76],"user":[77],"intention":[78],"scene":[80],"context,":[81],"enabling":[82],"intuitive":[83],"precise":[85],"robot":[86],"manipulation.":[87],"Our":[88],"method":[89],"accurately":[90],"determines":[91],"the":[92,101,139],"fixation":[94],"time":[95],"interval,":[96],"reducing":[97],"noise":[98],"caused":[99],"by":[100],"dynamic":[103],"nature.":[104],"Experimental":[105],"evaluations":[106],"demonstrate":[107],"FAM-HRI":[109],"achieves":[110],"a":[111,120,125],"high":[112],"success":[113],"rate":[114],"task":[116],"execution":[117],"while":[118],"maintaining":[119],"low":[121],"time,":[123],"providing":[124],"practical":[126],"solution":[127],"individuals":[129],"limited":[131],"mobility":[133],"motor":[135],"To":[137],"support":[138],"community,":[140],"have":[142],"released":[143],"design,":[146],"algorithms,":[147],"at":[150],"https://github.com/laiyuzhi/FAM-HRI.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}
