{"id":"https://openalex.org/W7126092470","doi":"https://doi.org/10.1109/comcomap68359.2025.11353191","title":"Integrating Multimodal AI Services into Pepper for Natural Human-Robot Interaction","display_name":"Integrating Multimodal AI Services into Pepper for Natural Human-Robot Interaction","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7126092470","doi":"https://doi.org/10.1109/comcomap68359.2025.11353191"},"language":null,"primary_location":{"id":"doi:10.1109/comcomap68359.2025.11353191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/comcomap68359.2025.11353191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Computing, Communications and IoT Applications (ComComAp)","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/A5121773569","display_name":"Avvai Chandrasekaran","orcid":null},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Avvai Chandrasekaran","raw_affiliation_strings":["Georgia State University,Dept. of Computer Science,Atlanta,GA,USA"],"affiliations":[{"raw_affiliation_string":"Georgia State University,Dept. of Computer Science,Atlanta,GA,USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124289038","display_name":"Sebastien Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastien Lee","raw_affiliation_strings":["Georgia Institute of Technology,Dept. of Computer Science,Atlanta,GA,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Dept. of Computer Science,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122966955","display_name":"Anu G. Bourgeois","orcid":null},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anu G. Bourgeois","raw_affiliation_strings":["Georgia State University,Dept. of Computer Science,Atlanta,GA,USA"],"affiliations":[{"raw_affiliation_string":"Georgia State University,Dept. of Computer Science,Atlanta,GA,USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079063339","display_name":"Rajshekhar Sunderraman","orcid":"https://orcid.org/0000-0001-6822-6629"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajshekhar Sunderraman","raw_affiliation_strings":["Georgia State University,Dept. of Computer Science,Atlanta,GA,USA"],"affiliations":[{"raw_affiliation_string":"Georgia State University,Dept. of Computer Science,Atlanta,GA,USA","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5121773569"],"corresponding_institution_ids":["https://openalex.org/I181565077"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73536924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4514999985694885,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4514999985694885,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.15680000185966492,"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/T12031","display_name":"Speech and dialogue systems","score":0.10520000010728836,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6816999912261963},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.6406999826431274},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5658000111579895},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5034999847412109},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4634999930858612},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.41769999265670776}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6816999912261963},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6406999826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5999000072479248},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.48809999227523804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4636000096797943},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.41769999265670776},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.40869998931884766},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.34220001101493835},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/comcomap68359.2025.11353191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/comcomap68359.2025.11353191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Computing, Communications and IoT Applications (ComComAp)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6967337727546692}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2157837575","https://openalex.org/W2871950322","https://openalex.org/W2901645617","https://openalex.org/W4281643269","https://openalex.org/W4402819134","https://openalex.org/W4405036395"],"related_works":[],"abstract_inverted_index":{"Humanoid":[0],"robots":[1],"such":[2],"as":[3],"Softbank\u2019s":[4],"Pepper":[5,52,97],"have":[6],"demonstrated":[7],"strong":[8],"potential":[9],"for":[10,105],"facilitating":[11],"human":[12],"interaction":[13],"in":[14],"retail,":[15],"hospitality,":[16],"and":[17,38,61,69,86],"educational":[18],"settings.":[19],"However,":[20],"their":[21],"conversational":[22],"abilities":[23],"are":[24],"often":[25],"limited":[26,39],"by":[27],"narrow":[28],"natural":[29,70],"language":[30,58],"processing":[31],"(NLP)":[32],"models,":[33],"reliance":[34],"on":[35],"pre-scripted":[36],"responses,":[37],"context":[40],"retention.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,91],"present":[46],"a":[47,78,82,99],"multimodal":[48],"pipeline":[49,84],"that":[50],"integrates":[51],"with":[53],"speech":[54],"recognition":[55],"(STT),":[56],"large":[57],"models":[59,63],"(LLMs),":[60],"vision-language":[62],"(VLMs)":[64],"to":[65],"enable":[66],"dynamic,":[67],"context-aware,":[68],"interactions.":[71],"We":[72],"detail":[73],"the":[74],"system":[75],"architecture,":[76],"including":[77],"NAOqi-based":[79],"Choregraphe":[80],"application,":[81],"custom":[83],"service,":[85],"AI-powered":[87],"RESTful":[88],"services.":[89],"Finally,":[90],"discuss":[92],"future":[93],"work":[94],"toward":[95],"developing":[96],"into":[98],"fully":[100],"autonomous":[101],"humanoid":[102],"tour":[103],"guide":[104],"Georgia":[106],"State":[107],"University.":[108]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-30T00:00:00"}
