{"id":"https://openalex.org/W4413979245","doi":"https://doi.org/10.1109/rcar65431.2025.11139480","title":"RoboFlamingo-Plus: Fusion of Depth and RGB Perception with Vision-Language Models for Enhanced Robotic Manipulation","display_name":"RoboFlamingo-Plus: Fusion of Depth and RGB Perception with Vision-Language Models for Enhanced Robotic Manipulation","publication_year":2025,"publication_date":"2025-06-01","ids":{"openalex":"https://openalex.org/W4413979245","doi":"https://doi.org/10.1109/rcar65431.2025.11139480"},"language":"en","primary_location":{"id":"doi:10.1109/rcar65431.2025.11139480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar65431.2025.11139480","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 Real-time Computing and Robotics (RCAR)","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/A5100679806","display_name":"Xiaojian Li","orcid":"https://orcid.org/0000-0002-3175-7810"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaojian Li","raw_affiliation_strings":["Hefei University of Technology,School of Management,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Management,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371249","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0001-9923-4381"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Wang","raw_affiliation_strings":["Hefei University of Technology,School of Electrical Engineering and Automation,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Electrical Engineering and Automation,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408370","display_name":"Chao Chen","orcid":"https://orcid.org/0000-0002-8061-0292"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Chen","raw_affiliation_strings":["Hefei University of Technology,School of Management,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Management,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002952783","display_name":"Hongtao Wei","orcid":"https://orcid.org/0000-0001-5920-2019"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Wei","raw_affiliation_strings":["Hefei University of Technology,School of Management,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Management,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112528684","display_name":"Yudong Shi","orcid":"https://orcid.org/0000-0003-4379-6638"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Shi","raw_affiliation_strings":["Hefei University of Technology,School of Management,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Management,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033077344","display_name":"Hangjie Mo","orcid":"https://orcid.org/0000-0001-8628-3838"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangjie Mo","raw_affiliation_strings":["Hefei University of Technology,School of Management,Hefei,China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Management,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100679806"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.356968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"311","last_page":"316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9822999835014343,"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":0.9822999835014343,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T12549","display_name":"Image and Object Detection Techniques","score":0.9480999708175659,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6544482111930847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6238934993743896},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6166407465934753},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5997422337532043},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5781011581420898},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5754188299179077},{"id":"https://openalex.org/keywords/depth-perception","display_name":"Depth perception","score":0.4466377794742584},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1530930995941162},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10644841194152832},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05896267294883728}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6544482111930847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6238934993743896},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6166407465934753},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5997422337532043},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5781011581420898},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5754188299179077},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.4466377794742584},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1530930995941162},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10644841194152832},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05896267294883728},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcar65431.2025.11139480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcar65431.2025.11139480","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 Real-time Computing and Robotics (RCAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2760103357","https://openalex.org/W2891177506","https://openalex.org/W3176484337","https://openalex.org/W4285218426","https://openalex.org/W4285601030","https://openalex.org/W4293498911","https://openalex.org/W4383109478","https://openalex.org/W4385245566","https://openalex.org/W4385430679","https://openalex.org/W4401416041","https://openalex.org/W4402727516"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W2486460843","https://openalex.org/W2168109476","https://openalex.org/W1968121071","https://openalex.org/W2061647633","https://openalex.org/W3203087560","https://openalex.org/W2020254986","https://openalex.org/W2686985752","https://openalex.org/W1992540108","https://openalex.org/W3171276242"],"abstract_inverted_index":{"As":[0],"robotics":[1],"advances":[2],"towards":[3],"complex":[4],"multimodal":[5,74],"interactions":[6],"and":[7,24,30,90],"manipulation":[8,50,101],"tasks,":[9],"integrating":[10,43],"Vision-Language":[11],"Models":[12],"(VLMs)":[13],"has":[14],"become":[15],"crucial.":[16],"Despite":[17],"progress,":[18],"challenges":[19],"remain":[20],"in":[21,27],"fusing":[22],"depth":[23,44,80,87],"RGB":[25],"information":[26],"3D":[28],"environments":[29],"executing":[31],"language-guided":[32],"tasks.":[33],"To":[34],"address":[35],"these,":[36],"we":[37],"introduce":[38],"RoboFlamingo-Plus,":[39],"enhancing":[40],"RoboFlamingo":[41],"by":[42,58,103],"data":[45,68],"into":[46],"VLMs,":[47],"significantly":[48],"improving":[49],"performance.":[51],"Our":[52],"research":[53],"achieves":[54],"nuanced":[55],"RGB-depth":[56],"fusion":[57],"combining":[59],"a":[60,83,106],"pre-trained":[61,84],"Vision":[62],"Transformer":[63],"(ViT)":[64],"with":[65,69],"resampling,":[66],"aligning":[67],"linguistic":[70],"cues":[71],"for":[72,79,86,93],"superior":[73],"understanding.":[75],"RoboFlamingo-Plus":[76,99],"adapts":[77],"inputs":[78],"processing,":[81],"uses":[82],"resampler":[85],"feature":[88,95],"extraction,":[89],"employs":[91],"cross-attention":[92],"optimal":[94],"integration.":[96],"Experiments":[97],"show":[98],"boosts":[100],"performance":[102],"10-20%,":[104],"marking":[105],"significant":[107],"advancement.":[108]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}