{"id":"https://openalex.org/W4409479999","doi":"https://doi.org/10.14428/esann/2025.es2025-35","title":"Open-Vocabulary Robotic Object Manipulation using Foundation Models","display_name":"Open-Vocabulary Robotic Object Manipulation using Foundation Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409479999","doi":"https://doi.org/10.14428/esann/2025.es2025-35"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2025.es2025-35","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-35","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-35","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2025.es2025-35","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117166116","display_name":"Stig Griebenow","orcid":null},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Stig Griebenow","raw_affiliation_strings":["University of Hamburg -Knowledge Technology Group Vogt-Klln-Strae 30 , 22527 Hamburg - Germany"],"affiliations":[{"raw_affiliation_string":"University of Hamburg -Knowledge Technology Group Vogt-Klln-Strae 30 , 22527 Hamburg - Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102301388","display_name":"Ozan \u00d6zdemir","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ozan \u00d6zdemir","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["University of Hamburg -Knowledge Technology Group Vogt-Klln-Strae 30 , 22527 Hamburg - Germany"],"affiliations":[{"raw_affiliation_string":"University of Hamburg -Knowledge Technology Group Vogt-Klln-Strae 30 , 22527 Hamburg - Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["University of Hamburg -Knowledge Technology Group Vogt-Klln-Strae 30 , 22527 Hamburg - Germany"],"affiliations":[{"raw_affiliation_string":"University of Hamburg -Knowledge Technology Group Vogt-Klln-Strae 30 , 22527 Hamburg - Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5117166116"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03311281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"633","last_page":"638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9865999817848206,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9865999817848206,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9448999762535095,"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/foundation","display_name":"Foundation (evidence)","score":0.7426620125770569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6819865703582764},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6025513410568237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5598637461662292},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.554109513759613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41729605197906494},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3794843852519989},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3227125406265259},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15017056465148926}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7426620125770569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819865703582764},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6025513410568237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5598637461662292},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.554109513759613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41729605197906494},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3794843852519989},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3227125406265259},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15017056465148926},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2025.es2025-35","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-35","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-35","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2025.es2025-35","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-35","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-35","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7226905331","display_name":null,"funder_award_id":"TRR-169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409479999.pdf","grobid_xml":"https://content.openalex.org/works/W4409479999.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2082511574","https://openalex.org/W2771461682","https://openalex.org/W2975395092","https://openalex.org/W2981852735","https://openalex.org/W4381249600","https://openalex.org/W4385473486","https://openalex.org/W4391417118","https://openalex.org/W4394989737","https://openalex.org/W4402364458"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2790817834","https://openalex.org/W2777605427","https://openalex.org/W2501983714"],"abstract_inverted_index":{"Classical":[0],"vision-language-action":[1,88],"models":[2],"are":[3],"limited":[4],"by":[5],"unidirectional":[6],"communication,":[7],"hindering":[8],"natural":[9],"human-robot":[10],"interaction.The":[11],"recent":[12],"CrossT5":[13,44],"embeds":[14],"an":[15,21],"efficient":[16],"vision":[17],"action":[18],"pathway":[19],"into":[20,43],"LLM,":[22],"but":[23],"lacks":[24],"visual":[25],"generalization,":[26],"restricting":[27],"actions":[28,48],"to":[29,45],"objects":[30],"seen":[31],"during":[32],"training.We":[33],"introduce":[34],"OWLT5,":[35],"which":[36],"integrates":[37],"the":[38,59,66],"OWLv2":[39],"object":[40,80],"detection":[41],"model":[42],"enable":[46],"robot":[47,62],"on":[49,54,65],"unseen":[50,73],"objects.OWLT5":[51],"is":[52],"trained":[53],"a":[55],"simulated":[56],"dataset":[57,69],"using":[58],"NICO":[60],"humanoid":[61],"and":[63],"evaluated":[64],"new":[67],"CLAEO":[68],"featuring":[70],"interactions":[71],"with":[72],"objects.Results":[74],"show":[75],"that":[76],"OWLT5":[77],"achieves":[78],"zero-shot":[79],"recognition":[81],"for":[82],"robotic":[83],"manipulation,":[84],"while":[85],"efficiently":[86],"integrating":[87],"capabilities.":[89]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
