{"id":"https://openalex.org/W7141724551","doi":"https://doi.org/10.1109/lra.2026.3678454","title":"Flex: End-to-End Text-Instructed Visual Navigation From Foundation Model Features","display_name":"Flex: End-to-End Text-Instructed Visual Navigation From Foundation Model Features","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7141724551","doi":"https://doi.org/10.1109/lra.2026.3678454"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3678454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3678454","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-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/A5005163899","display_name":"Makram Chahine","orcid":"https://orcid.org/0000-0002-6807-7042"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Makram Chahine","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6807-7042","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119025633","display_name":"Alex Quach","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Quach","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060064468","display_name":"Alaa Maalouf","orcid":"https://orcid.org/0000-0002-3800-9460"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alaa Maalouf","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3800-9460","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017563787","display_name":"Tsun-Hsuan Wang","orcid":"https://orcid.org/0000-0002-7259-5686"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsun-Hsuan Wang","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7259-5686","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066830185","display_name":"Daniela Rus","orcid":"https://orcid.org/0000-0001-5473-3566"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniela Rus","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5473-3566","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory CSAIL, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31217296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"5","first_page":"6480","last_page":"6487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.631600022315979,"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":0.631600022315979,"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/T10799","display_name":"Data Visualization and Analytics","score":0.05990000069141388,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.04450000077486038,"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/visualization","display_name":"Visualization","score":0.3513999879360199},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.33379998803138733},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29190000891685486},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2700999975204468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5128999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4724999964237213},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45879998803138733},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27000001072883606},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2547000050544739},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2433999925851822}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3678454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3678454","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306077","display_name":"Boeing","ror":"https://ror.org/04sm5zn07"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2051224630","https://openalex.org/W2615547864","https://openalex.org/W2968983352","https://openalex.org/W2982419388","https://openalex.org/W3034445502","https://openalex.org/W3131287736","https://openalex.org/W3205220487","https://openalex.org/W3210065386","https://openalex.org/W3215048956","https://openalex.org/W4200438872","https://openalex.org/W4214926101","https://openalex.org/W4312282373","https://openalex.org/W4312563428","https://openalex.org/W4312910992","https://openalex.org/W4312956471","https://openalex.org/W4313136445","https://openalex.org/W4352977012","https://openalex.org/W4366371396","https://openalex.org/W4383108895","https://openalex.org/W4385431115","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4386285856","https://openalex.org/W4386918877","https://openalex.org/W4389665434","https://openalex.org/W4390874575","https://openalex.org/W4391827404","https://openalex.org/W4401415107"],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"learning":[1],"directly":[2],"maps":[3],"sensory":[4],"inputs":[5],"to":[6,23,31,50,131],"actions,":[7],"creating":[8],"highly":[9],"integrated":[10],"and":[11,35,46,63,99,138],"efficient":[12],"policies":[13,58],"for":[14],"complex":[15],"robotics":[16],"tasks.":[17],"However,":[18],"such":[19],"models":[20],"often":[21],"struggle":[22],"generalize":[24,130],"beyond":[25],"their":[26],"training":[27],"scenarios,":[28],"limiting":[29],"adaptability":[30],"new":[32],"environments,":[33],"tasks,":[34],"concepts.":[36],"In":[37],"this":[38,107],"work,":[39],"we":[40],"investigate":[41],"the":[42,104],"minimal":[43],"data":[44],"requirements":[45],"architectural":[47],"adaptations":[48],"necessary":[49],"achieve":[51],"robust":[52],"closed-loop":[53],"performance":[54],"with":[55,134],"vision-based":[56],"control":[57],"under":[59],"unseen":[60],"text":[61],"instructions":[62],"visual":[64,100],"distribution":[65],"shifts.":[66],"Our":[67],"findings":[68],"are":[69],"synthesized":[70],"in":[71],"Flex":[72],"(<italic":[73],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[74,76],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">F</i>ly-<italic":[75],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">lex</i>ically),":[77],"a":[78,110,121],"framework":[79],"that":[80,96],"uses":[81],"pre-trained":[82],"Vision":[83],"Language":[84],"Models":[85],"(VLMs)":[86],"as":[87],"frozen":[88],"patch-wise":[89],"feature":[90],"extractors,":[91],"generating":[92],"spatially":[93],"aware":[94],"embeddings":[95],"integrate":[97],"semantic":[98],"information.":[101],"We":[102],"demonstrate":[103],"effectiveness":[105],"of":[106],"approach":[108],"on":[109,120],"quadrotor":[111],"fly-to-target":[112],"task,":[113],"where":[114],"agents":[115],"trained":[116],"via":[117],"behavior":[118],"cloning":[119],"small":[122],"simulated":[123],"dataset":[124],"(with":[125],"zero":[126],"real-world":[127,132],"images)":[128],"successfully":[129],"scenes":[133],"diverse":[135],"novel":[136],"goals":[137],"command":[139],"formulations.":[140]},"counts_by_year":[],"updated_date":"2026-04-15T05:59:14.812645","created_date":"2026-03-28T00:00:00"}