{"id":"https://openalex.org/W4401415476","doi":"https://doi.org/10.1109/icra57147.2024.10610111","title":"Unifying Foundation Models with Quadrotor Control for Visual Tracking Beyond Object Categories","display_name":"Unifying Foundation Models with Quadrotor Control for Visual Tracking Beyond Object Categories","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401415476","doi":"https://doi.org/10.1109/icra57147.2024.10610111"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5026292215","display_name":"Alessandro Saviolo","orcid":"https://orcid.org/0000-0002-8308-1402"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alessandro Saviolo","raw_affiliation_strings":["New York University,Tandon School of Engineering,Brooklyn,NY,USA,11201"],"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111055148","display_name":"Pratyaksh Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratyaksh Rao","raw_affiliation_strings":["New York University,Tandon School of Engineering,Brooklyn,NY,USA,11201"],"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112132678","display_name":"Vivek Radhakrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Radhakrishnan","raw_affiliation_strings":["New York University,Tandon School of Engineering,Brooklyn,NY,USA,11201"],"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033664308","display_name":"Jiuhong Xiao","orcid":"https://orcid.org/0000-0002-7574-398X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiuhong Xiao","raw_affiliation_strings":["New York University,Tandon School of Engineering,Brooklyn,NY,USA,11201"],"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077485450","display_name":"Giuseppe Loianno","orcid":"https://orcid.org/0000-0002-3263-5401"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giuseppe Loianno","raw_affiliation_strings":["New York University,Tandon School of Engineering,Brooklyn,NY,USA,11201"],"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026292215"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":1.579,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84350166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7389","last_page":"7396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9997000098228455,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9994999766349792,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.7217370867729187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6860334873199463},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6022002696990967},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5693647265434265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5408940315246582},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.499767541885376},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47701191902160645},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4320376515388489},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3250443935394287},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06279528141021729}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7217370867729187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6860334873199463},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6022002696990967},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5693647265434265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5408940315246582},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.499767541885376},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47701191902160645},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4320376515388489},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3250443935394287},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06279528141021729},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"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:10.1109/icra57147.2024.10610111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W1506477171","https://openalex.org/W1861492603","https://openalex.org/W1903193263","https://openalex.org/W1970923953","https://openalex.org/W2076106578","https://openalex.org/W2089801374","https://openalex.org/W2098536261","https://openalex.org/W2143017962","https://openalex.org/W2166711818","https://openalex.org/W2167501464","https://openalex.org/W2553976574","https://openalex.org/W2557430988","https://openalex.org/W2747329762","https://openalex.org/W2751547291","https://openalex.org/W2755898301","https://openalex.org/W2765891159","https://openalex.org/W2895824696","https://openalex.org/W2910687636","https://openalex.org/W2954378215","https://openalex.org/W2955368974","https://openalex.org/W2963388701","https://openalex.org/W2964270628","https://openalex.org/W2965588739","https://openalex.org/W2966233967","https://openalex.org/W2993182889","https://openalex.org/W3015505697","https://openalex.org/W3016645518","https://openalex.org/W3035442500","https://openalex.org/W3037812513","https://openalex.org/W3089642910","https://openalex.org/W3092206239","https://openalex.org/W3130757488","https://openalex.org/W3144656351","https://openalex.org/W3196920896","https://openalex.org/W3202883604","https://openalex.org/W3205490848","https://openalex.org/W3205649931","https://openalex.org/W3214700612","https://openalex.org/W4236881204","https://openalex.org/W4248304976","https://openalex.org/W4283748233","https://openalex.org/W4286212714","https://openalex.org/W4286372820","https://openalex.org/W4295350588","https://openalex.org/W4297436774","https://openalex.org/W4308870024","https://openalex.org/W4310560841","https://openalex.org/W4312326540","https://openalex.org/W4312396403","https://openalex.org/W4312454273","https://openalex.org/W4313072750","https://openalex.org/W4313153453","https://openalex.org/W4317632731","https://openalex.org/W4319866011","https://openalex.org/W4321195201","https://openalex.org/W4323525809","https://openalex.org/W4360876082","https://openalex.org/W4366084253","https://openalex.org/W4367000115","https://openalex.org/W4377090795","https://openalex.org/W4378804727","https://openalex.org/W4379468852","https://openalex.org/W4382323286","https://openalex.org/W4382362889","https://openalex.org/W4383108590","https://openalex.org/W4383180710","https://openalex.org/W4385430610","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W4385834002","https://openalex.org/W4388823657","https://openalex.org/W4389331546","https://openalex.org/W4389667532","https://openalex.org/W4390874575","https://openalex.org/W6606706834","https://openalex.org/W6678589667","https://openalex.org/W6760405395","https://openalex.org/W6765456200","https://openalex.org/W6783068448","https://openalex.org/W6839204832","https://openalex.org/W6839744764","https://openalex.org/W6844186880","https://openalex.org/W6846643076","https://openalex.org/W6852276098","https://openalex.org/W6852703390","https://openalex.org/W6853219587","https://openalex.org/W6853815901","https://openalex.org/W6854738657"],"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/W2220552745","https://openalex.org/W2777605427"],"abstract_inverted_index":{"Visual":[0],"control":[1],"enables":[2],"quadrotors":[3],"to":[4,50,141],"adaptively":[5],"navigate":[6],"using":[7],"real-time":[8,26],"sensory":[9],"data,":[10],"bridging":[11],"perception":[12,32],"with":[13,58,69],"action.":[14],"Yet,":[15],"challenges":[16],"persist,":[17],"including":[18],"generalization":[19],"across":[20],"scenarios,":[21],"maintaining":[22],"reliability,":[23],"and":[24,42,75,103,115,123,144],"ensuring":[25,62],"responsiveness.":[27],"This":[28],"paper":[29],"introduces":[30],"a":[31,54,81,130],"framework":[33],"grounded":[34],"in":[35,111,133],"foundation":[36,60],"models":[37],"for":[38,85],"universal":[39],"object":[40],"detection":[41],"tracking,":[43,136],"moving":[44,137],"beyond":[45],"specific":[46],"training":[47],"categories.":[48],"Integral":[49],"our":[51,120,127],"approach":[52],"is":[53],"multi-layered":[55],"tracker":[56],"integrated":[57],"the":[59],"detector,":[61],"continuous":[63],"target":[64],"visibility,":[65],"even":[66],"when":[67],"faced":[68],"motion":[70],"blur,":[71],"abrupt":[72],"light":[73],"shifts,":[74],"occlusions.":[76],"Complementing":[77],"this,":[78],"we":[79,118],"introduce":[80],"model-free":[82],"controller":[83],"tailored":[84],"resilient":[86],"quadrotor":[87,134],"visual":[88,135],"tracking.":[89],"Our":[90],"system":[91],"operates":[92],"efficiently":[93],"on":[94,99],"limited":[95],"hardware,":[96],"relying":[97],"solely":[98],"an":[100,104],"onboard":[101],"camera":[102],"inertial":[105],"measurement":[106],"unit.":[107],"Through":[108],"extensive":[109],"validation":[110],"diverse":[112],"challenging":[113],"indoor":[114],"outdoor":[116],"environments,":[117],"demonstrate":[119],"system\u2019s":[121],"effectiveness":[122],"adaptability.":[124],"In":[125],"conclusion,":[126],"research":[128],"represents":[129],"step":[131],"forward":[132],"from":[138],"task-specific":[139],"methods":[140],"more":[142],"versatile":[143],"adaptable":[145],"operations.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}