{"id":"https://openalex.org/W4416750587","doi":"https://doi.org/10.1109/iros60139.2025.11247773","title":"UAV-MaLO: Mamba-Augmented YOLO Hybrid Architecture for UAV Micro-Object Detection in Autonomous Robotics","display_name":"UAV-MaLO: Mamba-Augmented YOLO Hybrid Architecture for UAV Micro-Object Detection in Autonomous Robotics","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750587","doi":"https://doi.org/10.1109/iros60139.2025.11247773"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Lennox Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lennox Wei","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology, Faculty of Computing,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology, Faculty of Computing,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014915112","display_name":"Shixin Sun","orcid":"https://orcid.org/0000-0003-1603-5868"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixin Sun","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology, Faculty of Computing,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology, Faculty of Computing,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031092444","display_name":"J. M. Yao","orcid":"https://orcid.org/0000-0001-9505-1852"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Yao","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology, Faculty of Computing,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology, Faculty of Computing,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110086384","display_name":"Yachun Mi","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yachun Mi","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology, Faculty of Computing,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology, Faculty of Computing,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109656059","display_name":"Xiangyu Sui","orcid":"https://orcid.org/0000-0002-9124-4822"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Sui","raw_affiliation_strings":["Meituan Group,Beijing,China,100102"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Group,Beijing,China,100102","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324378","display_name":"Heng Chen","orcid":"https://orcid.org/0000-0001-6256-4184"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Chen","raw_affiliation_strings":["Kuaishou Technology,Beijing,China,100085"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China,100085","institution_ids":["https://openalex.org/I4210155967"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445780","display_name":"Shaohui Liu","orcid":"https://orcid.org/0000-0002-1810-5412"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohui Liu","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology, Faculty of Computing,Harbin,China,150001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology, Faculty of Computing,Harbin,China,150001","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8187","last_page":"8193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6277999877929688,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6277999877929688,"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/T11133","display_name":"UAV Applications and Optimization","score":0.19850000739097595,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.01730000041425228,"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/drone","display_name":"Drone","score":0.6524999737739563},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5892000198364258},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4415000081062317},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.423799991607666},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.39309999346733093},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3718000054359436},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35499998927116394},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33160001039505005}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7064999938011169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7050999999046326},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.6524999737739563},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5892000198364258},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4465000033378601},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.423799991607666},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.2574999928474426},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2068730032","https://openalex.org/W2145023731","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2954996726","https://openalex.org/W2962766617","https://openalex.org/W2962834855","https://openalex.org/W2989611864","https://openalex.org/W3034552520","https://openalex.org/W3047237378","https://openalex.org/W3096609285","https://openalex.org/W3208645658","https://openalex.org/W3210586215","https://openalex.org/W4312823573","https://openalex.org/W4313172897","https://openalex.org/W4313561323","https://openalex.org/W4315782998","https://openalex.org/W4372347372","https://openalex.org/W4382059335","https://openalex.org/W4382468064","https://openalex.org/W4386072246","https://openalex.org/W4390872550","https://openalex.org/W4391559306","https://openalex.org/W4391559729","https://openalex.org/W4393233221","https://openalex.org/W4395056538","https://openalex.org/W4401415788","https://openalex.org/W4402716047","https://openalex.org/W4402754006","https://openalex.org/W4402754239","https://openalex.org/W4402979889","https://openalex.org/W4403770406","https://openalex.org/W4410616160","https://openalex.org/W4414243662","https://openalex.org/W4416748912"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,12,25,94,160,168],"drone":[4],"technology":[5],"has":[6],"led":[7],"to":[8],"the":[9,23,92,102,121,126,150,165],"widespread":[10],"application":[11],"micro-object":[13,115],"detection":[14,43,137],"in":[15,31,51,64,117,157],"Unmanned":[16],"Aerial":[17],"Vehicle":[18],"(UAV)":[19],"systems.":[20],"However,":[21],"with":[22],"constraint":[24],"real-time":[26,132],"computation,":[27],"critical":[28],"challenges":[29],"remain":[30],"addressing":[32],"extreme":[33],"scale":[34],"variations,":[35],"low-resolution":[36],"signatures":[37],"and":[38,61,98,125],"dense":[39],"occlusions.":[40],"For":[41],"object":[42],"task,":[44],"although":[45],"YOLO-based":[46],"detectors":[47],"outperform":[48],"transformer":[49],"models":[50],"efficiency-accuracy":[52],"balance,":[53],"their":[54],"limited":[55],"capacity":[56],"for":[57,143],"global":[58],"context":[59],"modeling":[60,85,97],"feature":[62,128],"discriminability":[63],"complex":[65],"aerial":[66],"environments":[67],"hinders":[68],"optimal":[69],"performance.":[70],"To":[71],"overcome":[72],"these":[73],"limitations,":[74],"we":[75],"introduce":[76],"UAV-MaLO,":[77],"a":[78,140,154],"novel":[79],"framework":[80],"that":[81],"incorporates":[82],"state":[83],"space":[84],"principles":[86],"into":[87],"YOLO\u2019s":[88],"architecture.":[89],"By":[90],"introducing":[91],"abilities":[93],"long-range":[95],"dependency":[96],"adaptive":[99],"spatial-frequency":[100],"fusion,":[101],"proposed":[103],"approach":[104],"dynamically":[105],"optimizes":[106],"receptive":[107],"fields":[108],"while":[109],"suppressing":[110],"background":[111],"interference,":[112],"achieving":[113],"robust":[114],"localization":[116],"cluttered":[118],"scenarios.":[119],"Furthermore,":[120],"parallelized":[122],"attention":[123],"mechanism":[124],"hierarchical":[127],"refinement":[129],"further":[130],"ensure":[131],"processing":[133],"capabilities":[134],"without":[135],"compromising":[136],"precision,":[138],"establishing":[139],"new":[141],"paradigm":[142],"UAV":[144],"deployment.":[145],"Our":[146],"experimental":[147],"results":[148],"on":[149],"VisDrone-2019-DET":[151],"dataset":[152],"reveal":[153],"significant":[155],"improvement":[156],"various":[158],"variants":[159],"average":[161],"precision":[162],"(AP),":[163],"indicating":[164],"extraordinary":[166],"performance":[167],"our":[169],"UAV-MaLO.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}