{"id":"https://openalex.org/W6940078332","doi":"https://doi.org/10.6094/unifr/17427","title":"Discovering and leveraging deep multimodal structure for reliable robot perception and localization","display_name":"Discovering and leveraging deep multimodal structure for reliable robot perception and localization","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W6940078332","doi":"https://doi.org/10.6094/unifr/17427"},"language":"en","primary_location":{"id":"pmh:oai:freidok.uni-freiburg.de:17427","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401057","display_name":"FreiDok plus (Universit\u00e4tsbibliothek Freiburg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I161046081","host_organization_name":"University of Freiburg","host_organization_lineage":["https://openalex.org/I161046081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral_thesis"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.6094/unifr/17427","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Valada, Abhinav","orcid":"https://orcid.org/0000-0003-4710-3114"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Valada, Abhinav","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10451","display_name":"Mycorrhizal Fungi and Plant Interactions","score":0.5827999711036682,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10451","display_name":"Mycorrhizal Fungi and Plant Interactions","score":0.5827999711036682,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.09099999815225601,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10825","display_name":"Plant Pathogens and Fungal Diseases","score":0.06310000270605087,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6535000205039978},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.632099986076355},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5769000053405762},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5705000162124634},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5335999727249146},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.48170000314712524},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.3961000144481659},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38589999079704285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498999834060669},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6535000205039978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6355999708175659},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.632099986076355},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5769000053405762},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5734999775886536},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.48170000314712524},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C111151474","wikidata":"https://www.wikidata.org/wiki/Q1653368","display_name":"iCub","level":4,"score":0.31470000743865967},{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C2780565519","wikidata":"https://www.wikidata.org/wiki/Q1208937","display_name":"Multitude","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C28063669","wikidata":"https://www.wikidata.org/wiki/Q7167042","display_name":"Perceptual system","level":3,"score":0.2888000011444092},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27900001406669617}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:freidok.uni-freiburg.de:17427","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401057","display_name":"FreiDok plus (Universit\u00e4tsbibliothek Freiburg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I161046081","host_organization_name":"University of Freiburg","host_organization_lineage":["https://openalex.org/I161046081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral_thesis"},{"id":"pmh:oai:freidok.uni-freiburg.de:17427","is_oa":false,"landing_page_url":"https://freidok.uni-freiburg.de/data/17427","pdf_url":null,"source":{"id":"https://openalex.org/S4306401057","display_name":"FreiDok plus (Universit\u00e4tsbibliothek Freiburg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I161046081","host_organization_name":"University of Freiburg","host_organization_lineage":["https://openalex.org/I161046081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral_thesis"},{"id":"doi:10.6094/unifr/17427","is_oa":true,"landing_page_url":"https://doi.org/10.6094/unifr/17427","pdf_url":null,"source":{"id":"https://openalex.org/S4306401057","display_name":"FreiDok plus (Universit\u00e4tsbibliothek Freiburg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I161046081","host_organization_name":"University of Freiburg","host_organization_lineage":["https://openalex.org/I161046081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.6094/unifr/17427","is_oa":true,"landing_page_url":"https://doi.org/10.6094/unifr/17427","pdf_url":null,"source":{"id":"https://openalex.org/S4306401057","display_name":"FreiDok plus (Universit\u00e4tsbibliothek Freiburg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I161046081","host_organization_name":"University of Freiburg","host_organization_lineage":["https://openalex.org/I161046081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.4418719708919525}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Advances":[0],"in":[1,11,41,198,244,301,384,396,461,528,591],"robotics":[2],"and":[3,21,60,87,95,116,138,194,225,242,266,285,316,352,363,387,404,429,486,516,534,573],"machine":[4],"learning":[5,412,426,471,478,502],"are":[6,34,46,125,276],"creating":[7],"unprecedented":[8],"seismic":[9],"shifts":[10],"several":[12],"domains":[13],"including":[14],"the":[15,28,49,56,101,113,136,157,161,199,286,332,390,394,409,445,448,456,459,483,488,491,520,525,566],"service":[16],"industry,":[17],"mining,":[18],"domestic":[19],"chores":[20],"transportation.":[22],"As":[23],"we":[24,45,148,204,253,335,407,467,548],"move":[25],"deeper":[26],"into":[27],"age":[29],"of":[30,52,58,80,93,104,112,140,160,201,223,304,393,427,447,458,490,503,552,554,561,571],"intelligent":[31],"robots":[32,234,280,375,442,563,583],"that":[33,76,99,124,151,209,232,261,295,327,340,419,539,541,564,578],"no":[35],"longer":[36],"confined":[37],"to":[38,73,97,130,155,218,235,293,313,331,354,380,401,424,434,443,454,473,479,568],"operational":[39],"scenarios":[40,312],"simplistic":[42],"controlled":[43],"environments,":[44,85],"faced":[47],"with":[48,55,135,281,377],"critical":[50],"challenge":[51],"equipping":[53],"them":[54,72],"capability":[57],"perceiving":[59],"understanding":[61,260],"our":[62,141,378,542,555,600],"continuously":[63],"evolving":[64],"complex":[65,592],"world.":[66],"Amongst":[67],"others,":[68],"this":[69,146,529],"entails":[70],"enabling":[71],"recognize":[74],"objects":[75,294],"have":[77,581],"a":[78,153,215,220,322,366,462,469,559,569,584],"multitude":[79],"variations,":[81],"model":[82],"highly":[83],"dynamic":[84],"synthesize":[86],"make":[88],"decisions":[89],"from":[90,163,170,190,308,344,519],"disparate":[91],"streams":[92],"modalities":[94,171,346],"adapt":[96],"circumstances":[98],"change":[100],"visual":[102,174,202,240,349],"appearance":[103],"places":[105],"such":[106,347,359],"as":[107,176,178,214,321,348,360,509,511],"different":[108,305,562],"weather":[109,403],"conditions,":[110],"times":[111],"day,":[114],"illumination":[115],"structural":[117,517],"changes.":[118],"Such":[119],"factors":[120],"render":[121],"current":[122],"methods":[123,557],"hand-tuned":[126],"for":[127,258,270,365,414],"specialized":[128],"situations":[129],"break":[131],"down":[132],"when":[133],"presented":[134],"complexity":[137],"richness":[139],"vast":[142],"perceptual":[143,398,574],"space.":[144],"In":[145],"thesis,":[147],"introduce":[149],"techniques":[150,269,373,580],"enable":[152,233,374,441],"robot":[154,506],"learn":[156],"semantic":[158,272,289,369,416,432],"structure":[159,182],"environment":[162,449],"prior":[164],"experiences":[165],"by":[166,179,499,512],"leveraging":[167],"robust":[168],"representations":[169],"beyond":[172,496],"just":[173],"images":[175,303],"well":[177,510],"discovering":[180],"shared":[181],"between":[183],"multiple":[184,299],"diverse":[185],"tasks.":[186],"Firstly,":[187],"taking":[188],"inspiration":[189],"how":[191],"humans":[192],"sense":[193],"navigate":[195],"on":[196,279,531],"terrains":[197,238],"absence":[200],"perception,":[203],"propose":[205,336,408],"novel":[206,268],"network":[207,413],"architectures":[208,257,339],"exploit":[210,356,475],"vehicle-terrain":[211],"interaction":[212],"sounds":[213],"proprioceptive":[216],"modality":[217],"classify":[219,237],"wide":[221],"range":[222],"indoor":[224,314],"outdoor":[226],"terrains.":[227],"These":[228,372],"include":[229],"recurrent":[230],"models":[231,275,326,379,440,543],"accurately":[236],"without":[239],"information":[241,265,343],"even":[243],"adverse":[245],"real-world":[246,550,593],"acoustic":[247],"conditions":[248,399],"using":[249,558],"inexpensive":[250],"microphones.":[251],"Secondly,":[252],"present":[254,468,535,549],"compact":[255],"fully-convolutional":[256],"scene":[259,370,395,460,484],"aggregate":[262],"multiscale":[263],"contextual":[264],"incorporate":[267],"high-resolution":[271],"segmentation.":[273],"Our":[274,438,493],"efficiently":[277],"deployable":[278],"limited":[282],"computational":[283],"resources":[284],"resulting":[287],"pixel-level":[288],"classification":[290,386],"effectively":[291,513],"generalizes":[292],"often":[296],"appear":[297],"at":[298],"scales":[300],"natural":[302],"environments":[306,572,594],"ranging":[307],"urban":[309],"autonomous":[310],"driving":[311],"scenes":[315],"unstructured":[317],"forested":[318],"environments.":[319],"Thirdly,":[320],"step":[323,585],"towards":[324,587],"neural":[325],"reconfigure":[328],"themselves":[329],"according":[330],"encountered":[333],"situation,":[334],"self-supervised":[337],"multimodal":[338],"dynamically":[341],"fuse":[342],"complementary":[345],"images,":[350],"depth":[351],"infrared":[353],"correspondingly":[355,430],"object":[357],"properties":[358],"appearance,":[361],"geometry":[362],"reflectance":[364],"more":[367],"holistic":[368],"understanding.":[371],"equipped":[376],"resolve":[381],"local":[382],"ambiguities":[383],"their":[385],"robustly":[388],"identify":[389],"various":[391],"elements":[392],"challenging":[397],"attributed":[400],"changing":[402],"seasons.":[405],"Fourthly,":[406],"first":[410],"end-to-end":[411],"joint":[415],"motion":[417,422,436],"segmentation":[418],"simultaneously":[420],"exploits":[421,431],"cues":[423,433],"improve":[425,435],"semantics":[428,457,485],"estimation.":[437],"proposed":[439,556],"understand":[444],"dynamics":[446],"while":[450,477],"concurrently":[451],"being":[452,588],"able":[453],"discern":[455],"temporally":[463],"coherent":[464],"manner.":[465],"Finally,":[466],"multitask":[470],"strategy":[472],"automatically":[474],"synergies":[476],"visually":[480],"localize,":[481],"predict":[482],"estimate":[487],"ego-motion":[489],"robot.":[492],"contributions":[494],"goes":[495],"existing":[497],"paradigms":[498],"facilitating":[500],"cooperative":[501],"these":[504,579],"key":[505],"autonomy":[507],"enablers":[508],"encoding":[514],"geometric":[515],"constraints":[518],"environment.":[521],"We":[522,576],"comprehensively":[523],"evaluate":[524],"approaches":[526],"introduced":[527],"thesis":[530],"standard":[532],"benchmarks":[533],"extensive":[536],"empirical":[537],"evidence":[538],"demonstrates":[540],"achieve":[544],"state-of-the-art":[545],"performance.":[546],"Additionally,":[547],"evaluations":[551],"each":[553],"number":[560],"demonstrate":[565],"generalizability":[567],"variety":[570],"conditions.":[575],"believe":[577],"brought":[582],"closer":[586],"reliably":[589],"deployed":[590],"where":[595],"they":[596],"will":[597],"fundamentally":[598],"transform":[599],"society":[601],"forever.":[602]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}