{"id":"https://openalex.org/W4389667392","doi":"https://doi.org/10.1109/iros55552.2023.10342535","title":"See What the Robot Can't See: Learning Cooperative Perception for Visual Navigation","display_name":"See What the Robot Can't See: Learning Cooperative Perception for Visual Navigation","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667392","doi":"https://doi.org/10.1109/iros55552.2023.10342535"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5081322765","display_name":"Jan Blumenkamp","orcid":"https://orcid.org/0000-0002-1243-7707"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jan Blumenkamp","raw_affiliation_strings":["University of Cambridge,Department of Computer Science and Technology,United Kingdom","Department of Computer Science and Technology, University of Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Computer Science and Technology,United Kingdom","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078405776","display_name":"Qingbiao Li","orcid":"https://orcid.org/0000-0003-2761-1218"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qingbiao Li","raw_affiliation_strings":["University of Cambridge,Department of Computer Science and Technology,United Kingdom","Department of Computer Science and Technology, University of Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Computer Science and Technology,United Kingdom","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103184383","display_name":"Binyu Wang","orcid":"https://orcid.org/0009-0005-7358-5040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binyu Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462338","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0001-6753-0303"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["University of Cambridge,Department of Computer Science and Technology,United Kingdom","Department of Computer Science and Technology, University of Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Computer Science and Technology,United Kingdom","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066624177","display_name":"Amanda Prorok","orcid":"https://orcid.org/0000-0001-7313-5983"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amanda Prorok","raw_affiliation_strings":["University of Cambridge,Department of Computer Science and Technology,United Kingdom","Department of Computer Science and Technology, University of Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Computer Science and Technology,United Kingdom","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081322765"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54947444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7333","last_page":"7340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7557799816131592},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.6195487976074219},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6127064228057861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6041984558105469},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5351800322532654},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5221081972122192},{"id":"https://openalex.org/keywords/wireless-sensor-network","display_name":"Wireless sensor network","score":0.49791646003723145},{"id":"https://openalex.org/keywords/mobile-robot-navigation","display_name":"Mobile robot navigation","score":0.4907926023006439},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.43303436040878296},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3222716152667999},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.21352243423461914},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10343277454376221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557799816131592},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.6195487976074219},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6127064228057861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6041984558105469},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5351800322532654},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5221081972122192},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.49791646003723145},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.4907926023006439},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.43303436040878296},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3222716152667999},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.21352243423461914},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10343277454376221},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1534630452","https://openalex.org/W1923344279","https://openalex.org/W2014824949","https://openalex.org/W2019145051","https://openalex.org/W2039252979","https://openalex.org/W2115402120","https://openalex.org/W2129209579","https://openalex.org/W2146417222","https://openalex.org/W2746349752","https://openalex.org/W2884565639","https://openalex.org/W2898179042","https://openalex.org/W2903328861","https://openalex.org/W2910561533","https://openalex.org/W2962793481","https://openalex.org/W2962810718","https://openalex.org/W2963073614","https://openalex.org/W2963163009","https://openalex.org/W2963184124","https://openalex.org/W2963933833","https://openalex.org/W3130631955","https://openalex.org/W3162351594","https://openalex.org/W3180526717","https://openalex.org/W3209562766","https://openalex.org/W4297664295","https://openalex.org/W4297795161"],"related_works":["https://openalex.org/W2093507260","https://openalex.org/W2562628082","https://openalex.org/W2378318959","https://openalex.org/W2083994890","https://openalex.org/W2369541203","https://openalex.org/W2360994936","https://openalex.org/W3081536868","https://openalex.org/W2523265608","https://openalex.org/W2122735287","https://openalex.org/W2324656256"],"abstract_inverted_index":{"We":[0,81,241],"consider":[1],"the":[2,24,27,45,51,61,75,78,83,88,96,100,103,107,146,149,184,199,205,222,226,238,253],"problem":[3],"of":[4,85,183,193,207,218],"navigating":[5],"a":[6,10,111,117,168,176,190,243],"mobile":[7,62],"robot":[8,25,239],"towards":[9],"target":[11,76,108,223],"in":[12,158,210],"an":[13],"unknown":[14],"environment":[15],"that":[16,92,141],"is":[17,67,172],"endowed":[18],"with":[19,134],"visual":[20],"sensors,":[21],"where":[22],"neither":[23],"nor":[26,181],"sensors":[28,52,89,147],"have":[29],"access":[30],"to":[31,43,53,60,68,72,74,98,106,130,154,167,198,221],"global":[32,177],"positioning":[33,179],"information":[34,59,71],"and":[35,55,148,257],"only":[36],"use":[37,69],"first-person-":[38],"view":[39],"images.":[40],"In":[41,123],"order":[42],"overcome":[44,82],"need":[46],"for":[47],"positioning,":[48],"we":[49,126,151,188,215],"train":[50],"encode":[54],"communicate":[56],"relevant":[57],"viewpoint":[58],"robot,":[63,150],"whose":[64],"objective":[65],"it":[66],"this":[70],"navigate":[73],"along":[77,102],"shortest":[79,104],"path.":[80],"challenge":[84],"enabling":[86],"all":[87],"(even":[90],"those":[91],"cannot":[93],"directly":[94],"see":[95],"target)":[97],"predict":[99],"direction":[101],"path":[105],"by":[109,142,162],"implementing":[110],"neighborhood-based":[112],"feature":[113],"aggregation":[114],"module":[115],"using":[116,143],"Graph":[118],"Neural":[119],"Network":[120],"(GNN)":[121],"architecture.":[122],"our":[124,194,208],"experiments,":[125],"first":[127],"demonstrate":[128,204],"generalizability":[129],"previously":[131],"unseen":[132],"environments":[133],"various":[135,211],"sensor":[136,185,227],"layouts.":[137],"Our":[138],"results":[139],"show":[140],"communication":[144],"between":[145],"achieve":[152],"up":[153],"2.0":[155],"\u00d7":[156],"improvement":[157],"SPL":[159],"(Success":[160],"weighted":[161],"Path":[163],"Length)":[164],"when":[165],"compared":[166],"communication-free":[169],"baseline.":[170],"This":[171],"done":[173],"without":[174],"requiring":[175],"map,":[178],"data,":[180],"pre-calibration":[182],"network.":[186],"Second,":[187],"perform":[189],"zero-shot":[191],"transfer":[192],"model":[195],"from":[196],"simulation":[197],"real":[200],"world.":[201],"Laboratory":[202],"experiments":[203],"feasibility":[206],"approach":[209],"cluttered":[212],"environments.":[213],"Finally,":[214],"showcase":[216],"examples":[217],"successful":[219],"navigation":[220],"while":[224],"both":[225],"network":[228],"layout":[229],"as":[230,232,237],"well":[231],"obstacles":[233],"are":[234],"dynamically":[235],"reconfigured":[236],"navigates.":[240],"provide":[242],"video":[244],"demo":[245],"<sup":[246,249,260,263],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[247,250,261,264],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[248,251],"https://www.youtube.com/watch?v=kcrnr6RUgucw,":[252],"dataset,":[254],"trained":[255],"models,":[256],"source":[258],"code":[259],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[262,265],"https://github.com/proroklab/sensor-guided-visual-nav.":[266]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
