{"id":"https://openalex.org/W4388709698","doi":"https://doi.org/10.1109/lra.2023.3333238","title":"VME-Transformer: Enhancing Visual Memory Encoding for Navigation in Interactive Environments","display_name":"VME-Transformer: Enhancing Visual Memory Encoding for Navigation in Interactive Environments","publication_year":2023,"publication_date":"2023-11-15","ids":{"openalex":"https://openalex.org/W4388709698","doi":"https://doi.org/10.1109/lra.2023.3333238"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3333238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3333238","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/A5055933562","display_name":"Jiwei Shen","orcid":"https://orcid.org/0000-0002-1987-4926"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiwei Shen","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication &amp; Electronic Engineering, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication &amp; Electronic Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093270085","display_name":"Pengjie Lou","orcid":"https://orcid.org/0009-0007-3077-8330"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengjie Lou","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication &amp; Electronic Engineering, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication &amp; Electronic Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390896","display_name":"Liang Yuan","orcid":"https://orcid.org/0000-0002-7068-8766"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Yuan","raw_affiliation_strings":["Beijing Advanced Innovation Center for Soft Matter Science and Engineering, Beijing University of Chemical Technology, Chaoyang, China"],"affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Soft Matter Science and Engineering, Beijing University of Chemical Technology, Chaoyang, China","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075220317","display_name":"Shujing Lyu","orcid":"https://orcid.org/0000-0003-2623-1379"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujing Lyu","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication &amp; Electronic Engineering, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication &amp; Electronic Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031868292","display_name":"Yue Lu","orcid":"https://orcid.org/0000-0003-4062-6553"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Lu","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication &amp; Electronic Engineering, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication &amp; Electronic Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055933562"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":8.3985,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.97327623,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"9","issue":"1","first_page":"643","last_page":"650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9987000226974487,"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":0.6973589658737183},{"id":"https://openalex.org/keywords/vmebus","display_name":"VMEbus","score":0.6098868250846863},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5764625668525696},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5668176412582397},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5533662438392639},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5397471189498901},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5385215878486633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4801459014415741},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44112512469291687},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3466678857803345},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1594354510307312},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.1336706578731537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973589658737183},{"id":"https://openalex.org/C117180269","wikidata":"https://www.wikidata.org/wiki/Q1377238","display_name":"VMEbus","level":3,"score":0.6098868250846863},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5764625668525696},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5668176412582397},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5533662438392639},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5397471189498901},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5385215878486633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4801459014415741},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44112512469291687},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3466678857803345},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1594354510307312},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1336706578731537},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3333238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3333238","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":[{"id":"https://openalex.org/G2973223028","display_name":null,"funder_award_id":"22DZ2229004","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2962789679","https://openalex.org/W2963846044","https://openalex.org/W2990881323","https://openalex.org/W2998903229","https://openalex.org/W3009928773","https://openalex.org/W3043971245","https://openalex.org/W3130407530","https://openalex.org/W3165538103","https://openalex.org/W3184282957","https://openalex.org/W3201759799","https://openalex.org/W4230024974","https://openalex.org/W4281696864","https://openalex.org/W4285102264","https://openalex.org/W4312707839","https://openalex.org/W4312770775","https://openalex.org/W4313180266","https://openalex.org/W4319990479","https://openalex.org/W4372266976","https://openalex.org/W6729556111","https://openalex.org/W6731334075","https://openalex.org/W6735003056","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6768810269","https://openalex.org/W6774815639","https://openalex.org/W6780443396","https://openalex.org/W6780978170","https://openalex.org/W6783944145","https://openalex.org/W6843158373"],"related_works":["https://openalex.org/W3005183616","https://openalex.org/W365128091","https://openalex.org/W2055571762","https://openalex.org/W4244067293","https://openalex.org/W1594266030","https://openalex.org/W2352105002","https://openalex.org/W2013717263","https://openalex.org/W1977151579","https://openalex.org/W2000146075","https://openalex.org/W847575121"],"abstract_inverted_index":{"The":[0],"efficiency":[1],"of":[2,92,120],"a":[3,26,37,73,77,85],"robotic":[4],"system":[5],"is":[6],"primarily":[7],"determined":[8],"by":[9,130],"its":[10,40,136,163],"ability":[11],"to":[12,28,35,51,63,70,115,159],"navigate":[13,29],"complex":[14],"and":[15,32,61,76,96],"interactive":[16],"environments.":[17,142],"In":[18,143],"real-world":[19],"scenarios,":[20],"cluttered":[21],"surroundings":[22],"are":[23],"common,":[24],"requiring":[25],"robot":[27],"diverse":[30],"spaces":[31],"displace":[33],"objects":[34],"pave":[36],"path":[38],"towards":[39],"objective.":[41],"Consequently,":[42],"\u201cVisual":[43],"Interactive":[44,146],"Navigation\u201d":[45],"presents":[46],"several":[47],"challenges,":[48,82],"including":[49],"how":[50,62],"retain":[52],"historical":[53],"exploration":[54,98],"information":[55,99],"from":[56],"partially":[57],"observable":[58],"visual":[59],"signals,":[60],"utilize":[64],"sparse":[65],"rewards":[66],"in":[67,139],"reinforcement":[68],"learning":[69,118],"simultaneously":[71],"learn":[72],"latent":[74],"representation":[75],"control":[78],"policy.":[79],"Addressing":[80],"these":[81],"we":[83,103],"introduce":[84],"Transformer-based":[86],"Visual":[87,145],"Memory":[88],"Encoder":[89],"(VME-Transformer),":[90],"capable":[91],"embedding":[93],"both":[94],"recent":[95],"long-term":[97],"into":[100],"memory.":[101],"Additionally,":[102],"explicitly":[104],"estimate":[105],"the":[106,112,117,121,127,144,150,153],"robot's":[107],"next":[108],"pose,":[109],"conditioned":[110],"on":[111],"impending":[113],"action,":[114],"bootstrap":[116],"process":[119],"high-capacity":[122],"VME-Transformer.":[123],"We":[124],"further":[125],"regularize":[126],"value":[128],"function":[129],"introducing":[131],"input":[132],"perturbations,":[133],"thereby":[134],"enhancing":[135],"generalization":[137],"capabilities":[138],"previously":[140],"unseen":[141],"Navigation":[147],"tasks":[148],"within":[149],"iGibson":[151],"environment,":[152],"VME-Transformer":[154],"demonstrates":[155],"superior":[156],"performance":[157],"compared":[158],"state-of-the-art":[160],"methods,":[161],"underlining":[162],"effectiveness.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
