{"id":"https://openalex.org/W4319990479","doi":"https://doi.org/10.1109/lra.2023.3241803","title":"Transformer Memory for Interactive Visual Navigation in Cluttered Environments","display_name":"Transformer Memory for Interactive Visual Navigation in Cluttered Environments","publication_year":2023,"publication_date":"2023-02-02","ids":{"openalex":"https://openalex.org/W4319990479","doi":"https://doi.org/10.1109/lra.2023.3241803"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3241803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3241803","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/A5063060971","display_name":"Weiyuan Li","orcid":"https://orcid.org/0000-0001-5615-4795"},"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":"Weiyuan Li","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5615-4795","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronic Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046918484","display_name":"Ruoxin Hong","orcid":null},"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":"Ruoxin Hong","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronic Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","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":false,"raw_author_name":"Jiwei Shen","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1987-4926","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and 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"],"raw_orcid":null,"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":"last","author":{"id":"https://openalex.org/A5101615349","display_name":"Yue Lu","orcid":"https://orcid.org/0000-0002-8784-4657"},"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 and Electronic Engineering, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8784-4657","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and 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":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4701,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.9093669,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"8","issue":"3","first_page":"1731","last_page":"1738"},"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":0.9908000230789185,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9886999726295471,"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":0.8007376194000244},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6764366626739502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.577975332736969},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5735002160072327},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5480225682258606},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.519656777381897},{"id":"https://openalex.org/keywords/waypoint","display_name":"Waypoint","score":0.5061344504356384},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4672425091266632},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.4106346368789673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3656166195869446},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3481920063495636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34065675735473633},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.24654576182365417},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.23678329586982727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007376194000244},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6764366626739502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.577975332736969},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5735002160072327},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5480225682258606},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.519656777381897},{"id":"https://openalex.org/C2781271823","wikidata":"https://www.wikidata.org/wiki/Q138081","display_name":"Waypoint","level":2,"score":0.5061344504356384},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4672425091266632},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.4106346368789673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3656166195869446},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3481920063495636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34065675735473633},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.24654576182365417},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.23678329586982727},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3241803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3241803","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":[{"display_name":"Quality Education","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4"}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2157331557","https://openalex.org/W2593841437","https://openalex.org/W2884565639","https://openalex.org/W2904246096","https://openalex.org/W2962789679","https://openalex.org/W2998903229","https://openalex.org/W3009928773","https://openalex.org/W3130407530","https://openalex.org/W3175482402","https://openalex.org/W3176232375","https://openalex.org/W3184282957","https://openalex.org/W4200523064","https://openalex.org/W4223656432","https://openalex.org/W4230024974","https://openalex.org/W4281696864","https://openalex.org/W4312770775","https://openalex.org/W4385245566","https://openalex.org/W6731334075","https://openalex.org/W6751885507","https://openalex.org/W6753516098","https://openalex.org/W6757592117","https://openalex.org/W6768810269","https://openalex.org/W6773029903","https://openalex.org/W6780443396","https://openalex.org/W6780978170","https://openalex.org/W6784119104","https://openalex.org/W6787713516","https://openalex.org/W6790124654"],"related_works":["https://openalex.org/W2688471429","https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Substantial":[0],"progress":[1],"has":[2,97],"been":[3],"achieved":[4],"in":[5,29,57,107,131,166,189],"embodied":[6],"visual":[7,51,84],"navigation":[8,85],"based":[9],"on":[10],"reinforcement":[11],"learning":[12,157],"(RL).":[13],"These":[14],"studies":[15],"presume":[16],"that":[17],"the":[18,24,40,45,49,58,62,73,78,94,104,118,121,128,132,146,150,155,160,167,178,183,190,195],"environment":[19,46,169],"is":[20,135],"stationary":[21],"where":[22],"all":[23],"obstacles":[25,74],"are":[26],"static.":[27],"However,":[28,125],"real":[30],"cluttered":[31],"scenes,":[32],"interactable":[33],"objects":[34],"(e.g.":[35],"shoes":[36],"and":[37,158,170,182,194],"boxes)":[38],"blocking":[39],"way":[41],"of":[42,60],"robots":[43],"makes":[44],"non-stationary.":[47],"Accordingly,":[48],"ego-centric":[50],"agent":[52],"will":[53],"easily":[54],"get":[55],"stuck":[56],"dilemma":[59],"finding":[61],"next":[63,147],"waypoint":[64,148],"as":[65,86,149],"it":[66],"struggles":[67],"to":[68,71,102,116,144],"decide":[69],"whether":[70],"push":[72],"ahead.":[75],"To":[76],"handle":[77],"predicament,":[79],"we":[80],"formulate":[81],"this":[82],"interactive":[83,123,179],"Partial":[87],"Observed":[88],"Markov":[89],"Decision":[90],"Process":[91],"(POMDP).":[92],"As":[93],"transformer":[95,129],"encoder":[96],"demonstrated":[98],"its":[99],"superior":[100],"ability":[101],"capture":[103],"spatial-temporal":[105],"dependencies":[106],"natural":[108],"language":[109],"processing.":[110],"We":[111,138,162],"propose":[112,140],"a":[113,141,174],"transformer-based":[114],"memory":[115],"empower":[117],"agents":[119],"utilizing":[120],"historical":[122],"information.":[124],"directly":[126],"leveraging":[127],"architecture":[130],"RL":[133,186],"settings":[134],"highly":[136],"unstable.":[137],"further":[139],"surrogate":[142],"objective":[143],"predict":[145],"auxiliary":[151],"task,":[152],"which":[153],"facilitates":[154],"representation":[156],"bootstraps":[159],"RL.":[161],"demonstrate":[163],"our":[164],"method":[165],"iGibson":[168],"experimental":[171],"results":[172],"show":[173],"significant":[175],"improvement":[176],"over":[177],"Gibson":[180],"benchmark":[181],"related":[184],"recurrent":[185],"policy":[187],"both":[188],"validation":[191],"seen":[192],"scenes":[193],"test":[196],"unseen":[197],"scenes.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}