{"id":"https://openalex.org/W2962887844","doi":"https://doi.org/10.1109/icra.2017.7989381","title":"Target-driven visual navigation in indoor scenes using deep reinforcement learning","display_name":"Target-driven visual navigation in indoor scenes using deep reinforcement learning","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2962887844","doi":"https://doi.org/10.1109/icra.2017.7989381","mag":"2962887844"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","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/A5030826237","display_name":"Yuke Zhu","orcid":"https://orcid.org/0000-0002-9198-2227"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuke Zhu","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070375939","display_name":"Roozbeh Mottaghi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140341","display_name":"Allen Institute","ror":"https://ror.org/03cpe7c52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140341"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roozbeh Mottaghi","raw_affiliation_strings":["Allen Institute for AI"],"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210140341"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035312572","display_name":"Eric Kolve","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140341","display_name":"Allen Institute","ror":"https://ror.org/03cpe7c52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140341"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Kolve","raw_affiliation_strings":["Allen Institute for AI"],"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210140341"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110492675","display_name":"Joseph J. Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I2800817003","display_name":"Southern California University for Professional Studies","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph J. Lim","raw_affiliation_strings":["Stanford University","University of Southern California"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101761266","display_name":"Abhinav Gupta","orcid":"https://orcid.org/0000-0002-3646-2421"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I4210140341","display_name":"Allen Institute","ror":"https://ror.org/03cpe7c52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140341"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Gupta","raw_affiliation_strings":["Allen Institute for AI","Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210140341"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Fei-Fei","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101576595","display_name":"Ali Farhadi","orcid":"https://orcid.org/0000-0001-7249-2380"},"institutions":[{"id":"https://openalex.org/I4210140341","display_name":"Allen Institute","ror":"https://ror.org/03cpe7c52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140341"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Farhadi","raw_affiliation_strings":["Allen Institute for AI","University of Washington"],"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210140341"]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5030826237"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":143.7485,"has_fulltext":false,"cited_by_count":1489,"citation_normalized_percentile":{"value":0.99972883,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3357","last_page":"3364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9976999759674072,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9976000189781189,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8876898288726807},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8014259338378906},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7416759729385376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6491929888725281},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6078925132751465},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5821549296379089},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5302103757858276},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.5234596133232117},{"id":"https://openalex.org/keywords/physics-engine","display_name":"Physics engine","score":0.4953068792819977},{"id":"https://openalex.org/keywords/feature-matching","display_name":"Feature matching","score":0.49455544352531433},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49280455708503723},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4751986265182495},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45964953303337097},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4494169354438782},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4142875671386719},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.253637433052063},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09817653894424438}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8876898288726807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014259338378906},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7416759729385376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6491929888725281},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6078925132751465},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5821549296379089},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5302103757858276},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5234596133232117},{"id":"https://openalex.org/C190390380","wikidata":"https://www.wikidata.org/wiki/Q62505","display_name":"Physics engine","level":2,"score":0.4953068792819977},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.49455544352531433},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49280455708503723},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4751986265182495},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45964953303337097},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4494169354438782},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4142875671386719},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.253637433052063},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09817653894424438},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2017.7989381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","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":71,"referenced_works":["https://openalex.org/W8177059","https://openalex.org/W15601695","https://openalex.org/W567721252","https://openalex.org/W1973350167","https://openalex.org/W1977655452","https://openalex.org/W1997645979","https://openalex.org/W2002639639","https://openalex.org/W2013489252","https://openalex.org/W2017995647","https://openalex.org/W2029143333","https://openalex.org/W2069830673","https://openalex.org/W2076367573","https://openalex.org/W2095784398","https://openalex.org/W2097482220","https://openalex.org/W2107684513","https://openalex.org/W2108734173","https://openalex.org/W2111654460","https://openalex.org/W2113243634","https://openalex.org/W2125409550","https://openalex.org/W2125612430","https://openalex.org/W2132400125","https://openalex.org/W2137051796","https://openalex.org/W2139053308","https://openalex.org/W2143824592","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155007355","https://openalex.org/W2157364932","https://openalex.org/W2171028727","https://openalex.org/W2171453194","https://openalex.org/W2181623680","https://openalex.org/W2187089797","https://openalex.org/W2190606234","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2271840356","https://openalex.org/W2283109172","https://openalex.org/W2293598046","https://openalex.org/W2301880263","https://openalex.org/W2397830550","https://openalex.org/W2414248975","https://openalex.org/W2415355599","https://openalex.org/W2431874326","https://openalex.org/W2480004914","https://openalex.org/W2562018939","https://openalex.org/W2565961086","https://openalex.org/W2584377191","https://openalex.org/W2950527027","https://openalex.org/W2962858248","https://openalex.org/W2963305465","https://openalex.org/W2963871073","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W2964269434","https://openalex.org/W3103780890","https://openalex.org/W4297810741","https://openalex.org/W4298174377","https://openalex.org/W6600624752","https://openalex.org/W6616173779","https://openalex.org/W6676172287","https://openalex.org/W6682849425","https://openalex.org/W6685726866","https://openalex.org/W6686008357","https://openalex.org/W6687086880","https://openalex.org/W6692339859","https://openalex.org/W6692846177","https://openalex.org/W6694517276","https://openalex.org/W6697152211","https://openalex.org/W6712616374","https://openalex.org/W6721634521","https://openalex.org/W6732837357"],"related_works":["https://openalex.org/W2264067234","https://openalex.org/W3124243301","https://openalex.org/W1571502335","https://openalex.org/W1589409554","https://openalex.org/W2759038785","https://openalex.org/W2172232600","https://openalex.org/W3123876860","https://openalex.org/W3124172198","https://openalex.org/W2142633247","https://openalex.org/W2148394657"],"abstract_inverted_index":{"Two":[0],"less":[1],"addressed":[2],"issues":[3,53],"of":[4,11,30,77,130,167,193],"deep":[5,146],"reinforcement":[6,147],"learning":[7,148],"are":[8],"(1)":[9,140],"lack":[10],"generalization":[12],"capability":[13],"to":[14,34,40,43,58,116,158],"new":[15],"goals,":[16],"and":[17,32,54,108,119,154,180],"(2)":[18,150],"data":[19],"inefficiency,":[20],"i.e.,":[21],"the":[22,64,78,83,92,97,144,170,194],"model":[23,57,71,171],"requires":[24],"several":[25],"(and":[26],"often":[27],"costly)":[28],"episodes":[29],"trial":[31],"error":[33],"converge,":[35],"which":[36,86,100],"makes":[37],"it":[38],"impractical":[39],"be":[41],"applied":[42],"real-world":[44],"scenarios.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,67,95,124],"address":[50,63,91],"these":[51],"two":[52],"apply":[55],"our":[56,137],"target-driven":[59],"visual":[60],"navigation.":[61],"To":[62,90],"first":[65],"issue,":[66,94],"propose":[68,96],"an":[69,102],"actor-critic":[70],"whose":[72],"policy":[73],"is":[74,172,177],"a":[75,109,127,159,164],"function":[76],"goal":[79],"as":[80,82],"well":[81],"current":[84],"state,":[85],"allows":[87],"better":[88],"generalization.":[89],"second":[93],"AI2-THOR":[98],"framework,":[99],"provides":[101],"environment":[103],"with":[104,121,163],"high-quality":[105],"3D":[106,191],"scenes":[107],"physics":[110],"engine.":[111],"Our":[112],"framework":[113],"enables":[114],"agents":[115],"take":[117],"actions":[118],"interact":[120],"objects.":[122],"Hence,":[123],"can":[125],"collect":[126],"huge":[128],"number":[129],"training":[131],"samples":[132],"efficiently.":[133],"We":[134],"show":[135],"that":[136],"proposed":[138],"method":[139],"converges":[141],"faster":[142],"than":[143],"state-of-the-art":[145],"methods,":[149],"generalizes":[151,157],"across":[152],"targets":[153],"scenes,":[155],"(3)":[156],"real":[160],"robot":[161],"scenario":[162],"small":[165],"amount":[166],"fine-tuning":[168],"(although":[169],"trained":[173],"in":[174],"simulation),":[175],"(4)":[176],"end-to-end":[178],"trainable":[179],"does":[181],"not":[182],"need":[183],"feature":[184,186],"engineering,":[185],"matching":[187],"between":[188],"frames":[189],"or":[190],"reconstruction":[192],"environment.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":110},{"year":2024,"cited_by_count":126},{"year":2023,"cited_by_count":167},{"year":2022,"cited_by_count":162},{"year":2021,"cited_by_count":225},{"year":2020,"cited_by_count":254},{"year":2019,"cited_by_count":244},{"year":2018,"cited_by_count":150},{"year":2017,"cited_by_count":39}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}