{"id":"https://openalex.org/W2966477753","doi":"https://doi.org/10.1109/tnnls.2019.2927869","title":"Deep Reinforcement Learning-Based Automatic Exploration for Navigation in Unknown Environment","display_name":"Deep Reinforcement Learning-Based Automatic Exploration for Navigation in Unknown Environment","publication_year":2019,"publication_date":"2019-08-06","ids":{"openalex":"https://openalex.org/W2966477753","doi":"https://doi.org/10.1109/tnnls.2019.2927869","mag":"2966477753","pmid":"https://pubmed.ncbi.nlm.nih.gov/31398138"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2019.2927869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2019.2927869","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100327745","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0003-2559-9585"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoran Li","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049454999","display_name":"Qichao Zhang","orcid":"https://orcid.org/0000-0001-9747-391X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichao Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100327745"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210100255","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":9.2139,"has_fulltext":false,"cited_by_count":245,"citation_normalized_percentile":{"value":0.98332439,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"31","issue":"6","first_page":"2064","last_page":"2076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8498177528381348},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7336848378181458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6938636302947998},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.589716374874115},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5453861951828003},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5221562385559082},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.5220627188682556},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.520035982131958},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5088539123535156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.507930338382721},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4767616391181946},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4105566442012787},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.24558928608894348}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8498177528381348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336848378181458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6938636302947998},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.589716374874115},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5453861951828003},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5221562385559082},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.5220627188682556},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.520035982131958},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5088539123535156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.507930338382721},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4767616391181946},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4105566442012787},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.24558928608894348},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.0},{"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2019.2927869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2019.2927869","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:31398138","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31398138","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G4342254174","display_name":null,"funder_award_id":"61803371","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5745859652","display_name":null,"funder_award_id":"61573353","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7163010157","display_name":null,"funder_award_id":"61533017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8332583322","display_name":null,"funder_award_id":"61603268","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2076518796","https://openalex.org/W2080823437","https://openalex.org/W2089437550","https://openalex.org/W2096052462","https://openalex.org/W2107667896","https://openalex.org/W2110178871","https://openalex.org/W2119112357","https://openalex.org/W2121863487","https://openalex.org/W2123651102","https://openalex.org/W2133464237","https://openalex.org/W2138761185","https://openalex.org/W2140881794","https://openalex.org/W2145339207","https://openalex.org/W2153054365","https://openalex.org/W2163605009","https://openalex.org/W2172103629","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2183137222","https://openalex.org/W2257979135","https://openalex.org/W2291737362","https://openalex.org/W2405379562","https://openalex.org/W2480536132","https://openalex.org/W2524771588","https://openalex.org/W2538000344","https://openalex.org/W2563670399","https://openalex.org/W2567015638","https://openalex.org/W2569527682","https://openalex.org/W2594903727","https://openalex.org/W2606548817","https://openalex.org/W2742332513","https://openalex.org/W2751973545","https://openalex.org/W2755236197","https://openalex.org/W2771342126","https://openalex.org/W2772589676","https://openalex.org/W2774451424","https://openalex.org/W2796447411","https://openalex.org/W2898691144","https://openalex.org/W2919115771","https://openalex.org/W2939569248","https://openalex.org/W2951799221","https://openalex.org/W2963523627","https://openalex.org/W2963809389","https://openalex.org/W2963864421","https://openalex.org/W2963948945","https://openalex.org/W4214717370","https://openalex.org/W4297795161","https://openalex.org/W6676388466","https://openalex.org/W6684191040","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6731334075","https://openalex.org/W6735003056","https://openalex.org/W6750185400"],"related_works":["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/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,8,13,18,78,82,90,93,119,142,145,149,153,163],"automatic":[4],"exploration":[5,74,79,116],"problem":[6,29],"under":[7],"unknown":[9,136],"environment,":[10],"which":[11,88],"is":[12,34],"key":[14],"point":[15],"of":[16,92],"applying":[17],"robotic":[19,94],"system":[20],"to":[21,27,36,65,114,162],"some":[22],"social":[23],"tasks.":[24],"The":[25,122],"solution":[26],"this":[28,68,98,126],"via":[30,76],"stacking":[31],"decision":[32,106],"rules":[33],"impossible":[35],"cover":[37],"various":[38],"environments":[39],"and":[40,60,85,133,148],"sensor":[41],"properties.":[42],"Learning-based":[43],"control":[44],"methods":[45,53],"are":[46,54],"adaptive":[47],"for":[48,135],"these":[49,52],"scenarios.":[50],"However,":[51],"damaged":[55],"by":[56],"low":[57],"learning":[58,115,131],"efficiency":[59,132],"awkward":[61],"transferability":[62],"from":[63,118,160],"simulation":[64,161],"reality.":[66],"In":[67,138],"paper,":[69],"we":[70,100,140],"construct":[71],"a":[72,102,110],"general":[73],"framework":[75],"decomposing":[77],"process":[80],"into":[81],"decision,":[83],"planning,":[84],"mapping":[86],"modules,":[87],"increases":[89],"modularity":[91],"system.":[95],"Based":[96],"on":[97,144],"framework,":[99],"propose":[101],"deep":[103,111],"reinforcement":[104],"learning-based":[105],"algorithm":[107,128],"that":[108,125,152],"uses":[109],"neural":[112],"network":[113],"strategy":[117],"partial":[120],"map.":[121],"results":[123,150],"show":[124],"proposed":[127],"has":[129],"better":[130],"adaptability":[134],"environments.":[137],"addition,":[139],"conduct":[141],"experiments":[143],"physical":[146],"robot,":[147],"suggest":[151],"learned":[154],"policy":[155],"can":[156],"be":[157],"well":[158],"transferred":[159],"real":[164],"robot.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":52},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":40},{"year":2020,"cited_by_count":16}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}