{"id":"https://openalex.org/W2898994065","doi":"https://doi.org/10.3390/s18113650","title":"Learn to Steer through Deep Reinforcement Learning","display_name":"Learn to Steer through Deep Reinforcement Learning","publication_year":2018,"publication_date":"2018-10-27","ids":{"openalex":"https://openalex.org/W2898994065","doi":"https://doi.org/10.3390/s18113650","mag":"2898994065","pmid":"https://pubmed.ncbi.nlm.nih.gov/30373261"},"language":"en","primary_location":{"id":"doi:10.3390/s18113650","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s18113650","pdf_url":"https://www.mdpi.com/1424-8220/18/11/3650/pdf?version=1541412428","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/18/11/3650/pdf?version=1541412428","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038637903","display_name":"Keyu Wu","orcid":"https://orcid.org/0000-0001-8493-0712"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Keyu Wu","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8493-0712","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035767152","display_name":"Mahdi Abolfazli Esfahani","orcid":"https://orcid.org/0000-0002-0709-0534"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mahdi Abolfazli Esfahani","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0709-0534","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026848789","display_name":"Shenghai Yuan","orcid":"https://orcid.org/0009-0003-1887-6342"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shenghai Yuan","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100452641","display_name":"Han Wang","orcid":"https://orcid.org/0000-0001-5448-9903"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Han Wang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100452641"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":4.2927,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.95186864,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"18","issue":"11","first_page":"3650","last_page":"3650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10653","display_name":"Robot Manipulation and Learning","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7446527481079102},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6466615200042725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4638725519180298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4137808680534363},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3651851415634155},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3650808334350586},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13666588068008423}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7446527481079102},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6466615200042725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4638725519180298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4137808680534363},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3651851415634155},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3650808334350586},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13666588068008423}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.3390/s18113650","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s18113650","pdf_url":"https://www.mdpi.com/1424-8220/18/11/3650/pdf?version=1541412428","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:30373261","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30373261","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":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:366e81862f8e4ae2b59bc0fd23be90bb","is_oa":true,"landing_page_url":"https://doaj.org/article/366e81862f8e4ae2b59bc0fd23be90bb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 18, Iss 11, p 3650 (2018)","raw_type":"article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/103342","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/103342","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:5257609","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6263476","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:mdpi.com:/1424-8220/18/11/3650/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/s18113650","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6263476","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6263476","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s18113650","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s18113650","pdf_url":"https://www.mdpi.com/1424-8220/18/11/3650/pdf?version=1541412428","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2898994065.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1512919909","https://openalex.org/W1757796397","https://openalex.org/W2111481694","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2167340365","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2528501250","https://openalex.org/W2563670399","https://openalex.org/W2567015638","https://openalex.org/W2573311857","https://openalex.org/W2597525528","https://openalex.org/W2610859226","https://openalex.org/W2611290840","https://openalex.org/W2732319713","https://openalex.org/W2737529802","https://openalex.org/W2746553466","https://openalex.org/W2768393699","https://openalex.org/W2769883686","https://openalex.org/W2770679144","https://openalex.org/W2792791722","https://openalex.org/W2794689129","https://openalex.org/W2795561664","https://openalex.org/W2796447411","https://openalex.org/W2811406095","https://openalex.org/W2886678529","https://openalex.org/W2887063207","https://openalex.org/W2962832483","https://openalex.org/W2962887844","https://openalex.org/W2962954724","https://openalex.org/W2962957005","https://openalex.org/W2963019567","https://openalex.org/W2963129648","https://openalex.org/W2963428623","https://openalex.org/W2963544079","https://openalex.org/W2963591054","https://openalex.org/W2963780790","https://openalex.org/W2963821308","https://openalex.org/W2964174623","https://openalex.org/W6713134421","https://openalex.org/W6741312563"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"It":[0,136],"is":[1,75,125,137,144,164,230],"crucial":[2],"for":[3],"robots":[4],"to":[5,18,27,38,55,107,129,151,218],"autonomously":[6],"steer":[7],"in":[8,52,62,174,187],"complex":[9,63],"environments":[10],"safely":[11],"without":[12,154],"colliding":[13],"with":[14,40,86,168],"any":[15,155],"obstacles.":[16],"Compared":[17],"conventional":[19],"methods,":[20],"deep":[21,48],"reinforcement":[22,49],"learning-based":[23,91],"methods":[24,173],"are":[25,207],"able":[26],"learn":[28],"from":[29,82,97,147],"past":[30],"experiences":[31],"automatically":[32],"and":[33,104,110,134,166,221,234],"enhance":[34],"the":[35,57,72,94,119,122,131,141,181,184,212],"generalization":[36],"capability":[37],"cope":[39],"unseen":[41],"circumstances.":[42],"Therefore,":[43],"we":[44],"propose":[45],"an":[46],"end-to-end":[47],"learning":[50,132,192],"algorithm":[51],"this":[53],"paper":[54],"improve":[56,130],"performance":[58],"of":[59,77,118,171,183,189,204,215,227],"autonomous":[60],"steering":[61,79],"environments.":[64,177,224],"By":[65],"embedding":[66],"a":[67,169,202],"branching":[68],"noisy":[69],"dueling":[70],"architecture,":[71],"proposed":[73,162,185],"model":[74,186,217],"capable":[76],"deriving":[78],"commands":[80,113],"directly":[81],"raw":[83],"depth":[84,98,159],"images":[85],"high":[87,213],"efficiency.":[88],"Specifically,":[89],"our":[90,216,228],"approach":[92],"extracts":[93],"feature":[95],"representation":[96],"inputs":[99],"through":[100,115],"convolutional":[101],"neural":[102],"networks":[103],"maps":[105],"it":[106],"both":[108,219],"linear":[109],"angular":[111],"velocity":[112],"simultaneously":[114],"different":[116],"streams":[117],"network.":[120],"Moreover,":[121,201],"training":[123,149],"framework":[124],"also":[126,208],"meticulously":[127],"designed":[128],"efficiency":[133],"effectiveness.":[135],"worth":[138],"noting":[139],"that":[140],"developed":[142],"system":[143],"readily":[145],"transferable":[146],"virtual":[148,176],"scenarios":[150],"real-world":[152,205],"deployment":[153],"fine-tuning":[156],"by":[157],"utilizing":[158],"images.":[160],"The":[161],"method":[163],"evaluated":[165],"compared":[167],"series":[170],"baseline":[172],"various":[175],"Experimental":[178],"results":[179],"demonstrate":[180],"superiority":[182],"terms":[188],"average":[190],"reward,":[191],"efficiency,":[193],"success":[194],"rate":[195],"as":[196,198],"well":[197],"computational":[199],"time.":[200],"variety":[203],"experiments":[206,229],"conducted":[209],"which":[210],"reveal":[211],"adaptability":[214],"static":[220],"dynamic":[222],"obstacle-cluttered":[223],"A":[225],"video":[226],"available":[231],"at":[232],"https://youtu.be/yixnmFXIKf4":[233],"http://v.youku.com/vshow/idXMzg1ODYwMzM5Ng.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}