{"id":"https://openalex.org/W3004238231","doi":"https://doi.org/10.1109/iros40897.2019.8967612","title":"End-to-end sensorimotor control problems of AUVs with deep reinforcement learning","display_name":"End-to-end sensorimotor control problems of AUVs with deep reinforcement learning","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3004238231","doi":"https://doi.org/10.1109/iros40897.2019.8967612","mag":"3004238231"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8967612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5002406417","display_name":"Hui Wu","orcid":"https://orcid.org/0000-0001-7906-5170"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hui Wu","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,P.R.China","Department of Automation, Tsinghua University, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,P.R.China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, P.R.China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101868179","display_name":"Shiji Song","orcid":"https://orcid.org/0000-0003-0858-1770"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiji Song","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,P.R.China","Department of Automation, Tsinghua University, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,P.R.China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, P.R.China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020768563","display_name":"Ya-Chu Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yachu Hsu","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,P.R.China","Department of Automation, Tsinghua University, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,P.R.China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, P.R.China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088962631","display_name":"Keyou You","orcid":"https://orcid.org/0000-0003-4355-5340"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyou You","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,P.R.China","Department of Automation, Tsinghua University, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,P.R.China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, P.R.China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100752413","display_name":"Cheng Wu","orcid":"https://orcid.org/0000-0002-8611-2665"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Wu","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,P.R.China","Department of Automation, Tsinghua University, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,P.R.China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, P.R.China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002406417"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.1201,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.84378676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5869","last_page":"5874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7712396383285522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7215437889099121},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.6674425601959229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5879828333854675},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5729153156280518},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5584596395492554},{"id":"https://openalex.org/keywords/sonar","display_name":"Sonar","score":0.5425108671188354},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.5249252915382385},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.47602325677871704},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4442817270755768},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4325101971626282},{"id":"https://openalex.org/keywords/remotely-operated-underwater-vehicle","display_name":"Remotely operated underwater vehicle","score":0.4136642813682556},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.21371734142303467},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.21091815829277039}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7712396383285522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215437889099121},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.6674425601959229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5879828333854675},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5729153156280518},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5584596395492554},{"id":"https://openalex.org/C555745239","wikidata":"https://www.wikidata.org/wiki/Q133220","display_name":"Sonar","level":2,"score":0.5425108671188354},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5249252915382385},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.47602325677871704},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4442817270755768},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4325101971626282},{"id":"https://openalex.org/C145424490","wikidata":"https://www.wikidata.org/wiki/Q618465","display_name":"Remotely operated underwater vehicle","level":4,"score":0.4136642813682556},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.21371734142303467},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.21091815829277039},{"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros40897.2019.8967612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","score":0.5799999833106995,"display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1771410628","https://openalex.org/W1944816615","https://openalex.org/W2055067868","https://openalex.org/W2071279196","https://openalex.org/W2123998235","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2214731807","https://openalex.org/W2388591084","https://openalex.org/W2410619805","https://openalex.org/W2503435921","https://openalex.org/W2736601468","https://openalex.org/W2736791111","https://openalex.org/W2774922731","https://openalex.org/W2869375357","https://openalex.org/W2897553353","https://openalex.org/W2906829782","https://openalex.org/W2963864421","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6741002519"],"related_works":["https://openalex.org/W2071768959","https://openalex.org/W4319442894","https://openalex.org/W3199220297","https://openalex.org/W2137769200","https://openalex.org/W2070821970","https://openalex.org/W2032962400","https://openalex.org/W2921408402","https://openalex.org/W1961162662","https://openalex.org/W2090198653","https://openalex.org/W2102288430"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"on":[3,97],"sensorimotor":[4],"control":[5,28],"problems":[6],"of":[7,35,52,84,100],"Autonomous":[8],"Underwater":[9],"Vehicles":[10],"(AUVs)":[11],"using":[12],"deep":[13],"reinforcement":[14],"learning.":[15],"We":[16],"design":[17],"an":[18],"end-to-end":[19],"learning":[20,47],"architecture":[21,86],"mapping":[22],"original":[23],"sensor":[24,71],"input":[25],"to":[26,32,80,103],"continuous":[27],"output":[29],"without":[30,48],"referring":[31],"the":[33,46,50,82,90,94],"dynamics":[34],"vehicles.":[36],"To":[37],"avoid":[38],"difficult":[39],"and":[40,59,72,87],"noisy":[41],"underwater":[42,65,101],"localization,":[43],"we":[44,92],"implement":[45],"knowing":[49],"positions":[51],"AUVs":[53],"by":[54],"proposing":[55],"novel":[56],"state":[57],"encoder":[58],"reward":[60],"shaping":[61],"strategies.":[62,88],"Two":[63],"distinct":[64],"tasks,":[66],"obstacle":[67],"avoidance":[68],"with":[69,75],"sonar":[70],"pipeline":[73],"following":[74],"visual":[76],"sensor,":[77],"are":[78],"simulated":[79],"validate":[81],"effectiveness":[83],"proposed":[85],"For":[89],"latter,":[91],"test":[93],"learned":[95],"policy":[96],"realistic":[98],"images":[99],"pipelines":[102],"check":[104],"its":[105],"generalization":[106],"ability.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}