{"id":"https://openalex.org/W3003660171","doi":"https://doi.org/10.1109/iros40897.2019.8967630","title":"Reinforcement Learning Boat Autopilot: A Sample-efficient and Model Predictive Control based Approach","display_name":"Reinforcement Learning Boat Autopilot: A Sample-efficient and Model Predictive Control based Approach","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3003660171","doi":"https://doi.org/10.1109/iros40897.2019.8967630","mag":"3003660171"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8967630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967630","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":"conference-paper","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/A5011048472","display_name":"Yunduan Cui","orcid":"https://orcid.org/0000-0001-5539-4260"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yunduan Cui","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Japan","Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027562344","display_name":"Shigeki Osaki","orcid":null},"institutions":[{"id":"https://openalex.org/I908894572","display_name":"Furuno (Japan)","ror":"https://ror.org/01a9h7w04","country_code":"JP","type":"company","lineage":["https://openalex.org/I908894572"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Osaki","raw_affiliation_strings":["FURUNO ELECTRIC CO., LTD.,Japan","FURUNO ELECTRIC CO., LTD., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FURUNO ELECTRIC CO., LTD.,Japan","institution_ids":["https://openalex.org/I908894572"]},{"raw_affiliation_string":"FURUNO ELECTRIC CO., LTD., Japan","institution_ids":["https://openalex.org/I908894572"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Japan","Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2868","last_page":"2875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9921000003814697,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9921000003814697,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9796000123023987,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9639000296592712,"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/autopilot","display_name":"Autopilot","score":0.9118615984916687},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.810541033744812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.632760763168335},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5778375864028931},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5472504496574402},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5301557183265686},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5218868851661682},{"id":"https://openalex.org/keywords/global-positioning-system","display_name":"Global Positioning System","score":0.5076311826705933},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4925287663936615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4612544775009155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4263013005256653},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3688187599182129},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.31588414311408997},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.27668941020965576},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.2618524432182312}],"concepts":[{"id":"https://openalex.org/C18020424","wikidata":"https://www.wikidata.org/wiki/Q220858","display_name":"Autopilot","level":2,"score":0.9118615984916687},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.810541033744812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.632760763168335},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5778375864028931},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5472504496574402},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5301557183265686},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5218868851661682},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.5076311826705933},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4925287663936615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4612544775009155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4263013005256653},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3688187599182129},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31588414311408997},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27668941020965576},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2618524432182312},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros40897.2019.8967630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967630","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":[{"score":0.7799999713897705,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W316935178","https://openalex.org/W1585754671","https://openalex.org/W1607198972","https://openalex.org/W1869302287","https://openalex.org/W1971071052","https://openalex.org/W1977655452","https://openalex.org/W1978956894","https://openalex.org/W2013928382","https://openalex.org/W2018705428","https://openalex.org/W2060794637","https://openalex.org/W2094941760","https://openalex.org/W2099768828","https://openalex.org/W2104281387","https://openalex.org/W2104533781","https://openalex.org/W2107804093","https://openalex.org/W2118081656","https://openalex.org/W2121863487","https://openalex.org/W2152842312","https://openalex.org/W2345644119","https://openalex.org/W2395636425","https://openalex.org/W2418467170","https://openalex.org/W2500214046","https://openalex.org/W2580909119","https://openalex.org/W2700407638","https://openalex.org/W2738778707","https://openalex.org/W2894693945","https://openalex.org/W2950077224","https://openalex.org/W2963809569","https://openalex.org/W3140968660","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W6639339491","https://openalex.org/W6674989108","https://openalex.org/W6675740164","https://openalex.org/W6712388604","https://openalex.org/W6740033195","https://openalex.org/W6755524192"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W2273635966","https://openalex.org/W2330887794","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W4290792893","https://openalex.org/W2959276766","https://openalex.org/W4319083788","https://openalex.org/W1984351658","https://openalex.org/W2963749556"],"abstract_inverted_index":{"In":[0],"this":[1,46],"research":[2],"we":[3,48],"focus":[4],"on":[5],"developing":[6],"a":[7,12,18,42,50,80,116,131,136],"reinforcement":[8,56,63],"learning":[9,57,64],"system":[10,100,126],"for":[11],"challenging":[13,29],"task:":[14],"autonomous":[15],"control":[16,68,76,91,97],"of":[17,37],"real-sized":[19,132],"boat,":[20],"with":[21,41,135],"difficulties":[22],"arising":[23],"from":[24],"large":[25],"uncertainties":[26],"in":[27,115,147],"the":[28,33,94,124],"ocean":[30],"environment":[31],"and":[32,39,65,85,139,145],"extremely":[34],"high":[35],"cost":[36],"exploring":[38],"sampling":[40],"real":[43,120],"boat.":[44],"To":[45],"end,":[47],"explore":[49],"novel":[51],"Gaussian":[52,81],"processes":[53],"(GP)":[54],"based":[55],"approach":[58],"that":[59],"combines":[60],"sample-efficient":[61,72],"model-based":[62],"model":[66,74,84],"predictive":[67,75],"(MPC).":[69],"Our":[70],"approach,":[71],"probabilistic":[73],"(SPMPC),":[77],"iteratively":[78],"learns":[79,128],"process":[82],"dynamics":[83],"uses":[86],"it":[87],"to":[88,105,129],"efficiently":[89,106],"update":[90],"signals":[92],"within":[93],"MPC":[95],"closed":[96],"loop.":[98],"A":[99],"using":[101],"SPMPC":[102],"is":[103],"built":[104],"learn":[107],"an":[108,148],"autopilot":[109,149],"task.":[110],"After":[111],"investigating":[112],"its":[113],"performance":[114],"simulation":[117],"modeled":[118],"upon":[119],"boat":[121,133],"driving":[122],"data,":[123],"proposed":[125],"successfully":[127],"drive":[130],"equipped":[134],"single":[137],"engine":[138],"sensors":[140],"measuring":[141],"GPS,":[142],"speed,":[143],"direction,":[144],"wind":[146],"task":[150],"without":[151],"human":[152],"demonstration.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}