{"id":"https://openalex.org/W4389667358","doi":"https://doi.org/10.1109/iros55552.2023.10342389","title":"Robust Unmanned Surface Vehicle Navigation with Distributional Reinforcement Learning","display_name":"Robust Unmanned Surface Vehicle Navigation with Distributional Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667358","doi":"https://doi.org/10.1109/iros55552.2023.10342389"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5100450524","display_name":"Lin Xi","orcid":"https://orcid.org/0000-0003-0118-7391"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xi Lin","raw_affiliation_strings":["Stevens Institute of Technology,Department of Mechanical Engineering,Hoboken,NJ,USA,07030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology,Department of Mechanical Engineering,Hoboken,NJ,USA,07030","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086621167","display_name":"John McConnell","orcid":"https://orcid.org/0000-0002-4742-9854"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John McConnell","raw_affiliation_strings":["Stevens Institute of Technology,Department of Mechanical Engineering,Hoboken,NJ,USA,07030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology,Department of Mechanical Engineering,Hoboken,NJ,USA,07030","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044251670","display_name":"Brendan Englot","orcid":"https://orcid.org/0000-0002-7966-2917"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendan Englot","raw_affiliation_strings":["Stevens Institute of Technology,Department of Mechanical Engineering,Hoboken,NJ,USA,07030"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology,Department of Mechanical Engineering,Hoboken,NJ,USA,07030","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.468,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91333012,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6185","last_page":"6191"},"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/T11622","display_name":"Maritime Navigation and Safety","score":0.9950000047683716,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9868000149726868,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8847739696502686},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.7769805788993835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7145179510116577},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6572439670562744},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.5667251348495483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5516449809074402},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.45423856377601624},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.44606485962867737},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3376033306121826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3301210403442383},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18375006318092346}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8847739696502686},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.7769805788993835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145179510116577},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6572439670562744},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5667251348495483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5516449809074402},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.45423856377601624},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.44606485962867737},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3376033306121826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3301210403442383},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18375006318092346},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3693076604","display_name":null,"funder_award_id":"N00014-20-1-2570,N00014-21-1-2161","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1092373588","https://openalex.org/W1515188965","https://openalex.org/W1608481154","https://openalex.org/W1978580424","https://openalex.org/W1992534732","https://openalex.org/W1993718093","https://openalex.org/W2055930054","https://openalex.org/W2071099748","https://openalex.org/W2083513815","https://openalex.org/W2098412395","https://openalex.org/W2102684965","https://openalex.org/W2103120971","https://openalex.org/W2105043361","https://openalex.org/W2120579877","https://openalex.org/W2145339207","https://openalex.org/W2154984757","https://openalex.org/W2303431639","https://openalex.org/W2397340831","https://openalex.org/W2557621405","https://openalex.org/W2562163136","https://openalex.org/W2602991367","https://openalex.org/W2728420778","https://openalex.org/W2892245714","https://openalex.org/W2897477155","https://openalex.org/W2911283711","https://openalex.org/W2939163388","https://openalex.org/W2963428623","https://openalex.org/W2969897047","https://openalex.org/W3016687824","https://openalex.org/W3019349330","https://openalex.org/W3045974612","https://openalex.org/W3081803538","https://openalex.org/W3086606660","https://openalex.org/W3132663004","https://openalex.org/W3179660843","https://openalex.org/W3206010851","https://openalex.org/W3209852576","https://openalex.org/W3216772467","https://openalex.org/W4205404209","https://openalex.org/W4383108603","https://openalex.org/W6683300800","https://openalex.org/W6751629939","https://openalex.org/W6804601995","https://openalex.org/W6809924501"],"related_works":["https://openalex.org/W2155467318","https://openalex.org/W122632647","https://openalex.org/W2060743914","https://openalex.org/W2359600231","https://openalex.org/W187779371","https://openalex.org/W3216757130","https://openalex.org/W2380019117","https://openalex.org/W2093343611","https://openalex.org/W1987886368","https://openalex.org/W1660309994"],"abstract_inverted_index":{"Autonomous":[0],"navigation":[1,23],"of":[2,32,57,69],"Unmanned":[3],"Surface":[4],"Vehicles":[5],"(USV)":[6],"in":[7,25,74,139],"marine":[8],"environments":[9,27],"with":[10],"current":[11,34],"flows":[12],"is":[13,125,131],"challenging,":[14],"and":[15,36,60,86,108,118,130,142],"few":[16],"prior":[17,30],"works":[18],"have":[19],"addressed":[20],"the":[21,33,55,67,72,75,119,122],"sensor-based":[22],"problem":[24],"such":[26,113],"under":[28],"no":[29],"knowledge":[31],"flow":[35],"obstacles.":[37],"We":[38],"propose":[39],"a":[40,81,92,103],"Distributional":[41],"Reinforcement":[42],"Learning":[43],"(RL)":[44],"based":[45,95,106],"local":[46,110],"path":[47],"planner":[48,79,107,124],"that":[49,64,100,136],"learns":[50],"return":[51],"distributions":[52],"which":[53],"capture":[54],"uncertainty":[56],"action":[58],"outcomes,":[59],"an":[61],"adaptive":[62],"algorithm":[63],"automatically":[65],"tunes":[66],"level":[68],"sensitivity":[70],"to":[71,88,102,133],"risk":[73],"environment.":[76],"The":[77],"proposed":[78,123],"achieves":[80],"more":[82],"stable":[83],"learning":[84],"performance":[85],"converges":[87],"safer":[89],"policies":[90],"than":[91],"traditional":[93,104],"RL":[94,105],"planner.":[96],"Computational":[97],"experiments":[98],"demonstrate":[99],"comparing":[101],"classical":[109],"planning":[111],"methods":[112],"as":[114],"Artificial":[115],"Potential":[116],"Fields":[117],"Bug":[120],"Algorithm,":[121],"robust":[126],"against":[127],"environmental":[128],"flows,":[129],"able":[132],"plan":[134],"trajectories":[135],"are":[137],"superior":[138],"safety,":[140],"time":[141],"energy":[143],"consumption.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}