{"id":"https://openalex.org/W4200294561","doi":"https://doi.org/10.1109/iros51168.2021.9635925","title":"Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation","display_name":"Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W4200294561","doi":"https://doi.org/10.1109/iros51168.2021.9635925"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9635925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635925","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5058298540","display_name":"Enrico Marchesini","orcid":"https://orcid.org/0000-0003-1858-7279"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enrico Marchesini","raw_affiliation_strings":["University of Verona, Verona, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110796636","display_name":"Davide Corsi","orcid":"https://orcid.org/0000-0002-1908-4449"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Corsi","raw_affiliation_strings":["University of Verona, Verona, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045922629","display_name":"Alessandro Farinelli","orcid":"https://orcid.org/0000-0002-2592-5814"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Farinelli","raw_affiliation_strings":["University of Verona, Verona, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3951,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85064695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5590","last_page":"5595"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9972000122070312,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9944999814033508,"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":0.9144929647445679},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8791318535804749},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8373647928237915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.755729079246521},{"id":"https://openalex.org/keywords/crossover","display_name":"Crossover","score":0.6543349623680115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6272582411766052},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.583463191986084},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5714244842529297},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5289918184280396},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4773566722869873},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43638935685157776},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11847835779190063},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.10218894481658936}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9144929647445679},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8791318535804749},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8373647928237915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755729079246521},{"id":"https://openalex.org/C122507166","wikidata":"https://www.wikidata.org/wiki/Q628906","display_name":"Crossover","level":2,"score":0.6543349623680115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6272582411766052},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.583463191986084},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5714244842529297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5289918184280396},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4773566722869873},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43638935685157776},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11847835779190063},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.10218894481658936},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9635925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9635925","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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":0.7400000095367432,"display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W111814201","https://openalex.org/W2158782408","https://openalex.org/W2201581102","https://openalex.org/W2736601468","https://openalex.org/W2738056127","https://openalex.org/W2738165626","https://openalex.org/W2754517384","https://openalex.org/W2761873684","https://openalex.org/W2777417342","https://openalex.org/W2904076963","https://openalex.org/W2931855931","https://openalex.org/W2950029838","https://openalex.org/W2950730819","https://openalex.org/W2950752390","https://openalex.org/W2951278471","https://openalex.org/W2962692913","https://openalex.org/W2963019567","https://openalex.org/W2967847744","https://openalex.org/W3011105131","https://openalex.org/W3037430760","https://openalex.org/W3089695338","https://openalex.org/W3099303207","https://openalex.org/W3104379836","https://openalex.org/W3116714419","https://openalex.org/W3120345700","https://openalex.org/W3132490819","https://openalex.org/W3185656037","https://openalex.org/W4205950066","https://openalex.org/W6604554258","https://openalex.org/W6687681856","https://openalex.org/W6741002519","https://openalex.org/W6746964556","https://openalex.org/W6754681091","https://openalex.org/W6757575293","https://openalex.org/W6760757228","https://openalex.org/W6779884726","https://openalex.org/W6780559895","https://openalex.org/W6788085919","https://openalex.org/W6798969013"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W4399363378"],"abstract_inverted_index":{"We":[0],"propose":[1,74,89],"a":[2,64,75,90,106,148],"novel":[3],"benchmark":[4,149],"environment":[5,25],"for":[6,150],"Safe":[7],"Reinforcement":[8,69],"Learning":[9,70],"focusing":[10],"on":[11,94],"aquatic":[12],"navigation.":[13],"Aquatic":[14],"navigation":[15],"is":[16,35],"an":[17],"extremely":[18],"challenging":[19],"task":[20],"due":[21],"to":[22,37,53,84,127],"the":[23,27,30,39,43,47,50,99,102,115,129,135,141],"non-stationary":[24],"and":[26,66,72,81],"uncertainties":[28],"of":[29,42,49,101,108,131,156],"robotic":[31],"platform,":[32],"hence":[33],"it":[34],"crucial":[36],"consider":[38,63],"safety":[40],"aspect":[41],"problem,":[44],"by":[45,140],"analyzing":[46],"behavior":[48,100],"trained":[51,103],"network":[52],"avoid":[54],"dangerous":[55],"situations":[56],"(e.g.,":[57],"collisions).":[58],"To":[59],"this":[60,144,154],"end,":[61],"we":[62,73,88],"value-based":[65],"policy-gradient":[67],"Deep":[68],"(DRL)":[71],"crossover-based":[76,116],"strategy":[77,92],"that":[78,97,114,133,137],"combines":[79],"gradient-based":[80],"gradient-free":[82],"DRL":[83,120],"improve":[85],"sample-efficiency.":[86],"Moreover,":[87],"verification":[91,124],"based":[93],"interval":[95],"analysis":[96],"checks":[98],"models":[104],"over":[105],"set":[107],"desired":[109],"properties.":[110,142],"Our":[111],"results":[112],"show":[113],"training":[117],"outperforms":[118],"prior":[119],"approaches,":[121],"while":[122],"our":[123],"allows":[125],"us":[126],"quantify":[128],"number":[130],"configurations":[132],"violate":[134],"behaviors":[136],"are":[138],"described":[139],"Crucially,":[143],"will":[145],"serve":[146],"as":[147],"future":[151],"research":[152],"in":[153],"domain":[155],"applications.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}