{"id":"https://openalex.org/W4315433670","doi":"https://doi.org/10.3389/fnbot.2022.1105480","title":"Research on reinforcement learning-based safe decision-making methodology for multiple unmanned aerial vehicles","display_name":"Research on reinforcement learning-based safe decision-making methodology for multiple unmanned aerial vehicles","publication_year":2023,"publication_date":"2023-01-10","ids":{"openalex":"https://openalex.org/W4315433670","doi":"https://doi.org/10.3389/fnbot.2022.1105480","pmid":"https://pubmed.ncbi.nlm.nih.gov/36704719"},"language":"en","primary_location":{"id":"doi:10.3389/fnbot.2022.1105480","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2022.1105480","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1105480/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1105480/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082177775","display_name":"Longfei Yue","orcid":"https://orcid.org/0000-0003-4618-5955"},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longfei Yue","raw_affiliation_strings":["Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080016253","display_name":"Rennong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rennong Yang","raw_affiliation_strings":["Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386104","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-2674-1638"},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China","institution_ids":["https://openalex.org/I4210104252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033950972","display_name":"Jialiang Zuo","orcid":"https://orcid.org/0000-0001-7085-7032"},"institutions":[{"id":"https://openalex.org/I4210104252","display_name":"Air Force Engineering University","ror":"https://ror.org/00seraz22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jialiang Zuo","raw_affiliation_strings":["Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an, China","institution_ids":["https://openalex.org/I4210104252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033950972"],"corresponding_institution_ids":["https://openalex.org/I4210104252"],"apc_list":{"value":2950,"currency":"USD","value_usd":2950},"apc_paid":{"value":2950,"currency":"USD","value_usd":2950},"fwci":1.0295,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80101072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"16","issue":null,"first_page":"1105480","last_page":"1105480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9800999760627747,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9660999774932861,"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":0.8605560064315796},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7989444732666016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7684195041656494},{"id":"https://openalex.org/keywords/lagrange-multiplier","display_name":"Lagrange multiplier","score":0.479469895362854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47601157426834106},{"id":"https://openalex.org/keywords/lagrangian","display_name":"Lagrangian","score":0.4382963180541992},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41270098090171814},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3568563163280487},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3391822278499603},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.22967371344566345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06831419467926025}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8605560064315796},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7989444732666016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684195041656494},{"id":"https://openalex.org/C73684929","wikidata":"https://www.wikidata.org/wiki/Q598870","display_name":"Lagrange multiplier","level":2,"score":0.479469895362854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47601157426834106},{"id":"https://openalex.org/C53469067","wikidata":"https://www.wikidata.org/wiki/Q505735","display_name":"Lagrangian","level":2,"score":0.4382963180541992},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41270098090171814},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3568563163280487},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3391822278499603},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.22967371344566345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06831419467926025},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fnbot.2022.1105480","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2022.1105480","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1105480/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},{"id":"pmid:36704719","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36704719","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":"Frontiers in neurorobotics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9873372","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9873372","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9873372/pdf/fnbot-16-1105480.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Neurorobot","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:9c683c96854e4d2fba5c0259872798f7","is_oa":true,"landing_page_url":"https://doaj.org/article/9c683c96854e4d2fba5c0259872798f7","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Neurorobotics, Vol 16 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fnbot.2022.1105480","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2022.1105480","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1105480/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G1281605329","display_name":null,"funder_award_id":"62106284","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2998737151","display_name":null,"funder_award_id":"62106284","funder_id":"https://openalex.org/F4320324173","funder_display_name":"Natural Science Foundation of Shaanxi Province"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3569266497","display_name":null,"funder_award_id":"20220101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7762281137","display_name":null,"funder_award_id":"2021JQ-370","funder_id":"https://openalex.org/F4320324173","funder_display_name":"Natural Science Foundation of Shaanxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324173","display_name":"Natural Science Foundation of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4315433670.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1589747210","https://openalex.org/W2037265949","https://openalex.org/W2043939916","https://openalex.org/W2129973382","https://openalex.org/W2135889985","https://openalex.org/W2168281840","https://openalex.org/W2304578911","https://openalex.org/W2516164580","https://openalex.org/W2518892488","https://openalex.org/W2529741607","https://openalex.org/W2585821313","https://openalex.org/W2781726626","https://openalex.org/W2790930275","https://openalex.org/W2805394695","https://openalex.org/W2904246096","https://openalex.org/W2966848886","https://openalex.org/W2972452616","https://openalex.org/W2997849501","https://openalex.org/W3007553593","https://openalex.org/W3037168587","https://openalex.org/W3082622020","https://openalex.org/W3112673853","https://openalex.org/W3125535900","https://openalex.org/W3176452384","https://openalex.org/W4231027539","https://openalex.org/W4233840023","https://openalex.org/W4293545785","https://openalex.org/W6631190155","https://openalex.org/W6680172340","https://openalex.org/W6737893269","https://openalex.org/W6747473740","https://openalex.org/W6757592117","https://openalex.org/W6774126978"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4404955202"],"abstract_inverted_index":{"A":[0],"system":[1],"with":[2,65,88],"multiple":[3],"cooperating":[4],"unmanned":[5],"aerial":[6],"vehicles":[7],"(multi-UAVs)":[8],"can":[9,122],"use":[10],"its":[11],"advantages":[12],"to":[13,42,77,103,112,133,135],"accomplish":[14],"complicated":[15],"tasks.":[16],"Recent":[17],"developments":[18],"in":[19,72,93],"deep":[20],"reinforcement":[21],"learning":[22,100],"(DRL)":[23],"offer":[24],"good":[25],"prospects":[26],"for":[27,29,56],"decision-making":[28],"multi-UAV":[30,57],"systems.":[31],"However,":[32],"the":[33,79,94,110,113,119,124,131],"safety":[34,74,125],"and":[35,106,126,129],"training":[36,108,127],"efficiencies":[37,128],"of":[38,109],"DRL":[39],"still":[40],"need":[41],"be":[43],"improved":[44],"before":[45],"practical":[46],"use.":[47],"This":[48],"study":[49],"presents":[50],"a":[51,66,89,136],"transfer-safe":[52],"soft":[53,82],"actor-critic":[54],"(TSSAC)":[55],"decision-making.":[58],"Decision-making":[59],"by":[60],"each":[61],"UAV":[62],"is":[63,75,86,101],"modeled":[64],"constrained":[67,76],"Markov":[68],"decision":[69],"process":[70],"(CMDP),":[71],"which":[73],"maximize":[78],"return.":[80],"The":[81],"actor-critic-Lagrangian":[83],"(SAC-Lagrangian)":[84],"algorithm":[85],"combined":[87],"modified":[90],"Lagrangian":[91],"multiplier":[92],"CMDP":[95],"model.":[96],"Moreover,":[97],"parameter-based":[98],"transfer":[99],"used":[102],"enable":[104],"cooperative":[105],"efficient":[107],"tasks":[111],"multi-UAVs.":[114],"Simulation":[115],"experiments":[116],"indicate":[117],"that":[118],"proposed":[120],"method":[121],"improve":[123],"allow":[130],"UAVs":[132],"adapt":[134],"dynamic":[137],"scenario.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}