{"id":"https://openalex.org/W7161773895","doi":"https://doi.org/10.1109/tase.2026.3695304","title":"Safe Fuzzy-CBF: A Monitoring Approach for Deep Reinforcement Learning Navigation Agents","display_name":"Safe Fuzzy-CBF: A Monitoring Approach for Deep Reinforcement Learning Navigation Agents","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7161773895","doi":"https://doi.org/10.1109/tase.2026.3695304"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3695304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3695304","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-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/A5136517226","display_name":"Min Yang","orcid":"https://orcid.org/0000-0002-7282-0759"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Yang","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7282-0759","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100647139","display_name":"Liu G","orcid":"https://orcid.org/0000-0002-5944-9852"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanjun Liu","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China","School of Electro-Mechanical Engineering, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-7523-4827","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"School of Electro-Mechanical Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136582459","display_name":"Ziyuan Zhou","orcid":"https://orcid.org/0000-0002-2649-8666"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyuan Zhou","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2649-8666","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021236088","display_name":"Gaiyun Liu","orcid":"https://orcid.org/0000-0002-4947-6267"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaiyun Liu","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China","School of Electro-Mechanical Engineering, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-4947-6267","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"School of Electro-Mechanical Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79941314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"10041","last_page":"10056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5228000283241272,"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":0.5228000283241272,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.11509999632835388,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.01769999973475933,"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":0.4909999966621399},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.3506999909877777},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.335099995136261},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.31929999589920044},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3140999972820282},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3077000081539154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5442000031471252},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4372999966144562},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.41670000553131104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41499999165534973},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3140999972820282},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3695304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3695304","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.40337443351745605}],"awards":[{"id":"https://openalex.org/G7988459160","display_name":null,"funder_award_id":"92582104","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,67],"safety-critical":[1],"reinforcement":[2],"learning":[3],"tasks":[4,139],"such":[5],"as":[6],"robot":[7],"navigation,":[8],"autonomous":[9,143],"driving,":[10],"and":[11,78,88,110,140,155],"industrial":[12],"control,":[13],"real-time":[14],"monitoring":[15,39],"of":[16],"agent":[17,44],"behavior":[18],"is":[19,115],"paramount":[20],"to":[21,128,168],"prevent":[22],"unsafe":[23],"actions":[24],"from":[25,53,75],"compromising":[26],"system":[27],"reliability.":[28],"We":[29],"introduce":[30],"Safe":[31],"Fuzzy":[32],"Control":[33],"Barrier":[34],"Functions":[35],"(Safe":[36],"Fuzzy-CBF),":[37],"a":[38,47,63,80,91,119,130],"framework":[40,147],"that":[41,84],"continuously":[42,81],"evaluates":[43],"risk":[45,93],"using":[46,104],"smooth":[48],"control":[49,126],"barrier":[50,83,113],"function":[51],"learned":[52],"data":[54,77],"via":[55],"Takagi-Sugeno":[56],"fuzzy":[57,73],"rules,":[58],"rather":[59],"than":[60],"relying":[61],"on":[62,135],"predefined":[64],"model-based":[65],"barrier.":[66],"the":[68,100,112,124,141,161],"offline":[69],"phase,":[70],"we":[71,98,117],"extract":[72],"rules":[74],"trajectory":[76],"construct":[79],"differentiable":[82],"unifies":[85],"state,":[86],"action,":[87],"cost":[89],"into":[90],"single":[92],"metric.":[94],"During":[95],"online":[96],"execution,":[97],"estimate":[99],"barrier\u2019s":[101],"time":[102,154],"derivative":[103],"finite":[105],"differences,":[106],"apply":[107],"Lipschitz-based":[108],"corrections,":[109],"when":[111],"condition":[114],"violated,":[116],"solve":[118],"small":[120],"quadratic":[121],"program":[122],"in":[123,152,172],"normalized":[125],"space":[127],"compute":[129],"safe":[131],"corrective":[132],"action.":[133],"Evaluated":[134],"three":[136],"Safety-Gymnasium":[137],"navigation":[138],"MetaDrive":[142],"driving":[144],"environment,":[145],"our":[146],"detects":[148],"emerging":[149],"safety":[150,158],"violations":[151],"real":[153],"enforces":[156],"runtime":[157],"without":[159],"degrading":[160],"underlying":[162],"RL":[163],"policy\u2019s":[164],"performance,":[165],"achieving":[166],"up":[167],"an":[169],"86.8%":[170],"reduction":[171],"accumulated":[173],"cost.":[174]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-21T00:00:00"}