{"id":"https://openalex.org/W7127131206","doi":"https://doi.org/10.1109/trustcom66490.2025.00160","title":"Safety-Aware DRL Training Based on Reachability Analysis","display_name":"Safety-Aware DRL Training Based on Reachability Analysis","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W7127131206","doi":"https://doi.org/10.1109/trustcom66490.2025.00160"},"language":null,"primary_location":{"id":"doi:10.1109/trustcom66490.2025.00160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/trustcom66490.2025.00160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 24th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","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/A5039924074","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-8917-2196"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Yang","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing East China Normal University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402899","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3152-4347"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Shanghai Key Laboratory of Trustworthy Computing East China Normal University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Trustworthy Computing East China Normal University,Shanghai,China","institution_ids":["https://openalex.org/I4210139618","https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.80831814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1380","last_page":"1387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.4957999885082245,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.4957999885082245,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.3797000050544739,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.06379999965429306,"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/reachability","display_name":"Reachability","score":0.852400004863739},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.5378000140190125},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.520799994468689},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.5149999856948853},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.513700008392334},{"id":"https://openalex.org/keywords/formal-verification","display_name":"Formal verification","score":0.478300005197525},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.4584999978542328},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.45419999957084656}],"concepts":[{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.852400004863739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991999745368958},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.5378000140190125},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.5149999856948853},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.4584999978542328},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.44279998540878296},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C132835097","wikidata":"https://www.wikidata.org/wiki/Q7663745","display_name":"System safety","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.2768000066280365}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/trustcom66490.2025.00160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/trustcom66490.2025.00160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 24th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2053572490","https://openalex.org/W2080542576","https://openalex.org/W2105863608","https://openalex.org/W2109569369","https://openalex.org/W2615547864","https://openalex.org/W2788084076","https://openalex.org/W2892027510","https://openalex.org/W2963679616","https://openalex.org/W2968176166","https://openalex.org/W2987092895","https://openalex.org/W3026646233","https://openalex.org/W3035020089","https://openalex.org/W3038180127","https://openalex.org/W3129038712","https://openalex.org/W3133096016","https://openalex.org/W3135301907","https://openalex.org/W3159199672","https://openalex.org/W4211202104","https://openalex.org/W4312660377","https://openalex.org/W4385730946","https://openalex.org/W4388505288","https://openalex.org/W4402402057"],"related_works":[],"abstract_inverted_index":{"The":[0],"growing":[1],"adoption":[2],"of":[3],"deep":[4],"reinforcement":[5],"learning":[6],"(DRL)":[7],"in":[8,30,108,151],"safety-critical":[9,141],"domains":[10],"like":[11],"autonomous":[12,109],"driving":[13,110],"has":[14],"been":[15],"hindered":[16],"by":[17],"the":[18,57,94],"fundamental":[19],"conflict":[20],"between":[21],"performance":[22,115],"optimization":[23,95,150],"and":[24,34,80,134],"safety":[25,38,73,83,91,114],"assurance.":[26],"While":[27],"DRL":[28,49,119],"excels":[29],"high-dimensional":[31],"state":[32,77],"spaces":[33],"long-term":[35],"planning,":[36],"unexpected":[37],"violations":[39],"pose":[40],"catastrophic":[41],"risks.":[42],"This":[43,129],"work":[44,144],"introduces":[45],"a":[46,66,137],"novel":[47],"safety-aware":[48,138],"framework":[50,130],"that":[51],"integrates":[52],"formal":[53,132],"reachability":[54,68],"analysis":[55,69],"into":[56,93],"training":[58],"pipeline.":[59],"Our":[60],"approach":[61],"features":[62],"two":[63],"innovations:":[64],"1)":[65],"pre-trained":[67],"module":[70],"quantifying":[71],"runtime":[72],"risks":[74],"through":[75],"reachable":[76],"set":[78],"computation,":[79],"2)":[81],"dynamic":[82],"constraints":[84],"enabling":[85],"real-time":[86],"policy":[87],"adaptation.":[88],"By":[89],"embedding":[90],"verification":[92,133],"loop,":[96],"our":[97],"method":[98],"systematically":[99],"balances":[100],"exploration":[101],"efficiency":[102,149],"with":[103],"risk":[104],"mitigation.":[105],"Empirical":[106],"validation":[107],"scenarios":[111],"demonstrates":[112],"superior":[113],"compared":[116],"to":[117],"conventional":[118],"methods,":[120],"achieving":[121],"significant":[122],"collision":[123],"avoidance":[124],"while":[125],"maintaining":[126],"competitive":[127],"efficiency.":[128],"bridges":[131],"DRL,":[135],"providing":[136],"solution":[139],"for":[140],"systems.":[142],"Future":[143],"will":[145],"focus":[146],"on":[147],"computational":[148],"dense":[152],"obstacle":[153],"environments.":[154]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-03T00:00:00"}