{"id":"https://openalex.org/W4415708287","doi":"https://doi.org/10.1109/icme59968.2025.11209801","title":"Safety-constrained Reinforcement Learning with Interaction-aware for Decision-making of Autonomous Driving","display_name":"Safety-constrained Reinforcement Learning with Interaction-aware for Decision-making of Autonomous Driving","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708287","doi":"https://doi.org/10.1109/icme59968.2025.11209801"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102940417","display_name":"Di Zhang","orcid":"https://orcid.org/0000-0001-7194-0591"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Zhang","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085348492","display_name":"Haonan Luo","orcid":"https://orcid.org/0000-0002-9121-2687"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Luo","raw_affiliation_strings":["Southwest Jiaotong University,School of Computer and Artificial Intelligence,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University,School of Computer and Artificial Intelligence,China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103272601","display_name":"Honglin Dong","orcid":"https://orcid.org/0000-0002-3372-4094"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honglin Dong","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011582298","display_name":"Jianfeng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Lu","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.4690000116825104,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.4690000116825104,"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":0.2822999954223633,"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/T10524","display_name":"Traffic control and management","score":0.11060000211000443,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8184000253677368},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5383999943733215},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4618000090122223},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.37540000677108765},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.3709999918937683},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.30059999227523804}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8184000253677368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6516000032424927},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47049999237060547},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4618000090122223},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2777999937534332},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2619999945163727},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2939569248","https://openalex.org/W2951360122","https://openalex.org/W2963165400","https://openalex.org/W2989964169","https://openalex.org/W2990123902","https://openalex.org/W3003329097","https://openalex.org/W3121045039","https://openalex.org/W3127561923","https://openalex.org/W3130519362","https://openalex.org/W3176452384","https://openalex.org/W3191652410","https://openalex.org/W3203497287","https://openalex.org/W4287947470","https://openalex.org/W4383502669","https://openalex.org/W4386076400","https://openalex.org/W4390788068","https://openalex.org/W4390872423","https://openalex.org/W4391793348","https://openalex.org/W4392449656"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning(RL)":[1],"has":[2],"made":[3],"significant":[4],"advancements":[5],"in":[6,134],"autonomous":[7,27],"driving(AD).":[8],"However,":[9],"the":[10,18,48,54,71,84,94,99],"stochastic":[11],"nature":[12],"of":[13,20,98],"dynamic":[14],"traffic":[15],"scenario":[16],"and":[17,32,66,74,80,96,105,116,140],"diversity":[19],"road":[21],"type":[22],"make":[23,30],"it":[24,82],"challenging":[25],"for":[26],"vehicles":[28],"to":[29,52,62,92,114],"safe":[31],"efficient":[33],"decisions.":[34],"To":[35,101],"tackle":[36],"these":[37],"problems,":[38],"this":[39],"paper":[40],"proposes":[41],"a":[42,78,111],"novel":[43],"RL":[44,127],"framework":[45],"that":[46,123],"incorporates":[47],"motion":[49],"prediction":[50],"model":[51,63],"enhance":[53],"agent\u2019s":[55],"decision-making":[56],"capability.":[57],"We":[58],"first":[59],"utilize":[60],"Transformer":[61],"driving":[64],"scenarios":[65],"capture":[67],"interaction-aware":[68],"relationships":[69],"between":[70],"ego":[72],"vehicle":[73],"scenarios,":[75],"then":[76],"design":[77],"safety-constraint":[79],"integrate":[81],"into":[83],"Proximal":[85],"Policy":[86],"Optimization":[87],"(PPO)":[88],"algorithm":[89],"so":[90],"as":[91],"guarantee":[93],"safety":[95],"feasibility":[97],"policy.":[100],"improve":[102],"data":[103,141],"efficiency":[104],"filter":[106],"noisy":[107],"samples,":[108],"we":[109],"construct":[110],"dual":[112],"network":[113],"communicate":[115],"guide":[117],"each":[118],"other.":[119],"Experimental":[120],"results":[121],"show":[122],"compared":[124],"with":[125],"popular":[126],"algorithms,":[128],"our":[129],"method":[130],"demonstrates":[131],"superior":[132],"performance":[133],"success":[135],"rate,":[136],"completion":[137],"time,":[138],"safety,":[139],"efficiency.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}