{"id":"https://openalex.org/W4416748522","doi":"https://doi.org/10.1109/iros60139.2025.11247055","title":"Dynamic Residual Safe Reinforcement Learning for Multi-Agent Safety-Critical Scenarios Decision-Making","display_name":"Dynamic Residual Safe Reinforcement Learning for Multi-Agent Safety-Critical Scenarios Decision-Making","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748522","doi":"https://doi.org/10.1109/iros60139.2025.11247055"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5115597574","display_name":"Kaifeng Wang","orcid":"https://orcid.org/0009-0003-4676-2529"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaifeng Wang","raw_affiliation_strings":["Beijing Institute of Technology,School of Mechanical Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Mechanical Engineering,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113584976","display_name":"Yinsong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinsong Chen","raw_affiliation_strings":["Beijing Institute of Technology,School of Mechanical Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Mechanical Engineering,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453264","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0003-4879-1537"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Beijing Institute of Technology,School of Mechanical Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Mechanical Engineering,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054063853","display_name":"Xueyuan Li","orcid":"https://orcid.org/0000-0003-1112-5610"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyuan Li","raw_affiliation_strings":["Beijing Institute of Technology,School of Mechanical Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Mechanical Engineering,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100620847","display_name":"Xin Gao","orcid":"https://orcid.org/0000-0002-7317-8059"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Gao","raw_affiliation_strings":["Beijing Institute of Technology,School of Mechanical Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Mechanical Engineering,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5115597574"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.7262,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78019766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4520","last_page":"4527"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.5440999865531921,"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":0.5440999865531921,"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":0.15710000693798065,"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":0.04960000142455101,"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":0.809499979019165},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5799999833106995},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5476999878883362},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5383999943733215},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.4846999943256378},{"id":"https://openalex.org/keywords/dynamic-data","display_name":"Dynamic data","score":0.4284000098705292},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.4198000133037567},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.399399995803833}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.809499979019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293000221252441},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5476999878883362},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C197298091","wikidata":"https://www.wikidata.org/wiki/Q5318963","display_name":"Dynamic data","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":26,"referenced_works":["https://openalex.org/W2903709398","https://openalex.org/W2951360122","https://openalex.org/W3016931720","https://openalex.org/W3119924655","https://openalex.org/W3126673337","https://openalex.org/W3184178129","https://openalex.org/W4285742085","https://openalex.org/W4308068353","https://openalex.org/W4308080772","https://openalex.org/W4361861254","https://openalex.org/W4386918874","https://openalex.org/W4390605292","https://openalex.org/W4391335029","https://openalex.org/W4391768528","https://openalex.org/W4396910051","https://openalex.org/W4400726628","https://openalex.org/W4401607266","https://openalex.org/W4401717567","https://openalex.org/W4402194461","https://openalex.org/W4402570683","https://openalex.org/W4405305553","https://openalex.org/W4405306098","https://openalex.org/W4405360780","https://openalex.org/W4405778617","https://openalex.org/W4405785932","https://openalex.org/W4415799242"],"related_works":[],"abstract_inverted_index":{"In":[0],"multi-agent":[1,75,93],"safety-critical":[2],"scenarios,":[3],"traditional":[4,144],"autonomous":[5],"driving":[6],"frameworks":[7,19],"face":[8],"significant":[9],"challenges":[10],"in":[11,26,35,57,147],"balancing":[12],"safety":[13,82,87,164],"constraints":[14,113],"and":[15,28,39,109,150],"task":[16],"performance.":[17],"These":[18],"struggle":[20],"to":[21,132,160],"quantify":[22],"dynamic":[23,79,94],"interaction":[24],"risks":[25,104],"real-time":[27],"depend":[29],"heavily":[30],"on":[31,91],"manual":[32],"rules,":[33],"resulting":[34],"low":[36],"computational":[37],"efficiency":[38],"conservative":[40],"strategies.":[41],"To":[42],"address":[43],"these":[44],"limitations,":[45],"we":[46],"propose":[47],"a":[48,58,85,119],"Dynamic":[49],"Residual":[50],"Safe":[51],"Reinforcement":[52],"Learning":[53],"(DRS-RL)":[54],"framework":[55,99],"grounded":[56],"safety-enhanced":[59],"networked":[60],"Markov":[61],"decision":[62],"process.":[63],"It\u2019s":[64],"the":[65,69,92,111,139,155,163,171],"first":[66],"time":[67],"that":[68,138],"weak-to-strong":[70,86],"theory":[71],"is":[72],"introduced":[73],"into":[74],"decision-making,":[76],"enabling":[77],"lightweight":[78],"calibration":[80],"of":[81,114,170],"boundaries":[83],"via":[84],"correction":[88],"paradigm.":[89],"Based":[90],"conflict":[95],"zone":[96],"model,":[97],"our":[98],"accurately":[100],"captures":[101],"spatiotemporal":[102],"coupling":[103],"among":[105],"heterogeneous":[106],"traffic":[107],"participants":[108],"surpasses":[110],"static":[112],"conventional":[115],"geometric":[116],"rules.":[117],"Moreover,":[118],"risk-aware":[120],"prioritized":[121],"experience":[122],"replay":[123],"mechanism":[124],"mitigates":[125],"data":[126],"distribution":[127],"bias":[128],"by":[129,158],"mapping":[130],"risk":[131],"sampling":[133],"probability.":[134],"Experimental":[135],"results":[136],"reveal":[137],"proposed":[140],"method":[141],"significantly":[142],"outperforms":[143],"RL":[145],"algorithms":[146],"safety,":[148],"efficiency,":[149],"comfort.":[151],"Specifically,":[152],"it":[153],"reduces":[154],"collision":[156],"rate":[157],"up":[159],"92.17%,":[161],"while":[162],"model":[165],"accounts":[166],"for":[167],"merely":[168],"27%":[169],"main":[172],"model\u2019s":[173],"parameters.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-11-28T00:00:00"}