{"id":"https://openalex.org/W7136955866","doi":"https://doi.org/10.1109/itsc60802.2025.11423570","title":"Continuous Inverse Reinforcement Learning with State-wise Safety Constraints for Stable Driving Behavior Prediction","display_name":"Continuous Inverse Reinforcement Learning with State-wise Safety Constraints for Stable Driving Behavior Prediction","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W7136955866","doi":"https://doi.org/10.1109/itsc60802.2025.11423570"},"language":null,"primary_location":{"id":"doi:10.1109/itsc60802.2025.11423570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","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/A5129523413","display_name":"Minglu Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minglu Zhao","raw_affiliation_strings":["Institute of Science Tokyo,Department of Computer Science,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Department of Computer Science,Tokyo,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032839697","display_name":"Masamichi Shimosaka","orcid":"https://orcid.org/0000-0003-0558-2006"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masamichi Shimosaka","raw_affiliation_strings":["Institute of Science Tokyo,Department of Computer Science,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Department of Computer Science,Tokyo,Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"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":0.56735425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3820","last_page":"3826"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.4787999987602234,"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":0.4787999987602234,"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":0.2793000042438507,"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/T10805","display_name":"Vehicle Dynamics and Control Systems","score":0.017000000923871994,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4722000062465668},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.45809999108314514},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38370001316070557},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3395000100135803},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.33180001378059387},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.298799991607666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5199000239372253},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4722000062465668},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.45809999108314514},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3034999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2761000096797943},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25279998779296875},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc60802.2025.11423570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.594490647315979,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2107105977","https://openalex.org/W2566837261","https://openalex.org/W3003474222","https://openalex.org/W3014596384","https://openalex.org/W3133456577","https://openalex.org/W3161803565","https://openalex.org/W4206497039","https://openalex.org/W4210909794","https://openalex.org/W4212795265","https://openalex.org/W4229008414","https://openalex.org/W4323796747","https://openalex.org/W4385767976","https://openalex.org/W4396937861","https://openalex.org/W4400645782","https://openalex.org/W7124170927"],"related_works":[],"abstract_inverted_index":{"Inverse":[0],"reinforcement":[1],"learning":[2,14,30],"(IRL)":[3],"is":[4,44],"a":[5,57,67,147],"promising":[6],"approach":[7],"for":[8,46,74,150],"modeling":[9],"human":[10],"driving":[11,49,113,123,139],"behaviors":[12],"by":[13],"underlying":[15],"reward":[16,88],"functions":[17],"from":[18],"expert":[19],"demonstrations.":[20],"While":[21],"recent":[22],"studies":[23],"have":[24],"incorporated":[25],"failed":[26],"demonstrations":[27],"to":[28],"improve":[29],"robustness,":[31],"most":[32],"existing":[33],"methods":[34],"enforce":[35],"safety":[36,64,72,100,132],"constraints":[37,65],"only":[38],"at":[39,101],"the":[40,83,86,91,108],"trajectory":[41],"level,":[42],"which":[43,70],"insufficient":[45],"real-world":[47],"autonomous":[48,152],"scenarios":[50,114],"requiring":[51],"per-state":[52],"safety.":[53],"This":[54],"paper":[55],"proposes":[56],"novel":[58],"IRL":[59],"framework":[60],"that":[61,129],"introduces":[62],"state-wise":[63,131],"via":[66],"behavior":[68,120,140],"discriminator,":[69],"generates":[71],"labels":[73],"each":[75],"state":[76],"based":[77],"on":[78],"environmental":[79],"context.":[80],"By":[81],"integrating":[82],"discriminator":[84],"into":[85],"main":[87],"optimization":[89],"loop,":[90],"proposed":[92],"method":[93],"avoids":[94],"additional":[95],"computational":[96],"complexity":[97],"while":[98],"ensuring":[99],"every":[102],"decision":[103],"point.":[104],"Experimental":[105],"results":[106,127],"in":[107,118,138,142],"CARLA":[109],"simulator":[110],"across":[111],"multiple":[112],"demonstrate":[115],"improved":[116],"performance":[117],"both":[119],"imitation":[121],"and":[122,136],"task":[124],"requirements.":[125],"The":[126],"confirm":[128],"enforcing":[130],"significantly":[133],"enhances":[134],"stability":[135],"reliability":[137],"prediction":[141],"static":[143],"contextual":[144],"environments,":[145],"providing":[146],"viable":[148],"direction":[149],"safer":[151],"decision-making.":[153]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-17T00:00:00"}