{"id":"https://openalex.org/W4309675374","doi":"https://doi.org/10.1109/smc53654.2022.9945511","title":"Policy Transfer in POMDP Models for Safety-Critical Autonomous Vehicles Applications","display_name":"Policy Transfer in POMDP Models for Safety-Critical Autonomous Vehicles Applications","publication_year":2022,"publication_date":"2022-10-09","ids":{"openalex":"https://openalex.org/W4309675374","doi":"https://doi.org/10.1109/smc53654.2022.9945511"},"language":"en","primary_location":{"id":"doi:10.1109/smc53654.2022.9945511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945511","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5042700188","display_name":"Parisa Pouya","orcid":"https://orcid.org/0000-0002-8055-2002"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parisa Pouya","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA","University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053541626","display_name":"Azad M. Madni","orcid":"https://orcid.org/0000-0001-5225-0034"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Azad M. Madni","raw_affiliation_strings":["University of Southern California,Los Angeles,CA,USA","University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"1350","last_page":"1355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9878000020980835,"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.9660999774932861,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.9296643733978271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8003753423690796},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7666821479797363},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.7021670341491699},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5721529722213745},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5339891314506531},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.518886387348175},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.40890681743621826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3877546489238739},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33699172735214233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2992837727069855},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.23196744918823242},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.23110714554786682},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.1546218991279602},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09562540054321289}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.9296643733978271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003753423690796},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7666821479797363},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.7021670341491699},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5721529722213745},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5339891314506531},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.518886387348175},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.40890681743621826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3877546489238739},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33699172735214233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2992837727069855},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.23196744918823242},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.23110714554786682},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.1546218991279602},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09562540054321289},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53654.2022.9945511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945511","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":37,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W52153049","https://openalex.org/W72798631","https://openalex.org/W105074360","https://openalex.org/W107848263","https://openalex.org/W158722652","https://openalex.org/W225503657","https://openalex.org/W2055921164","https://openalex.org/W2095750692","https://openalex.org/W2097381042","https://openalex.org/W2123651102","https://openalex.org/W2141559023","https://openalex.org/W2250558341","https://openalex.org/W2252011326","https://openalex.org/W2582504501","https://openalex.org/W2800829932","https://openalex.org/W2808213164","https://openalex.org/W2886076544","https://openalex.org/W2963412383","https://openalex.org/W2963560082","https://openalex.org/W2998667194","https://openalex.org/W3046960330","https://openalex.org/W3111597472","https://openalex.org/W3214434388","https://openalex.org/W4210395649","https://openalex.org/W4220902314","https://openalex.org/W4287183137","https://openalex.org/W6604307813","https://openalex.org/W6674380327","https://openalex.org/W6674600207","https://openalex.org/W6680962669","https://openalex.org/W6681472862","https://openalex.org/W6691492831","https://openalex.org/W6733037351","https://openalex.org/W6781579029","https://openalex.org/W6795842337","https://openalex.org/W6809635482"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"Developing":[0],"models":[1,121],"of":[2,19,118],"complex":[3,183],"systems,":[4],"such":[5,43],"as":[6,129],"Autonomous":[7],"Vehicles":[8],"(AVs)":[9],"that":[10,38,80,142],"operate":[11],"in":[12,23,58,84,151,180,193],"uncertain,":[13],"reactive":[14],"environments":[15],"is":[16,33,39,48,65,104,126],"challenging":[17],"because":[18],"complexity":[20],"and":[21,61,72,91,187],"uncertainty":[22],"their":[24],"operational":[25],"environments.":[26],"Partially":[27],"Observable":[28],"Markov":[29],"Decision":[30],"Process":[31],"(POMDP)":[32],"a":[34,54,138,144,161,167,173,177,181],"mathematically":[35],"principled":[36],"framework":[37],"suitable":[40],"for":[41,148,166],"developing":[42],"models.":[44],"A":[45],"POMDP":[46,162],"model":[47,90],"typically":[49],"defined":[50,70],"with":[51],"respect":[52],"to":[53,94,100,105,113,128,157,176],"specific":[55],"task":[56,71,86,171,179],"performed":[57],"the":[59,62,69,76,85,89,107,110,194],"environment":[60,195],"resulting":[63],"policy":[64,92,149],"obtained":[66],"based":[67],"on":[68],"information":[73],"available":[74],"about":[75],"environment.":[77],"This":[78,124],"implies":[79],"if":[81],"changes":[82],"occur":[83],"and/or":[87],"environment,":[88,175,184],"need":[93],"be":[95,197],"updated.":[96],"One":[97],"efficient":[98],"way":[99],"achieve":[101],"this":[102,134,155],"end":[103],"reuse":[106],"experience":[108],"from":[109,122,160,190],"initial":[111],"task(s)":[112,116],"perform":[114],"similar":[115,178],"instead":[117],"designing":[119],"new":[120],"scratch.":[123],"technique":[125,141,156],"referred":[127],"Transfer":[130],"Learning":[131],"(TL).":[132],"In":[133],"paper,":[135],"we":[136],"propose":[137],"novel":[139],"TL":[140],"uses":[143],"customized":[145],"Q-learning":[146],"algorithm":[147],"transfer":[150,158],"POMDPs.":[152],"We":[153],"use":[154],"policies":[159],"model,":[163],"initially":[164],"designed":[165],"simple":[168],"AV":[169],"lane-keeping":[170],"within":[172],"freeway":[174],"more":[182],"where":[185],"random":[186],"risky":[188],"behaviors":[189],"neighboring":[191],"vehicles":[192],"can":[196],"expected.":[198]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}