{"id":"https://openalex.org/W7010564517","doi":null,"title":"Integrating Vision-Language Models with Reinforcement Learning for Human-Aligned Decision-Making of Autonomous Vehicles","display_name":"Integrating Vision-Language Models with Reinforcement Learning for Human-Aligned Decision-Making of Autonomous Vehicles","publication_year":2024,"publication_date":"2024-11-29","ids":{"openalex":"https://openalex.org/W7010564517"},"language":"en","primary_location":{"id":"pmh:oai:https://spectrum.library.concordia.ca:995019","doi":null,"is_oa":true,"landing_page_url":"https://spectrum.library.concordia.ca/id/eprint/995019/1/Doroudian_MASc_S2025.pdf","pdf_url":"https://spectrum.library.concordia.ca/id/eprint/995019/1/Doroudian_MASc_S2025.pdf","source":{"id":"https://openalex.org/S4306400871","display_name":"Spectrum Research Repository (Concordia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I60158472","host_organization_name":"Concordia University","host_organization_lineage":["https://openalex.org/I60158472"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://spectrum.library.concordia.ca/id/eprint/995019/1/Doroudian_MASc_S2025.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115637392","display_name":"Erfan Doroudian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Doroudian, Erfan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5115637392"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.8511000275611877,"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":0.8511000275611877,"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":0.1315000057220459,"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":0.006000000052154064,"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/autonomous-vehicles","display_name":"autonomous vehicles","score":0.9800000190734863},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7990000247955322},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.9800000190734863},{"id":"https://openalex.org/keywords/reward-modeling","display_name":"reward modeling","score":0.8259999752044678},{"id":"https://openalex.org/keywords/unsignalized-intersections","display_name":"unsignalized intersections","score":0.9259999990463257},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6370000243186951},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.9169999957084656},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.9950000047683716},{"id":"https://openalex.org/keywords/traffic-flow-optimization","display_name":"traffic flow optimization","score":0.6959999799728394},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"collision avoidance","score":0.8209999799728394},{"id":"https://openalex.org/keywords/urban-driving","display_name":"urban driving","score":0.4869999885559082}],"concepts":[{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2809999883174896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26919999718666077}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:https://spectrum.library.concordia.ca:995019","doi":null,"is_oa":true,"landing_page_url":"https://spectrum.library.concordia.ca/id/eprint/995019/1/Doroudian_MASc_S2025.pdf","pdf_url":"https://spectrum.library.concordia.ca/id/eprint/995019/1/Doroudian_MASc_S2025.pdf","source":{"id":"https://openalex.org/S4306400871","display_name":"Spectrum Research Repository (Concordia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I60158472","host_organization_name":"Concordia University","host_organization_lineage":["https://openalex.org/I60158472"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:https://spectrum.library.concordia.ca:995019","doi":null,"is_oa":true,"landing_page_url":"https://spectrum.library.concordia.ca/id/eprint/995019/1/Doroudian_MASc_S2025.pdf","pdf_url":"https://spectrum.library.concordia.ca/id/eprint/995019/1/Doroudian_MASc_S2025.pdf","source":{"id":"https://openalex.org/S4306400871","display_name":"Spectrum Research Repository (Concordia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I60158472","host_organization_name":"Concordia University","host_organization_lineage":["https://openalex.org/I60158472"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.5142999887466431,"id":"https://metadata.un.org/sdg/11"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7010564517.pdf","grobid_xml":"https://content.openalex.org/works/W7010564517.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1658008008","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2201581102","https://openalex.org/W2260756217","https://openalex.org/W2736601468","https://openalex.org/W2920768993","https://openalex.org/W2947861305","https://openalex.org/W2964121744","https://openalex.org/W3030163527","https://openalex.org/W3037207827","https://openalex.org/W3094502228","https://openalex.org/W3107736070","https://openalex.org/W4311991106","https://openalex.org/W4318751977","https://openalex.org/W4322718191","https://openalex.org/W4361807044","https://openalex.org/W4386977020","https://openalex.org/W4387839182"],"related_works":["https://openalex.org/W4405765393","https://openalex.org/W4413858428","https://openalex.org/W7203833697","https://openalex.org/W4312252188","https://openalex.org/W7136657066","https://openalex.org/W4401607716","https://openalex.org/W4403977168","https://openalex.org/W7139942248","https://openalex.org/W7196981370","https://openalex.org/W4376868366"],"abstract_inverted_index":{"This":[0,177],"thesis":[1],"focuses":[2],"on":[3,87,158,197],"developing":[4],"a":[5,42,169],"new":[6],"approach":[7],"for":[8,13,103],"improving":[9,184],"the":[10,27,34,56,59,62,112,148,154,159,192,198,206,209,216,238],"decision-making":[11,114,186],"process":[12],"autonomous":[14,188,250],"vehicles":[15],"(AVs)":[16],"in":[17,37,133,168,183,187,219,268],"complex":[18,134],"urban":[19],"driving":[20,63,175],"scenarios,":[21],"particularly":[22,75],"at":[23],"unsignalized":[24,135],"intersections,":[25],"using":[26],"reinforcement":[28],"learning":[29],"(RL)":[30],"framework.":[31,211],"One":[32],"of":[33,58,140,156,208,240],"primary":[35],"difficulties":[36],"RL":[38,119],"environments":[39],"is":[40,143],"designing":[41],"suitable":[43],"reward":[44,84,108,150],"model,":[45,151],"which":[46,152,247],"can":[47],"often":[48],"be":[49],"challenging":[50],"to":[51,55,80,94,110,129,162,202,243],"achieve":[52],"manually":[53],"due":[54],"complexity":[57],"interactions":[60],"and":[61,89,97,125,146,164,204,225,229,255,260,265],"scenarios.":[64],"To":[65],"address":[66],"this":[67,69],"challenge,":[68],"work":[70],"utilizes":[71],"Vision-Language":[72],"Models":[73],"(VLMs),":[74],"CLIP":[76,157],"(Contrastive":[77],"Language-Image":[78],"Pretraining),":[79],"build":[81],"an":[82,131],"additional":[83],"model":[85],"based":[86],"visual":[88],"textual":[90],"cues.":[91],"CLIP\u2019s":[92],"ability":[93,161],"align":[95],"image":[96],"text":[98],"embeddings":[99],"provides":[100],"unique":[101],"features":[102],"translating":[104],"humanlike":[105],"instructions":[106],"into":[107],"signals":[109],"guide":[111,249],"AV\u2019s":[113],"process.":[115],"We":[116,190],"apply":[117],"two":[118],"algorithms,":[120],"Proximal":[121],"Policy":[122],"Optimization":[123],"(PPO)":[124],"Deep":[126],"Q-Network":[127],"(DQN),":[128],"train":[130],"agent":[132],"intersection":[136],"environments.":[137],"The":[138,235],"performance":[139],"these":[141],"algorithms":[142],"compared":[144],"with":[145,173],"without":[147],"CLIP-based":[149],"highlights":[153],"impact":[155],"agent\u2019s":[160],"learn":[163],"optimize":[165],"its":[166],"behavior":[167],"way":[170],"that":[171],"aligns":[172],"desired":[174],"actions.":[176],"study\u2019s":[178],"results":[179,236],"show":[180],"VLMs\u2019":[181],"capabilities":[182],"RL-based":[185],"driving.":[189],"utilize":[191],"Highway-env":[193],"simulation":[194,213],"package,":[195],"built":[196],"OpenAI":[199],"Gym":[200],"framework,":[201],"test":[203],"validate":[205],"effectiveness":[207,218],"proposed":[210],"Our":[212],"experiments":[214],"indicate":[215],"framework\u2019s":[217],"optimizing":[220],"traffic":[221],"flow,":[222],"minimizing":[223],"collisions,":[224],"balancing":[226],"both":[227],"individual":[228],"collective":[230],"benefits":[231],"among":[232],"road":[233],"users.":[234],"highlight":[237],"potential":[239],"integrating":[241],"VLMs":[242],"provide":[244],"human-aligned":[245],"instructions,":[246],"could":[248],"vehicle":[251],"actions":[252],"toward":[253],"safer":[254],"more":[256],"socially":[257],"acceptable":[258],"behaviors":[259],"eventually":[261],"promote":[262],"AVs\u2019":[263],"safe":[264],"trustable":[266],"deployment":[267],"future":[269],"intelligent":[270],"transportation":[271],"systems.":[272]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}