{"id":"https://openalex.org/W4414580640","doi":"https://doi.org/10.48550/arxiv.2505.15925","title":"VERDI: VLM-Embedded Reasoning for Autonomous Driving","display_name":"VERDI: VLM-Embedded Reasoning for Autonomous Driving","publication_year":2025,"publication_date":"2025-05-21","ids":{"openalex":"https://openalex.org/W4414580640","doi":"https://doi.org/10.48550/arxiv.2505.15925"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.15925","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15925","pdf_url":"https://arxiv.org/pdf/2505.15925","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15925","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Feng, Bowen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210124078","display_name":"Torc Robotics (United States)","ror":"https://ror.org/03233xn13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124078"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng, Bowen","raw_affiliation_strings":["Princeton University Torc Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University Torc Robotics","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I4210124078"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058149361","display_name":"Zhiting Mei","orcid":"https://orcid.org/0000-0003-1831-8335","observed_orcids":["https://orcid.org/0000-0003-1831-8335"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210124078","display_name":"Torc Robotics (United States)","ror":"https://ror.org/03233xn13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124078"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei, Zhiting","raw_affiliation_strings":["Princeton University Torc Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University Torc Robotics","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I4210124078"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085140402","display_name":"Julian Ost","orcid":"https://orcid.org/0000-0001-6860-0246","observed_orcids":["https://orcid.org/0000-0001-6860-0246"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210124078","display_name":"Torc Robotics (United States)","ror":"https://ror.org/03233xn13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124078"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ost, Julian","raw_affiliation_strings":["Princeton University Torc Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University Torc Robotics","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I4210124078"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ghilotti, Filippo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghilotti, Filippo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Baiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210124078","display_name":"Torc Robotics (United States)","ror":"https://ror.org/03233xn13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124078"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Baiang","raw_affiliation_strings":["Princeton University Torc Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University Torc Robotics","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I4210124078"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073901502","display_name":"Roger Girgis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210124078","display_name":"Torc Robotics (United States)","ror":"https://ror.org/03233xn13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124078"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Girgis, Roger","raw_affiliation_strings":["Princeton University Torc Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University Torc Robotics","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I4210124078"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792178","display_name":"Anirudha Majumdar","orcid":"https://orcid.org/0009-0002-2296-7485","observed_orcids":["https://orcid.org/0009-0002-2296-7485","https://orcid.org/0000-0002-9383-6071"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210124078","display_name":"Torc Robotics (United States)","ror":"https://ror.org/03233xn13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124078"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Majumdar, Anirudha","raw_affiliation_strings":["Princeton University Torc Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University Torc Robotics","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I4210124078"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059313827","display_name":"Felix Heide","orcid":"https://orcid.org/0000-0002-8054-9823","observed_orcids":["https://orcid.org/0000-0002-8054-9823"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I4210124078","display_name":"Torc Robotics (United States)","ror":"https://ror.org/03233xn13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210124078"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heide, Felix","raw_affiliation_strings":["Princeton University Torc Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University Torc Robotics","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I4210124078"]}]}],"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":true,"cited_by_count":4,"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":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9887999892234802,"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":0.9887999892234802,"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":0.0012000000569969416,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.9890000224113464},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9580000042915344},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"commonsense reasoning","score":0.8700000047683716},{"id":"https://openalex.org/keywords/trajectory-planning","display_name":"trajectory planning","score":0.8360000252723694},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.8519999980926514},{"id":"https://openalex.org/keywords/latent-space-alignment","display_name":"latent space alignment","score":0.7459999918937683},{"id":"https://openalex.org/keywords/partial-observability","display_name":"partial observability","score":0.6050000190734863},{"id":"https://openalex.org/keywords/closed-loop-simulation","display_name":"closed-loop simulation","score":0.5450000166893005},{"id":"https://openalex.org/keywords/inference-efficiency","display_name":"inference efficiency","score":0.5130000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896999716758728},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.7124000191688538},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.711899995803833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6252999901771545},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6029000282287598},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.3546999990940094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.31540000438690186},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C3746660","wikidata":"https://www.wikidata.org/wiki/Q1068763","display_name":"Rule of inference","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.15925","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15925","pdf_url":"https://arxiv.org/pdf/2505.15925","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.15925","doi":"https://doi.org/10.48550/arxiv.2505.15925","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15925","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15925","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15925","pdf_url":"https://arxiv.org/pdf/2505.15925","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414580640.pdf","grobid_xml":"https://content.openalex.org/works/W4414580640.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414199098","https://openalex.org/W4405627552","https://openalex.org/W7167590541","https://openalex.org/W7172304960","https://openalex.org/W7137819507","https://openalex.org/W7134806863","https://openalex.org/W6910591108","https://openalex.org/W4417466207","https://openalex.org/W4393399197","https://openalex.org/W4416034787"],"abstract_inverted_index":{"While":[0],"autonomous":[1,97],"driving":[2,142,202],"(AD)":[3],"stacks":[4],"struggle":[5],"with":[6,27,137],"decision":[7],"making":[8],"under":[9],"partial":[10],"observability":[11],"and":[12,80,108,134,178,197],"real-world":[13],"complexity,":[14],"human":[15,48],"drivers":[16],"are":[17,58],"capable":[18],"of":[19,78,111,169],"applying":[20],"commonsense":[21,109],"reasoning":[22,106,143,189],"to":[23,34,46,61,160,192],"make":[24],"near-optimal":[25],"decisions":[26],"limited":[28],"information.":[29],"Recent":[30],"work":[31],"has":[32],"attempted":[33],"leverage":[35],"finetuned":[36],"Vision-Language":[37],"Models":[38],"(VLMs)":[39],"for":[40,96],"trajectory":[41],"planning":[42,135],"at":[43,68,130],"inference":[44,67,219],"time":[45],"emulate":[47],"behavior.":[49],"Despite":[50],"their":[51,81],"success":[52],"in":[53,151,175,194,204,213],"benchmark":[54],"evaluations,":[55],"these":[56],"methods":[57],"often":[59],"impractical":[60],"deploy":[62],"(a":[63],"70B":[64],"parameter":[65],"VLM":[66],"merely":[69],"8":[70],"tokens":[71],"per":[72],"second":[73],"requires":[74],"more":[75],"than":[76],"160G":[77],"memory),":[79],"monolithic":[82],"network":[83],"structure":[84],"prohibits":[85],"safety":[86],"decomposition.":[87],"To":[88],"bridge":[89],"this":[90],"gap,":[91],"we":[92],"propose":[93],"VLM-Embedded":[94],"Reasoning":[95],"DrIving":[98],"(VERDI),":[99],"a":[100,210],"training-time":[101],"framework":[102],"that":[103],"distills":[104],"the":[105,114,131,141,156,166,199,205],"process":[107,144],"knowledge":[110],"VLMs":[112],"into":[113],"AD":[115,123,158],"stack.":[116],"VERDI":[117,154,174],"augments":[118],"modular":[119,157],"differentiable":[120],"end-to-end":[121,185],"(e2e)":[122],"models":[124],"by":[125,146,190],"aligning":[126],"intermediate":[127],"module":[128],"outputs":[129],"perception,":[132],"prediction,":[133],"stages":[136],"text":[138],"features":[139],"explaining":[140],"produced":[145],"VLMs.":[147,171],"By":[148],"encouraging":[149],"alignment":[150],"latent":[152],"space,":[153],"enables":[155],"stack":[159],"internalize":[161],"structured":[162],"reasoning,":[163],"without":[164,187],"incurring":[165],"inference-time":[167],"costs":[168],"large":[170],"We":[172],"evaluate":[173],"both":[176],"open-loop":[177],"closed-loop":[179,206],"settings.":[180],"Our":[181],"method":[182],"outperforms":[183],"existing":[184],"approaches":[186],"embedded":[188],"up":[191],"11%":[193],"$\\ell_{2}$":[195],"distance,":[196],"achieves":[198],"best":[200],"overall":[201],"performance":[203],"HugSim":[207],"simulator,":[208],"including":[209],"10%":[211],"improvement":[212],"Non-Collision":[214],"Rate,":[215],"while":[216],"maintaining":[217],"fast":[218],"speed.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-10T00:00:00"}