{"id":"https://openalex.org/W7135167717","doi":"https://doi.org/10.48550/arxiv.2603.11219","title":"Senna-2: Aligning VLM and End-to-End Driving Policy for Consistent Decision Making and Planning","display_name":"Senna-2: Aligning VLM and End-to-End Driving Policy for Consistent Decision Making and Planning","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135167717","doi":"https://doi.org/10.48550/arxiv.2603.11219"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.11219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11219","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.11219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111193633","display_name":"Yuehao Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Yuehao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128974506","display_name":"Shaoyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128939386","display_name":"Hao Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129031325","display_name":"Yifan Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087948841","display_name":"Weixiang Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue, Weixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101317824","display_name":"Jialv Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Jialv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129096308","display_name":"Bo Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042869521","display_name":"Zihao Lu","orcid":"https://orcid.org/0000-0002-6500-6732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Zihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129085428","display_name":"Yu Ting Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401608","display_name":"Qian Zhang","orcid":"https://orcid.org/0000-0002-0860-4023"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128957231","display_name":"Xinggang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xinggang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.632099986076355,"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":0.632099986076355,"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":0.10000000149011612,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06199999898672104,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/consistency","display_name":"Consistency (knowledge bases)","score":0.7215999960899353},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46549999713897705},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.3433000147342682},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.33059999346733093},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.30480000376701355},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.28349998593330383}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7215999960899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5730000138282776},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.41780000925064087},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2888999879360199},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C123587114","wikidata":"https://www.wikidata.org/wiki/Q2101508","display_name":"Policy analysis","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.11219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11219","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.11219","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11219","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[{"score":0.776838481426239,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"enhance":[3],"the":[4,22,36,42,55,72,89,113,119,124,127,135,152],"planning":[5],"capability":[6],"of":[7,54,115],"end-to-end":[8],"(E2E)":[9],"driving":[10,44,67,94,172],"policy":[11,68,111,129],"by":[12],"leveraging":[13],"high-level":[14,27],"semantic":[15],"reasoning.":[16],"However,":[17],"existing":[18],"approaches":[19],"often":[20],"overlook":[21],"dual-system":[23,163],"consistency":[24,164],"between":[25],"VLM's":[26],"decision":[28,104],"and":[29,51,78,100,126,154,169,180],"E2E's":[30],"low-level":[31],"planning.":[32,79],"As":[33],"a":[34,83,103],"result,":[35],"generated":[37],"trajectories":[38],"may":[39],"misalign":[40],"with":[41,102],"intended":[43],"decisions,":[45],"leading":[46],"to":[47,96,109,150],"weakened":[48],"top-down":[49],"guidance":[50],"decision-following":[52],"ability":[53],"system.":[56],"To":[57],"address":[58],"this":[59],"issue,":[60],"we":[61,92,122,138],"propose":[62],"Senna-2,":[63],"an":[64,131],"advanced":[65],"VLM-E2E":[66],"that":[69,159],"explicitly":[70],"aligns":[71],"two":[73],"systems":[74],"for":[75],"consistent":[76],"decision-making":[77,99],"Our":[80],"method":[81],"follows":[82],"consistency-oriented":[84],"three-stage":[85],"training":[86],"paradigm.":[87],"In":[88,118,134],"first":[90],"stage,":[91,121,137],"conduct":[93],"pre-training":[95],"achieve":[97],"preliminary":[98],"planning,":[101],"adapter":[105],"transmitting":[106],"VLM":[107,125],"decisions":[108],"E2E":[110,128],"in":[112,130,147,174],"form":[114],"implicit":[116],"embeddings.":[117],"second":[120],"align":[123],"open-loop":[132,176],"setting.":[133],"third":[136],"perform":[139],"closed-loop":[140,181],"alignment":[141],"via":[142],"bottom-up":[143],"Hierarchical":[144],"Reinforcement":[145],"Learning":[146],"3DGS":[148],"environments":[149],"reinforce":[151],"safety":[153,173],"efficiency.":[155],"Extensive":[156],"experiments":[157],"demonstrate":[158],"Senna-2":[160],"achieves":[161],"superior":[162],"(19.3%":[165],"F1":[166],"score":[167],"improvement)":[168],"significantly":[170],"enhances":[171],"both":[175],"(5.7%":[177],"FDE":[178],"reduction)":[179],"settings":[182],"(30.6%":[183],"AF-CR":[184],"reduction).":[185]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-14T00:00:00"}