{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2TZRMTGUCTVNGLA2OADGAXTTQC","short_pith_number":"pith:2TZRMTGU","schema_version":"1.0","canonical_sha256":"d4f3164cd414ead32c1a7006605e7380960014e650bec35cde3d09679d770a31","source":{"kind":"arxiv","id":"2408.04821","version":2},"attestation_state":"computed","paper":{"title":"VLM-MPC: Vision Language Foundation Model (VLM)-Guided Model Predictive Controller (MPC) for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haotian Shi, Jiaxi Liu, Keke Long, Xiaopeng Li","submitted_at":"2024-08-09T02:27:25Z","abstract_excerpt":"Motivated by the emergent reasoning capabilities of Vision Language Models (VLMs) and their potential to improve the comprehensibility of autonomous driving systems, this paper introduces a closed-loop autonomous driving controller called VLM-MPC, which combines the Model Predictive Controller (MPC) with VLM to evaluate how model-based control could enhance VLM decision-making. The proposed VLM-MPC is structured into two asynchronous components: The upper layer VLM generates driving parameters (e.g., desired speed, desired headway) for lower-level control based on front camera images, ego vehi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.04821","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-09T02:27:25Z","cross_cats_sorted":[],"title_canon_sha256":"4bd01a1ec357519561debfe6e9fa95ddeba0ef105d8358535b6bd0ce53ff70df","abstract_canon_sha256":"6d2e33fee44111498eaf43d0b5e967d66aec6944673b8b10f4af7e9cd4d4993c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:55.089243Z","signature_b64":"kDFL8ZuCe6mk3W67irCBV6BmjMbgyQ4FAPzpttIH4HpCs7OLXxpt6PDbY+jrB9qB7pfrBzv36Vq1uDfiljRzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4f3164cd414ead32c1a7006605e7380960014e650bec35cde3d09679d770a31","last_reissued_at":"2026-07-05T09:14:55.088756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:55.088756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM-MPC: Vision Language Foundation Model (VLM)-Guided Model Predictive Controller (MPC) for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haotian Shi, Jiaxi Liu, Keke Long, Xiaopeng Li","submitted_at":"2024-08-09T02:27:25Z","abstract_excerpt":"Motivated by the emergent reasoning capabilities of Vision Language Models (VLMs) and their potential to improve the comprehensibility of autonomous driving systems, this paper introduces a closed-loop autonomous driving controller called VLM-MPC, which combines the Model Predictive Controller (MPC) with VLM to evaluate how model-based control could enhance VLM decision-making. The proposed VLM-MPC is structured into two asynchronous components: The upper layer VLM generates driving parameters (e.g., desired speed, desired headway) for lower-level control based on front camera images, ego vehi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04821","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.04821/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.04821","created_at":"2026-07-05T09:14:55.088814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04821v2","created_at":"2026-07-05T09:14:55.088814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04821","created_at":"2026-07-05T09:14:55.088814+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TZRMTGUCTVN","created_at":"2026-07-05T09:14:55.088814+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TZRMTGUCTVNGLA2","created_at":"2026-07-05T09:14:55.088814+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TZRMTGU","created_at":"2026-07-05T09:14:55.088814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18074","citing_title":"4DLidarOpen: An Open 4D FMCW Lidar Dataset for Motion-Aware Autonomous Driving","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2TZRMTGUCTVNGLA2OADGAXTTQC","json":"https://pith.science/pith/2TZRMTGUCTVNGLA2OADGAXTTQC.json","graph_json":"https://pith.science/api/pith-number/2TZRMTGUCTVNGLA2OADGAXTTQC/graph.json","events_json":"https://pith.science/api/pith-number/2TZRMTGUCTVNGLA2OADGAXTTQC/events.json","paper":"https://pith.science/paper/2TZRMTGU"},"agent_actions":{"view_html":"https://pith.science/pith/2TZRMTGUCTVNGLA2OADGAXTTQC","download_json":"https://pith.science/pith/2TZRMTGUCTVNGLA2OADGAXTTQC.json","view_paper":"https://pith.science/paper/2TZRMTGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04821&json=true","fetch_graph":"https://pith.science/api/pith-number/2TZRMTGUCTVNGLA2OADGAXTTQC/graph.json","fetch_events":"https://pith.science/api/pith-number/2TZRMTGUCTVNGLA2OADGAXTTQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TZRMTGUCTVNGLA2OADGAXTTQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TZRMTGUCTVNGLA2OADGAXTTQC/action/storage_attestation","attest_author":"https://pith.science/pith/2TZRMTGUCTVNGLA2OADGAXTTQC/action/author_attestation","sign_citation":"https://pith.science/pith/2TZRMTGUCTVNGLA2OADGAXTTQC/action/citation_signature","submit_replication":"https://pith.science/pith/2TZRMTGUCTVNGLA2OADGAXTTQC/action/replication_record"}},"created_at":"2026-07-05T09:14:55.088814+00:00","updated_at":"2026-07-05T09:14:55.088814+00:00"}