{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UHJXI3KD5USFBIBWOPFZYEF4KJ","short_pith_number":"pith:UHJXI3KD","schema_version":"1.0","canonical_sha256":"a1d3746d43ed2450a03673cb9c10bc5264fb732318e59eb6318e0b67bc24ef93","source":{"kind":"arxiv","id":"2308.15808","version":2},"attestation_state":"computed","paper":{"title":"Learning the References of Online Model Predictive Control for Urban Self-Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hakim Ghazzai, Jun Ma, Yubin Wang, Yulin Li, Yusen Xie, Zengqi Peng","submitted_at":"2023-08-30T07:23:37Z","abstract_excerpt":"In this work, we propose a novel learning-based model predictive control (MPC) framework for motion planning and control of urban self-driving. In this framework, instantaneous references and cost functions of online MPC are learned from raw sensor data without relying on any oracle or predicted states of traffic. Moreover, driving safety conditions are latently encoded via the introduction of a learnable instantaneous reference vector. In particular, we implement a deep reinforcement learning (DRL) framework for policy search, where practical and lightweight raw observations are processed to "},"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":"2308.15808","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-08-30T07:23:37Z","cross_cats_sorted":[],"title_canon_sha256":"2bab6eee451ac6c09245611e3a402ea731fda8e88f790205a02b78a96275d30a","abstract_canon_sha256":"3739d3658645c6dca646d18e44823110705b5f08cab50bb74da0fc5deef6237e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:03.188246Z","signature_b64":"gFT5aNeClVbgLtbDDWX6njbct7I3CHmDDb+o/UA7kFNWMW5lunVB3y1OS90IupIipgkr89aPOcQATdRts3yPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1d3746d43ed2450a03673cb9c10bc5264fb732318e59eb6318e0b67bc24ef93","last_reissued_at":"2026-07-05T07:50:03.187768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:03.187768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning the References of Online Model Predictive Control for Urban Self-Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hakim Ghazzai, Jun Ma, Yubin Wang, Yulin Li, Yusen Xie, Zengqi Peng","submitted_at":"2023-08-30T07:23:37Z","abstract_excerpt":"In this work, we propose a novel learning-based model predictive control (MPC) framework for motion planning and control of urban self-driving. In this framework, instantaneous references and cost functions of online MPC are learned from raw sensor data without relying on any oracle or predicted states of traffic. Moreover, driving safety conditions are latently encoded via the introduction of a learnable instantaneous reference vector. In particular, we implement a deep reinforcement learning (DRL) framework for policy search, where practical and lightweight raw observations are processed to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15808","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/2308.15808/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":"2308.15808","created_at":"2026-07-05T07:50:03.187837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15808v2","created_at":"2026-07-05T07:50:03.187837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15808","created_at":"2026-07-05T07:50:03.187837+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHJXI3KD5USF","created_at":"2026-07-05T07:50:03.187837+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHJXI3KD5USFBIBW","created_at":"2026-07-05T07:50:03.187837+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHJXI3KD","created_at":"2026-07-05T07:50:03.187837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.17091","citing_title":"Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHJXI3KD5USFBIBWOPFZYEF4KJ","json":"https://pith.science/pith/UHJXI3KD5USFBIBWOPFZYEF4KJ.json","graph_json":"https://pith.science/api/pith-number/UHJXI3KD5USFBIBWOPFZYEF4KJ/graph.json","events_json":"https://pith.science/api/pith-number/UHJXI3KD5USFBIBWOPFZYEF4KJ/events.json","paper":"https://pith.science/paper/UHJXI3KD"},"agent_actions":{"view_html":"https://pith.science/pith/UHJXI3KD5USFBIBWOPFZYEF4KJ","download_json":"https://pith.science/pith/UHJXI3KD5USFBIBWOPFZYEF4KJ.json","view_paper":"https://pith.science/paper/UHJXI3KD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15808&json=true","fetch_graph":"https://pith.science/api/pith-number/UHJXI3KD5USFBIBWOPFZYEF4KJ/graph.json","fetch_events":"https://pith.science/api/pith-number/UHJXI3KD5USFBIBWOPFZYEF4KJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHJXI3KD5USFBIBWOPFZYEF4KJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHJXI3KD5USFBIBWOPFZYEF4KJ/action/storage_attestation","attest_author":"https://pith.science/pith/UHJXI3KD5USFBIBWOPFZYEF4KJ/action/author_attestation","sign_citation":"https://pith.science/pith/UHJXI3KD5USFBIBWOPFZYEF4KJ/action/citation_signature","submit_replication":"https://pith.science/pith/UHJXI3KD5USFBIBWOPFZYEF4KJ/action/replication_record"}},"created_at":"2026-07-05T07:50:03.187837+00:00","updated_at":"2026-07-05T07:50:03.187837+00:00"}