{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G7KKMBNGRFQM7X5VLH3IRVQLAY","short_pith_number":"pith:G7KKMBNG","schema_version":"1.0","canonical_sha256":"37d4a605a68960cfdfb559f688d60b062c21aa89e90533927c8571bc25b2f50c","source":{"kind":"arxiv","id":"2406.06978","version":4},"attestation_state":"computed","paper":{"title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Hydra-MDP trains an end-to-end planner by distilling knowledge from both human demonstrations and rule-based experts into a multi-head decoder that outputs diverse trajectories.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jan Kautz, Jose M. Alvarez, Kailin Li, Shihao Wang, Shiyi Lan, Yishen Ji, Yu-Gang Jiang, Zhenxin Li, Zhiding Yu, Zhiqi Li, Ziyue Zhu, Zuxuan Wu","submitted_at":"2024-06-11T06:18:26Z","abstract_excerpt":"We propose Hydra-MDP, a novel paradigm employing multiple teachers in a teacher-student model. This approach uses knowledge distillation from both human and rule-based teachers to train the student model, which features a multi-head decoder to learn diverse trajectory candidates tailored to various evaluation metrics. With the knowledge of rule-based teachers, Hydra-MDP learns how the environment influences the planning in an end-to-end manner instead of resorting to non-differentiable post-processing. This method achieves the $1^{st}$ place in the Navsim challenge, demonstrating significant i"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2406.06978","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T06:18:26Z","cross_cats_sorted":[],"title_canon_sha256":"bfc3f6c68a9e2b362c4e80b0e33a14901356db046042ed1ac0bb4b097b81116e","abstract_canon_sha256":"96d6a7a8343c519df05069304470aab8a6f9c4b32489e818f8e558a24f651279"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:50:37.321499Z","signature_b64":"GONj9MhQjiTvl6BrmyMCA0wDSux/YUXhR4bjG+xi3UuQudkbwYos1K2VPELDuUvThu1hlIi4ukfZyQkutQJ6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37d4a605a68960cfdfb559f688d60b062c21aa89e90533927c8571bc25b2f50c","last_reissued_at":"2026-05-18T03:50:37.320811Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:50:37.320811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Hydra-MDP trains an end-to-end planner by distilling knowledge from both human demonstrations and rule-based experts into a multi-head decoder that outputs diverse trajectories.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jan Kautz, Jose M. Alvarez, Kailin Li, Shihao Wang, Shiyi Lan, Yishen Ji, Yu-Gang Jiang, Zhenxin Li, Zhiding Yu, Zhiqi Li, Ziyue Zhu, Zuxuan Wu","submitted_at":"2024-06-11T06:18:26Z","abstract_excerpt":"We propose Hydra-MDP, a novel paradigm employing multiple teachers in a teacher-student model. This approach uses knowledge distillation from both human and rule-based teachers to train the student model, which features a multi-head decoder to learn diverse trajectory candidates tailored to various evaluation metrics. With the knowledge of rule-based teachers, Hydra-MDP learns how the environment influences the planning in an end-to-end manner instead of resorting to non-differentiable post-processing. This method achieves the $1^{st}$ place in the Navsim challenge, demonstrating significant i"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This method achieves the 1st place in the Navsim challenge, demonstrating significant improvements in generalization across diverse driving environments and conditions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The multi-head decoder can simultaneously absorb conflicting signals from human and rule-based teachers without mode collapse or degraded performance on any single metric.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Hydra-MDP uses multi-teacher distillation and a multi-head decoder to learn diverse, metric-specific trajectories in an end-to-end autonomous-driving planner, winning the Navsim challenge.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Hydra-MDP trains an end-to-end planner by distilling knowledge from both human demonstrations and rule-based experts into a multi-head decoder that outputs diverse trajectories.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"de0c17d258b240ad85c5a3c16695a2db5e4cfb1acc8ecbb1ce5a4525f905cc2b"},"source":{"id":"2406.06978","kind":"arxiv","version":4},"verdict":{"id":"8a072b7e-d671-4586-894f-e8acd65f7dfd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T23:08:25.962349Z","strongest_claim":"This method achieves the 1st place in the Navsim challenge, demonstrating significant improvements in generalization across diverse driving environments and conditions.","one_line_summary":"Hydra-MDP uses multi-teacher distillation and a multi-head decoder to learn diverse, metric-specific trajectories in an end-to-end autonomous-driving planner, winning the Navsim challenge.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The multi-head decoder can simultaneously absorb conflicting signals from human and rule-based teachers without mode collapse or degraded performance on any single metric.","pith_extraction_headline":"Hydra-MDP trains an end-to-end planner by distilling knowledge from both human demonstrations and rule-based experts into a multi-head decoder that outputs diverse trajectories."},"references":{"count":19,"sample":[{"doi":"","year":2024,"title":"Quad: Query-based in- terpretable neural motion planning for autonomous driving","work_id":"1a045cde-fbd3-4c5d-a59a-342f16668d6a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","work_id":"b16aace6-deff-4546-b333-bcb7c9c07cdb","ref_index":3,"cited_arxiv_id":"2106.11810","is_internal_anchor":true},{"doi":"","year":null,"title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","work_id":"e7670f83-e1e1-41e7-86eb-39477a3a10b2","ref_index":4,"cited_arxiv_id":"2402.13243","is_internal_anchor":true},{"doi":"","year":2022,"title":"Transfuser: Imita- tion with transformer-based sensor fusion for autonomous driving","work_id":"8b9d9ecc-fbc9-4be4-88eb-e6170c75b588","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Navsim: Data-driven non-reactive autonomous vehicle simulation","work_id":"ab2ad404-1d69-4f8c-bf71-ceae9114f626","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":19,"snapshot_sha256":"8c42e9a988fece09949b512fd17a08917c7b60c5907f38794a4ae7d315b9a618","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c62df76cd2204039c5969cebd20513310a5be001de94ef67328d611a0164f5b7"},"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":"2406.06978","created_at":"2026-05-18T03:50:37.320907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06978v4","created_at":"2026-05-18T03:50:37.320907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06978","created_at":"2026-05-18T03:50:37.320907+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7KKMBNGRFQM","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7KKMBNGRFQM7X5V","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7KKMBNG","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":41,"internal_anchor_count":41,"sample":[{"citing_arxiv_id":"2605.21139","citing_title":"Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2602.22801","citing_title":"Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21032","citing_title":"Towards Physically Consistent 4D Scene Reconstruction for Closed-loop Autonomous Driving Simulation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21061","citing_title":"Grounding Driving VLA via Inverse Kinematics","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21139","citing_title":"Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08830","citing_title":"VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15120","citing_title":"CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18059","citing_title":"Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19771","citing_title":"Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19631","citing_title":"HEAT: Heterogeneous End-to-End Autonomous Driving via Trajectory-Guided World Models","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16737","citing_title":"DriveSafer: End-to-End Autonomous Driving with Safety Guidance","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2507.04049","citing_title":"DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2507.17596","citing_title":"PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2511.23369","citing_title":"SimScale: Learning to Drive via Real-World Simulation at Scale","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2512.18662","citing_title":"Pseudo-Expert Regularized Offline RL for End-to-End Autonomous Driving in Photorealistic Closed-Loop Environments","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2603.13842","citing_title":"Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2603.19675","citing_title":"DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2506.13757","citing_title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10426","citing_title":"CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00813","citing_title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02714","citing_title":"ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11550","citing_title":"The DAWN of World-Action Interactive Models","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04647","citing_title":"ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving","ref_index":113,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08713","citing_title":"REAP: Reinforcement-Learning End-to-End Autonomous Parking with Gaussian Splatting Simulator for Real2Sim2Real Transfer","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08830","citing_title":"VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7KKMBNGRFQM7X5VLH3IRVQLAY","json":"https://pith.science/pith/G7KKMBNGRFQM7X5VLH3IRVQLAY.json","graph_json":"https://pith.science/api/pith-number/G7KKMBNGRFQM7X5VLH3IRVQLAY/graph.json","events_json":"https://pith.science/api/pith-number/G7KKMBNGRFQM7X5VLH3IRVQLAY/events.json","paper":"https://pith.science/paper/G7KKMBNG"},"agent_actions":{"view_html":"https://pith.science/pith/G7KKMBNGRFQM7X5VLH3IRVQLAY","download_json":"https://pith.science/pith/G7KKMBNGRFQM7X5VLH3IRVQLAY.json","view_paper":"https://pith.science/paper/G7KKMBNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06978&json=true","fetch_graph":"https://pith.science/api/pith-number/G7KKMBNGRFQM7X5VLH3IRVQLAY/graph.json","fetch_events":"https://pith.science/api/pith-number/G7KKMBNGRFQM7X5VLH3IRVQLAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7KKMBNGRFQM7X5VLH3IRVQLAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7KKMBNGRFQM7X5VLH3IRVQLAY/action/storage_attestation","attest_author":"https://pith.science/pith/G7KKMBNGRFQM7X5VLH3IRVQLAY/action/author_attestation","sign_citation":"https://pith.science/pith/G7KKMBNGRFQM7X5VLH3IRVQLAY/action/citation_signature","submit_replication":"https://pith.science/pith/G7KKMBNGRFQM7X5VLH3IRVQLAY/action/replication_record"}},"created_at":"2026-05-18T03:50:37.320907+00:00","updated_at":"2026-05-18T03:50:37.320907+00:00"}