{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZZUNDYQLKKK3G4QN6CZPRVDIZR","short_pith_number":"pith:ZZUNDYQL","schema_version":"1.0","canonical_sha256":"ce68d1e20b5295b3720df0b2f8d468cc5259473309a50f03e7e71dbb4ba2aabe","source":{"kind":"arxiv","id":"2206.03004","version":1},"attestation_state":"computed","paper":{"title":"Driving in Real Life with Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Bo Yang, Caglayan Dicle, Eric M. Wolff, Forbes Howington, Francisco Suarez-Ruiz, Momchil S. Tomov, Nanxiang Li, Robert Beaudoin, Sammy Omari, Samuel Findler, Sang Uk Lee, Ting-Sheng Chu, Tung Phan-Minh","submitted_at":"2022-06-07T04:36:46Z","abstract_excerpt":"In this paper, we introduce the first learning-based planner to drive a car in dense, urban traffic using Inverse Reinforcement Learning (IRL). Our planner, DriveIRL, generates a diverse set of trajectory proposals, filters these trajectories with a lightweight and interpretable safety filter, and then uses a learned model to score each remaining trajectory. The best trajectory is then tracked by the low-level controller of our self-driving vehicle. We train our trajectory scoring model on a 500+ hour real-world dataset of expert driving demonstrations in Las Vegas within the maximum entropy 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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.03004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-06-07T04:36:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bd037e353af45ed998191732d034072ce391de690d9bc7cfaee6f73b84504840","abstract_canon_sha256":"1c24c543fdc9cf184c3a48209568f8e269c721273419556ecb0c1e5a76dc8ffa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:38.107012Z","signature_b64":"qOuKAaAEecKIqXFi0pmP0ZlGfEyVDJ0y5COX4dKgyXT1fzrIShxUZw0n1tLOdtQqm+E8FOxKRXUH0uGWB6biAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce68d1e20b5295b3720df0b2f8d468cc5259473309a50f03e7e71dbb4ba2aabe","last_reissued_at":"2026-07-05T04:29:38.106520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:38.106520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Driving in Real Life with Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Bo Yang, Caglayan Dicle, Eric M. Wolff, Forbes Howington, Francisco Suarez-Ruiz, Momchil S. Tomov, Nanxiang Li, Robert Beaudoin, Sammy Omari, Samuel Findler, Sang Uk Lee, Ting-Sheng Chu, Tung Phan-Minh","submitted_at":"2022-06-07T04:36:46Z","abstract_excerpt":"In this paper, we introduce the first learning-based planner to drive a car in dense, urban traffic using Inverse Reinforcement Learning (IRL). Our planner, DriveIRL, generates a diverse set of trajectory proposals, filters these trajectories with a lightweight and interpretable safety filter, and then uses a learned model to score each remaining trajectory. The best trajectory is then tracked by the low-level controller of our self-driving vehicle. We train our trajectory scoring model on a 500+ hour real-world dataset of expert driving demonstrations in Las Vegas within the maximum entropy I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03004","kind":"arxiv","version":1},"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/2206.03004/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":"2206.03004","created_at":"2026-07-05T04:29:38.106584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.03004v1","created_at":"2026-07-05T04:29:38.106584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03004","created_at":"2026-07-05T04:29:38.106584+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZUNDYQLKKK3","created_at":"2026-07-05T04:29:38.106584+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZUNDYQLKKK3G4QN","created_at":"2026-07-05T04:29:38.106584+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZUNDYQL","created_at":"2026-07-05T04:29:38.106584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZZUNDYQLKKK3G4QN6CZPRVDIZR","json":"https://pith.science/pith/ZZUNDYQLKKK3G4QN6CZPRVDIZR.json","graph_json":"https://pith.science/api/pith-number/ZZUNDYQLKKK3G4QN6CZPRVDIZR/graph.json","events_json":"https://pith.science/api/pith-number/ZZUNDYQLKKK3G4QN6CZPRVDIZR/events.json","paper":"https://pith.science/paper/ZZUNDYQL"},"agent_actions":{"view_html":"https://pith.science/pith/ZZUNDYQLKKK3G4QN6CZPRVDIZR","download_json":"https://pith.science/pith/ZZUNDYQLKKK3G4QN6CZPRVDIZR.json","view_paper":"https://pith.science/paper/ZZUNDYQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.03004&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZUNDYQLKKK3G4QN6CZPRVDIZR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZUNDYQLKKK3G4QN6CZPRVDIZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZUNDYQLKKK3G4QN6CZPRVDIZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZUNDYQLKKK3G4QN6CZPRVDIZR/action/storage_attestation","attest_author":"https://pith.science/pith/ZZUNDYQLKKK3G4QN6CZPRVDIZR/action/author_attestation","sign_citation":"https://pith.science/pith/ZZUNDYQLKKK3G4QN6CZPRVDIZR/action/citation_signature","submit_replication":"https://pith.science/pith/ZZUNDYQLKKK3G4QN6CZPRVDIZR/action/replication_record"}},"created_at":"2026-07-05T04:29:38.106584+00:00","updated_at":"2026-07-05T04:29:38.106584+00:00"}