{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Z4OTZ6GOW2YIHVT2XV5P7BOMT4","short_pith_number":"pith:Z4OTZ6GO","schema_version":"1.0","canonical_sha256":"cf1d3cf8ceb6b083d67abd7aff85cc9f352869dffe4be7870bf934dddd167253","source":{"kind":"arxiv","id":"1904.11483","version":1},"attestation_state":"computed","paper":{"title":"Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alireza Nakhaei, Kikuo Fujimura, Maxime Bouton, Mykel J. Kochenderfer","submitted_at":"2019-04-25T17:52:28Z","abstract_excerpt":"Navigating urban environments represents a complex task for automated vehicles. They must reach their goal safely and efficiently while considering a multitude of traffic participants. We propose a modular decision making algorithm to autonomously navigate intersections, addressing challenges of existing rule-based and reinforcement learning (RL) approaches. We first present a safe RL algorithm relying on a model-checker to ensure safety guarantees. To make the decision strategy robust to perception errors and occlusions, we introduce a belief update technique using a learning based approach. "},"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":"1904.11483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-04-25T17:52:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"df00f16eb60c317817fb49a332c64ed6d9dbb3a3ffc9ad54d573bd90d6c5a895","abstract_canon_sha256":"75395365a08d9680141d4f3f236d47e3ceafe7ab0a5298a58e07d89cc3bdce57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:44.759923Z","signature_b64":"v+g1Y76+4+cd1DDOFPT4TDOUxYrqO+j8Ej7XKgQdhKJLOZfdgNZ3x+isIxYql7IBVr7RDnv+oFyPCVJe8iD0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf1d3cf8ceb6b083d67abd7aff85cc9f352869dffe4be7870bf934dddd167253","last_reissued_at":"2026-05-17T23:47:44.759337Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:44.759337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alireza Nakhaei, Kikuo Fujimura, Maxime Bouton, Mykel J. Kochenderfer","submitted_at":"2019-04-25T17:52:28Z","abstract_excerpt":"Navigating urban environments represents a complex task for automated vehicles. They must reach their goal safely and efficiently while considering a multitude of traffic participants. We propose a modular decision making algorithm to autonomously navigate intersections, addressing challenges of existing rule-based and reinforcement learning (RL) approaches. We first present a safe RL algorithm relying on a model-checker to ensure safety guarantees. To make the decision strategy robust to perception errors and occlusions, we introduce a belief update technique using a learning based approach. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11483","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":""},"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":"1904.11483","created_at":"2026-05-17T23:47:44.759425+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.11483v1","created_at":"2026-05-17T23:47:44.759425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11483","created_at":"2026-05-17T23:47:44.759425+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4OTZ6GOW2YI","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4OTZ6GOW2YIHVT2","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4OTZ6GO","created_at":"2026-05-18T12:33:33.725879+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/Z4OTZ6GOW2YIHVT2XV5P7BOMT4","json":"https://pith.science/pith/Z4OTZ6GOW2YIHVT2XV5P7BOMT4.json","graph_json":"https://pith.science/api/pith-number/Z4OTZ6GOW2YIHVT2XV5P7BOMT4/graph.json","events_json":"https://pith.science/api/pith-number/Z4OTZ6GOW2YIHVT2XV5P7BOMT4/events.json","paper":"https://pith.science/paper/Z4OTZ6GO"},"agent_actions":{"view_html":"https://pith.science/pith/Z4OTZ6GOW2YIHVT2XV5P7BOMT4","download_json":"https://pith.science/pith/Z4OTZ6GOW2YIHVT2XV5P7BOMT4.json","view_paper":"https://pith.science/paper/Z4OTZ6GO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.11483&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4OTZ6GOW2YIHVT2XV5P7BOMT4/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4OTZ6GOW2YIHVT2XV5P7BOMT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4OTZ6GOW2YIHVT2XV5P7BOMT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4OTZ6GOW2YIHVT2XV5P7BOMT4/action/storage_attestation","attest_author":"https://pith.science/pith/Z4OTZ6GOW2YIHVT2XV5P7BOMT4/action/author_attestation","sign_citation":"https://pith.science/pith/Z4OTZ6GOW2YIHVT2XV5P7BOMT4/action/citation_signature","submit_replication":"https://pith.science/pith/Z4OTZ6GOW2YIHVT2XV5P7BOMT4/action/replication_record"}},"created_at":"2026-05-17T23:47:44.759425+00:00","updated_at":"2026-05-17T23:47:44.759425+00:00"}