{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VWXOJSHMIOS7SYXFJWO4QF3BZL","short_pith_number":"pith:VWXOJSHM","schema_version":"1.0","canonical_sha256":"adaee4c8ec43a5f962e54d9dc81761caf58ff0940efeae5a146b25c2723e2a7d","source":{"kind":"arxiv","id":"2011.04752","version":1},"attestation_state":"computed","paper":{"title":"Trajectory Planning for Autonomous Vehicles Using Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"John M. Dolan, Kaleb Ben Naveed, Zhiqian Qiao","submitted_at":"2020-11-09T20:49:54Z","abstract_excerpt":"Planning safe trajectories under uncertain and dynamic conditions makes the autonomous driving problem significantly complex. Current sampling-based methods such as Rapidly Exploring Random Trees (RRTs) are not ideal for this problem because of the high computational cost. Supervised learning methods such as Imitation Learning lack generalization and safety guarantees. To address these problems and in order to ensure a robust framework, we propose a Hierarchical Reinforcement Learning (HRL) structure combined with a Proportional-Integral-Derivative (PID) controller for trajectory planning. HRL"},"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":"2011.04752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-09T20:49:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5cac32a938376d3462db9d6df163b247f42cee3f82cdd271e0f1f98226501d6","abstract_canon_sha256":"90bf5087b7ec5908a82ebb726d31383196f1a93c99f0abe893b91bed150a8ffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:39.970540Z","signature_b64":"Ys9OfXI/rPEEQY+LUuJ2HBDVkN/dPqIKLuGeupSByVoSnT/LvJfa598SzrgpGgUtQWRAHW4uw30CdZZ+32GYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adaee4c8ec43a5f962e54d9dc81761caf58ff0940efeae5a146b25c2723e2a7d","last_reissued_at":"2026-07-05T01:50:39.970097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:39.970097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trajectory Planning for Autonomous Vehicles Using Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"John M. Dolan, Kaleb Ben Naveed, Zhiqian Qiao","submitted_at":"2020-11-09T20:49:54Z","abstract_excerpt":"Planning safe trajectories under uncertain and dynamic conditions makes the autonomous driving problem significantly complex. Current sampling-based methods such as Rapidly Exploring Random Trees (RRTs) are not ideal for this problem because of the high computational cost. Supervised learning methods such as Imitation Learning lack generalization and safety guarantees. To address these problems and in order to ensure a robust framework, we propose a Hierarchical Reinforcement Learning (HRL) structure combined with a Proportional-Integral-Derivative (PID) controller for trajectory planning. HRL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04752","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/2011.04752/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":"2011.04752","created_at":"2026-07-05T01:50:39.970151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.04752v1","created_at":"2026-07-05T01:50:39.970151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04752","created_at":"2026-07-05T01:50:39.970151+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWXOJSHMIOS7","created_at":"2026-07-05T01:50:39.970151+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWXOJSHMIOS7SYXF","created_at":"2026-07-05T01:50:39.970151+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWXOJSHM","created_at":"2026-07-05T01:50:39.970151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08221","citing_title":"A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator","ref_index":122,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWXOJSHMIOS7SYXFJWO4QF3BZL","json":"https://pith.science/pith/VWXOJSHMIOS7SYXFJWO4QF3BZL.json","graph_json":"https://pith.science/api/pith-number/VWXOJSHMIOS7SYXFJWO4QF3BZL/graph.json","events_json":"https://pith.science/api/pith-number/VWXOJSHMIOS7SYXFJWO4QF3BZL/events.json","paper":"https://pith.science/paper/VWXOJSHM"},"agent_actions":{"view_html":"https://pith.science/pith/VWXOJSHMIOS7SYXFJWO4QF3BZL","download_json":"https://pith.science/pith/VWXOJSHMIOS7SYXFJWO4QF3BZL.json","view_paper":"https://pith.science/paper/VWXOJSHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.04752&json=true","fetch_graph":"https://pith.science/api/pith-number/VWXOJSHMIOS7SYXFJWO4QF3BZL/graph.json","fetch_events":"https://pith.science/api/pith-number/VWXOJSHMIOS7SYXFJWO4QF3BZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWXOJSHMIOS7SYXFJWO4QF3BZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWXOJSHMIOS7SYXFJWO4QF3BZL/action/storage_attestation","attest_author":"https://pith.science/pith/VWXOJSHMIOS7SYXFJWO4QF3BZL/action/author_attestation","sign_citation":"https://pith.science/pith/VWXOJSHMIOS7SYXFJWO4QF3BZL/action/citation_signature","submit_replication":"https://pith.science/pith/VWXOJSHMIOS7SYXFJWO4QF3BZL/action/replication_record"}},"created_at":"2026-07-05T01:50:39.970151+00:00","updated_at":"2026-07-05T01:50:39.970151+00:00"}