{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZUYRKJVZ2N3KFV5SDXSURIYN2Y","short_pith_number":"pith:ZUYRKJVZ","schema_version":"1.0","canonical_sha256":"cd311526b9d376a2d7b21de548a30dd62c4d03a1251bdb0af05c884e25309071","source":{"kind":"arxiv","id":"2403.06524","version":2},"attestation_state":"computed","paper":{"title":"Tactical Decision Making for Autonomous Trucks by Deep Reinforcement Learning with Total Cost of Operation Based Reward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Deepthi Pathare, Leo Laine, Morteza Haghir Chehreghani","submitted_at":"2024-03-11T08:58:42Z","abstract_excerpt":"We develop a deep reinforcement learning framework for tactical decision making in an autonomous truck, specifically for Adaptive Cruise Control (ACC) and lane change maneuvers in a highway scenario. Our results demonstrate that it is beneficial to separate high-level decision-making processes and low-level control actions between the reinforcement learning agent and the low-level controllers based on physical models. In the following, we study optimizing the performance with a realistic and multi-objective reward function based on Total Cost of Operation (TCOP) of the truck using different ap"},"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":"2403.06524","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T08:58:42Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"a19b1f7bb9408c5eac683dc972a6dcacfd27cd71bbf1586b740198c32394517d","abstract_canon_sha256":"c591dcfd4933c4a72c9ad623501eb8c5726f7cdc1ba869ce4de7d97b2c612e16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:44.783940Z","signature_b64":"pQRL5KJN8VQsxgI6dC7jbR2d9USvF9nJk0f3UD1Y4VzPgZ7Xg53I1JvRyg9UGizcMtEfuvhUPAGLpITImIK2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd311526b9d376a2d7b21de548a30dd62c4d03a1251bdb0af05c884e25309071","last_reissued_at":"2026-06-02T02:04:44.783460Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:44.783460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tactical Decision Making for Autonomous Trucks by Deep Reinforcement Learning with Total Cost of Operation Based Reward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Deepthi Pathare, Leo Laine, Morteza Haghir Chehreghani","submitted_at":"2024-03-11T08:58:42Z","abstract_excerpt":"We develop a deep reinforcement learning framework for tactical decision making in an autonomous truck, specifically for Adaptive Cruise Control (ACC) and lane change maneuvers in a highway scenario. Our results demonstrate that it is beneficial to separate high-level decision-making processes and low-level control actions between the reinforcement learning agent and the low-level controllers based on physical models. In the following, we study optimizing the performance with a realistic and multi-objective reward function based on Total Cost of Operation (TCOP) of the truck using different ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06524","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/2403.06524/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":"2403.06524","created_at":"2026-06-02T02:04:44.783530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06524v2","created_at":"2026-06-02T02:04:44.783530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06524","created_at":"2026-06-02T02:04:44.783530+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUYRKJVZ2N3K","created_at":"2026-06-02T02:04:44.783530+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUYRKJVZ2N3KFV5S","created_at":"2026-06-02T02:04:44.783530+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUYRKJVZ","created_at":"2026-06-02T02:04:44.783530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16858","citing_title":"Pedestrian-Aware LLM-Driven Behavioral Planning for Autonomous Vehicles","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUYRKJVZ2N3KFV5SDXSURIYN2Y","json":"https://pith.science/pith/ZUYRKJVZ2N3KFV5SDXSURIYN2Y.json","graph_json":"https://pith.science/api/pith-number/ZUYRKJVZ2N3KFV5SDXSURIYN2Y/graph.json","events_json":"https://pith.science/api/pith-number/ZUYRKJVZ2N3KFV5SDXSURIYN2Y/events.json","paper":"https://pith.science/paper/ZUYRKJVZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZUYRKJVZ2N3KFV5SDXSURIYN2Y","download_json":"https://pith.science/pith/ZUYRKJVZ2N3KFV5SDXSURIYN2Y.json","view_paper":"https://pith.science/paper/ZUYRKJVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06524&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUYRKJVZ2N3KFV5SDXSURIYN2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUYRKJVZ2N3KFV5SDXSURIYN2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUYRKJVZ2N3KFV5SDXSURIYN2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUYRKJVZ2N3KFV5SDXSURIYN2Y/action/storage_attestation","attest_author":"https://pith.science/pith/ZUYRKJVZ2N3KFV5SDXSURIYN2Y/action/author_attestation","sign_citation":"https://pith.science/pith/ZUYRKJVZ2N3KFV5SDXSURIYN2Y/action/citation_signature","submit_replication":"https://pith.science/pith/ZUYRKJVZ2N3KFV5SDXSURIYN2Y/action/replication_record"}},"created_at":"2026-06-02T02:04:44.783530+00:00","updated_at":"2026-06-02T02:04:44.783530+00:00"}