{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HNCKRJFCAI7U2HTKPQMKXO3XWK","short_pith_number":"pith:HNCKRJFC","schema_version":"1.0","canonical_sha256":"3b44a8a4a2023f4d1e6a7c18abbb77b2a4cf66fe57412743766e677a31da8ae2","source":{"kind":"arxiv","id":"2503.01125","version":4},"attestation_state":"computed","paper":{"title":"TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Canlun Zheng, Shiliang Guo, Shiyu Zhao, Zhikun Wang, Zikang Yin","submitted_at":"2025-03-03T03:11:50Z","abstract_excerpt":"Although acrobatic flight control has been studied extensively, one key limitation of the existing methods is that they are usually restricted to specific maneuver tasks and cannot change flight pattern parameters online. In this work, we propose a target-and-command-oriented reinforcement learning (TACO) framework, which can handle different maneuver tasks in a unified way and allows online parameter changes. Additionally, we propose a spectral normalization method with input-output rescaling to enhance the policy's temporal and spatial smoothness, independence, and symmetry, thereby overcomi"},"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":"2503.01125","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-03T03:11:50Z","cross_cats_sorted":[],"title_canon_sha256":"c6fa08dbaaea6b0a53c6bafc7486626a962d79d9edc274e79a47e5e826965afd","abstract_canon_sha256":"39d3234c0dddbb3cd559264eb98089b290e162ca0da6f8acccf5b97f499b4349"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:17.977404Z","signature_b64":"thm+HE5ElZXdhlp7DoR8OT34Y1pJgAZaLEqUaw6Frg3s6ocxlO5vglP1C4RRNp4M6HH7O57NF2w0QOLLxLf9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b44a8a4a2023f4d1e6a7c18abbb77b2a4cf66fe57412743766e677a31da8ae2","last_reissued_at":"2026-05-20T00:00:17.976629Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:17.976629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Canlun Zheng, Shiliang Guo, Shiyu Zhao, Zhikun Wang, Zikang Yin","submitted_at":"2025-03-03T03:11:50Z","abstract_excerpt":"Although acrobatic flight control has been studied extensively, one key limitation of the existing methods is that they are usually restricted to specific maneuver tasks and cannot change flight pattern parameters online. In this work, we propose a target-and-command-oriented reinforcement learning (TACO) framework, which can handle different maneuver tasks in a unified way and allows online parameter changes. Additionally, we propose a spectral normalization method with input-output rescaling to enhance the policy's temporal and spatial smoothness, independence, and symmetry, thereby overcomi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01125","kind":"arxiv","version":4},"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/2503.01125/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":"2503.01125","created_at":"2026-05-20T00:00:17.976763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01125v4","created_at":"2026-05-20T00:00:17.976763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01125","created_at":"2026-05-20T00:00:17.976763+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNCKRJFCAI7U","created_at":"2026-05-20T00:00:17.976763+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNCKRJFCAI7U2HTK","created_at":"2026-05-20T00:00:17.976763+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNCKRJFC","created_at":"2026-05-20T00:00:17.976763+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/HNCKRJFCAI7U2HTKPQMKXO3XWK","json":"https://pith.science/pith/HNCKRJFCAI7U2HTKPQMKXO3XWK.json","graph_json":"https://pith.science/api/pith-number/HNCKRJFCAI7U2HTKPQMKXO3XWK/graph.json","events_json":"https://pith.science/api/pith-number/HNCKRJFCAI7U2HTKPQMKXO3XWK/events.json","paper":"https://pith.science/paper/HNCKRJFC"},"agent_actions":{"view_html":"https://pith.science/pith/HNCKRJFCAI7U2HTKPQMKXO3XWK","download_json":"https://pith.science/pith/HNCKRJFCAI7U2HTKPQMKXO3XWK.json","view_paper":"https://pith.science/paper/HNCKRJFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01125&json=true","fetch_graph":"https://pith.science/api/pith-number/HNCKRJFCAI7U2HTKPQMKXO3XWK/graph.json","fetch_events":"https://pith.science/api/pith-number/HNCKRJFCAI7U2HTKPQMKXO3XWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNCKRJFCAI7U2HTKPQMKXO3XWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNCKRJFCAI7U2HTKPQMKXO3XWK/action/storage_attestation","attest_author":"https://pith.science/pith/HNCKRJFCAI7U2HTKPQMKXO3XWK/action/author_attestation","sign_citation":"https://pith.science/pith/HNCKRJFCAI7U2HTKPQMKXO3XWK/action/citation_signature","submit_replication":"https://pith.science/pith/HNCKRJFCAI7U2HTKPQMKXO3XWK/action/replication_record"}},"created_at":"2026-05-20T00:00:17.976763+00:00","updated_at":"2026-05-20T00:00:17.976763+00:00"}