{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PQT4RJ2O3LLFPENA3QNKYTH7NB","short_pith_number":"pith:PQT4RJ2O","schema_version":"1.0","canonical_sha256":"7c27c8a74edad65791a0dc1aac4cff68559b3d24ca06b76b4f1175dc4033492a","source":{"kind":"arxiv","id":"2605.16015","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dileep Kalathil, Moble Benedict, Sushil Vemuri, Vishnu Saj","submitted_at":"2026-05-15T14:49:58Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) for quadrotor flight control typically relies on Domain Randomization (DR) for sim-to-real transfer, resulting in overly conservative policies that struggle with dynamic disturbances. To overcome this, we propose a novel adaptive control architecture that actively perceives and reacts to instantaneous perturbations. First, we train an optimal outer-loop policy, then replace its reliance on ground-truth disturbance data with a Residual Dynamics Predictor (RDP). The RDP estimates the external forces and moments acting on the aircraft in flight online using only "},"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":"2605.16015","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-15T14:49:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"840d94fad42191de577a879d32e129118def77d642634c7ea03066efd838ecd0","abstract_canon_sha256":"b1c7285d23af9f1ceb13af5b8ec832fdb485d68ec2e5ddacee59f9e02d6db3c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:48.004309Z","signature_b64":"52l8q+RNjFAWdTz62GqWL2LgFg0X15wlSxEgfIlg8BpYFn6rJxbIIwE3nuGJi/hQWrfvTvINIEHYKxy2YAE6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c27c8a74edad65791a0dc1aac4cff68559b3d24ca06b76b4f1175dc4033492a","last_reissued_at":"2026-05-20T00:05:48.003653Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:48.003653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dileep Kalathil, Moble Benedict, Sushil Vemuri, Vishnu Saj","submitted_at":"2026-05-15T14:49:58Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) for quadrotor flight control typically relies on Domain Randomization (DR) for sim-to-real transfer, resulting in overly conservative policies that struggle with dynamic disturbances. To overcome this, we propose a novel adaptive control architecture that actively perceives and reacts to instantaneous perturbations. First, we train an optimal outer-loop policy, then replace its reliance on ground-truth disturbance data with a Residual Dynamics Predictor (RDP). The RDP estimates the external forces and moments acting on the aircraft in flight online using only "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16015","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/2605.16015/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":"2605.16015","created_at":"2026-05-20T00:05:48.003756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16015v2","created_at":"2026-05-20T00:05:48.003756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16015","created_at":"2026-05-20T00:05:48.003756+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQT4RJ2O3LLF","created_at":"2026-05-20T00:05:48.003756+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQT4RJ2O3LLFPENA","created_at":"2026-05-20T00:05:48.003756+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQT4RJ2O","created_at":"2026-05-20T00:05:48.003756+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/PQT4RJ2O3LLFPENA3QNKYTH7NB","json":"https://pith.science/pith/PQT4RJ2O3LLFPENA3QNKYTH7NB.json","graph_json":"https://pith.science/api/pith-number/PQT4RJ2O3LLFPENA3QNKYTH7NB/graph.json","events_json":"https://pith.science/api/pith-number/PQT4RJ2O3LLFPENA3QNKYTH7NB/events.json","paper":"https://pith.science/paper/PQT4RJ2O"},"agent_actions":{"view_html":"https://pith.science/pith/PQT4RJ2O3LLFPENA3QNKYTH7NB","download_json":"https://pith.science/pith/PQT4RJ2O3LLFPENA3QNKYTH7NB.json","view_paper":"https://pith.science/paper/PQT4RJ2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16015&json=true","fetch_graph":"https://pith.science/api/pith-number/PQT4RJ2O3LLFPENA3QNKYTH7NB/graph.json","fetch_events":"https://pith.science/api/pith-number/PQT4RJ2O3LLFPENA3QNKYTH7NB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQT4RJ2O3LLFPENA3QNKYTH7NB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQT4RJ2O3LLFPENA3QNKYTH7NB/action/storage_attestation","attest_author":"https://pith.science/pith/PQT4RJ2O3LLFPENA3QNKYTH7NB/action/author_attestation","sign_citation":"https://pith.science/pith/PQT4RJ2O3LLFPENA3QNKYTH7NB/action/citation_signature","submit_replication":"https://pith.science/pith/PQT4RJ2O3LLFPENA3QNKYTH7NB/action/replication_record"}},"created_at":"2026-05-20T00:05:48.003756+00:00","updated_at":"2026-05-20T00:05:48.003756+00:00"}