{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TU2LZSMYU7X4WUQ4ZOF2KCV73C","short_pith_number":"pith:TU2LZSMY","schema_version":"1.0","canonical_sha256":"9d34bcc998a7efcb521ccb8ba50abfd8a2ddb6dc73859e6f8e26e7124035c5dd","source":{"kind":"arxiv","id":"2008.02521","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning based Local Planner for UAV Obstacle Avoidance using Demonstration Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bifeng Song, James F. Whidborne, Lei He, Nabil Aouf","submitted_at":"2020-08-06T08:43:36Z","abstract_excerpt":"In this paper, a deep reinforcement learning (DRL) method is proposed to address the problem of UAV navigation in an unknown environment. However, DRL algorithms are limited by the data efficiency problem as they typically require a huge amount of data before they reach a reasonable performance. To speed up the DRL training process, we developed a novel learning framework which combines imitation learning and reinforcement learning and building upon Twin Delayed DDPG (TD3) algorithm. We newly introduced both policy and Q-value network are learned using the expert demonstration during the imita"},"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":"2008.02521","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-08-06T08:43:36Z","cross_cats_sorted":[],"title_canon_sha256":"ab2e13b99f3d3f1447f1d3b492fdac88e4d835f602a024dadb3019bb3563c0b6","abstract_canon_sha256":"10b8a9c352e83d019988d4cb095901b5ac008677837f2bcfa4137d915d0bc9b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:14.620114Z","signature_b64":"6rND5P4xtdqVwBjWzs7K7q34Z/qkJJhjMl3nb+jV1V7zoE/z60HAfVL8NTVR+Ow7H2BX7xUUhBqRUKsq0wP+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d34bcc998a7efcb521ccb8ba50abfd8a2ddb6dc73859e6f8e26e7124035c5dd","last_reissued_at":"2026-07-05T01:25:14.619646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:14.619646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning based Local Planner for UAV Obstacle Avoidance using Demonstration Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bifeng Song, James F. Whidborne, Lei He, Nabil Aouf","submitted_at":"2020-08-06T08:43:36Z","abstract_excerpt":"In this paper, a deep reinforcement learning (DRL) method is proposed to address the problem of UAV navigation in an unknown environment. However, DRL algorithms are limited by the data efficiency problem as they typically require a huge amount of data before they reach a reasonable performance. To speed up the DRL training process, we developed a novel learning framework which combines imitation learning and reinforcement learning and building upon Twin Delayed DDPG (TD3) algorithm. We newly introduced both policy and Q-value network are learned using the expert demonstration during the imita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02521","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/2008.02521/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":"2008.02521","created_at":"2026-07-05T01:25:14.619697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.02521v1","created_at":"2026-07-05T01:25:14.619697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02521","created_at":"2026-07-05T01:25:14.619697+00:00"},{"alias_kind":"pith_short_12","alias_value":"TU2LZSMYU7X4","created_at":"2026-07-05T01:25:14.619697+00:00"},{"alias_kind":"pith_short_16","alias_value":"TU2LZSMYU7X4WUQ4","created_at":"2026-07-05T01:25:14.619697+00:00"},{"alias_kind":"pith_short_8","alias_value":"TU2LZSMY","created_at":"2026-07-05T01:25:14.619697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07855","citing_title":"Path Planning Using Deep Deterministic Policy Gradient: A Reinforcement Learning Approach","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TU2LZSMYU7X4WUQ4ZOF2KCV73C","json":"https://pith.science/pith/TU2LZSMYU7X4WUQ4ZOF2KCV73C.json","graph_json":"https://pith.science/api/pith-number/TU2LZSMYU7X4WUQ4ZOF2KCV73C/graph.json","events_json":"https://pith.science/api/pith-number/TU2LZSMYU7X4WUQ4ZOF2KCV73C/events.json","paper":"https://pith.science/paper/TU2LZSMY"},"agent_actions":{"view_html":"https://pith.science/pith/TU2LZSMYU7X4WUQ4ZOF2KCV73C","download_json":"https://pith.science/pith/TU2LZSMYU7X4WUQ4ZOF2KCV73C.json","view_paper":"https://pith.science/paper/TU2LZSMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.02521&json=true","fetch_graph":"https://pith.science/api/pith-number/TU2LZSMYU7X4WUQ4ZOF2KCV73C/graph.json","fetch_events":"https://pith.science/api/pith-number/TU2LZSMYU7X4WUQ4ZOF2KCV73C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TU2LZSMYU7X4WUQ4ZOF2KCV73C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TU2LZSMYU7X4WUQ4ZOF2KCV73C/action/storage_attestation","attest_author":"https://pith.science/pith/TU2LZSMYU7X4WUQ4ZOF2KCV73C/action/author_attestation","sign_citation":"https://pith.science/pith/TU2LZSMYU7X4WUQ4ZOF2KCV73C/action/citation_signature","submit_replication":"https://pith.science/pith/TU2LZSMYU7X4WUQ4ZOF2KCV73C/action/replication_record"}},"created_at":"2026-07-05T01:25:14.619697+00:00","updated_at":"2026-07-05T01:25:14.619697+00:00"}