{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MJBGIKZPJDMIHXMKF7QHQOUZ24","short_pith_number":"pith:MJBGIKZP","schema_version":"1.0","canonical_sha256":"6242642b2f48d883dd8a2fe0783a99d7035564feab467dc5fe29b06e0e7cc968","source":{"kind":"arxiv","id":"2108.02665","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for Continuous Docking Control of Autonomous Underwater Vehicles: A Benchmarking Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bilal Wehbe, Matias Valdenegro-Toro, Mihir Patil","submitted_at":"2021-08-05T14:58:05Z","abstract_excerpt":"Docking control of an autonomous underwater vehicle (AUV) is a task that is integral to achieving persistent long term autonomy. This work explores the application of state-of-the-art model-free deep reinforcement learning (DRL) approaches to the task of AUV docking in the continuous domain. We provide a detailed formulation of the reward function, utilized to successfully dock the AUV onto a fixed docking platform. A major contribution that distinguishes our work from the previous approaches is the usage of a physics simulator to define and simulate the underwater environment as well as the D"},"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":"2108.02665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-08-05T14:58:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2f568287ace0a2704a59d71d3769e6e0b3fce061a343d9d332a5a2b84d81cd6a","abstract_canon_sha256":"e10b1803f24064b30a1497304eb35308a226dcdd5768718cbe281157710ec9dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:35.157001Z","signature_b64":"T6u+CyRaBU7G8XKmJWPU1g1ytDGxPx3y2S4iD8Hq/gPZq21lPUgg/mP4QVXcK9BgKvacj4fw3TAggAhSaNilAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6242642b2f48d883dd8a2fe0783a99d7035564feab467dc5fe29b06e0e7cc968","last_reissued_at":"2026-07-05T03:03:35.156624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:35.156624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Continuous Docking Control of Autonomous Underwater Vehicles: A Benchmarking Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Bilal Wehbe, Matias Valdenegro-Toro, Mihir Patil","submitted_at":"2021-08-05T14:58:05Z","abstract_excerpt":"Docking control of an autonomous underwater vehicle (AUV) is a task that is integral to achieving persistent long term autonomy. This work explores the application of state-of-the-art model-free deep reinforcement learning (DRL) approaches to the task of AUV docking in the continuous domain. We provide a detailed formulation of the reward function, utilized to successfully dock the AUV onto a fixed docking platform. A major contribution that distinguishes our work from the previous approaches is the usage of a physics simulator to define and simulate the underwater environment as well as the D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02665","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/2108.02665/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":"2108.02665","created_at":"2026-07-05T03:03:35.156689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.02665v1","created_at":"2026-07-05T03:03:35.156689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02665","created_at":"2026-07-05T03:03:35.156689+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJBGIKZPJDMI","created_at":"2026-07-05T03:03:35.156689+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJBGIKZPJDMIHXMK","created_at":"2026-07-05T03:03:35.156689+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJBGIKZP","created_at":"2026-07-05T03:03:35.156689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17823","citing_title":"Learning to Dock: A Simulation-based Study on Closing the Sim2Real Gap in Autonomous Underwater Docking","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MJBGIKZPJDMIHXMKF7QHQOUZ24","json":"https://pith.science/pith/MJBGIKZPJDMIHXMKF7QHQOUZ24.json","graph_json":"https://pith.science/api/pith-number/MJBGIKZPJDMIHXMKF7QHQOUZ24/graph.json","events_json":"https://pith.science/api/pith-number/MJBGIKZPJDMIHXMKF7QHQOUZ24/events.json","paper":"https://pith.science/paper/MJBGIKZP"},"agent_actions":{"view_html":"https://pith.science/pith/MJBGIKZPJDMIHXMKF7QHQOUZ24","download_json":"https://pith.science/pith/MJBGIKZPJDMIHXMKF7QHQOUZ24.json","view_paper":"https://pith.science/paper/MJBGIKZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.02665&json=true","fetch_graph":"https://pith.science/api/pith-number/MJBGIKZPJDMIHXMKF7QHQOUZ24/graph.json","fetch_events":"https://pith.science/api/pith-number/MJBGIKZPJDMIHXMKF7QHQOUZ24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJBGIKZPJDMIHXMKF7QHQOUZ24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJBGIKZPJDMIHXMKF7QHQOUZ24/action/storage_attestation","attest_author":"https://pith.science/pith/MJBGIKZPJDMIHXMKF7QHQOUZ24/action/author_attestation","sign_citation":"https://pith.science/pith/MJBGIKZPJDMIHXMKF7QHQOUZ24/action/citation_signature","submit_replication":"https://pith.science/pith/MJBGIKZPJDMIHXMKF7QHQOUZ24/action/replication_record"}},"created_at":"2026-07-05T03:03:35.156689+00:00","updated_at":"2026-07-05T03:03:35.156689+00:00"}