{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CZWBDHE27W7XIZYKBJ6TMESKF2","short_pith_number":"pith:CZWBDHE2","schema_version":"1.0","canonical_sha256":"166c119c9afdbf74670a0a7d36124a2eb97b5225afa41653152e9842bcef9646","source":{"kind":"arxiv","id":"1901.07517","version":1},"attestation_state":"computed","paper":{"title":"Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jemin Hwangbo, Joonho Lee, Marco Hutter","submitted_at":"2019-01-22T18:45:42Z","abstract_excerpt":"The ability to recover from a fall is an essential feature for a legged robot to navigate in challenging environments robustly. Until today, there has been very little progress on this topic. Current solutions mostly build upon (heuristically) predefined trajectories, resulting in unnatural behaviors and requiring considerable effort in engineering system-specific components. In this paper, we present an approach based on model-free Deep Reinforcement Learning (RL) to control recovery maneuvers of quadrupedal robots using a hierarchical behavior-based controller. The controller consists of fou"},"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":"1901.07517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-01-22T18:45:42Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"d5ed1e4a04035bfb655eae7373e2c84ade943d17fbf7b7ceee3366f7917e3d8c","abstract_canon_sha256":"8e03c65d17134a990d56e9c60b6808c183cf766c7fd2d0086403912f9218aa68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:23.018802Z","signature_b64":"90n6J91bE9uxBhsbKpsNbo/a4X6muUJ0VGM62vnLeduIcx4lwhnmgGt5fsRnUD0PW8jcKowFxMRESwEQXngnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"166c119c9afdbf74670a0a7d36124a2eb97b5225afa41653152e9842bcef9646","last_reissued_at":"2026-07-05T09:51:23.018456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:23.018456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jemin Hwangbo, Joonho Lee, Marco Hutter","submitted_at":"2019-01-22T18:45:42Z","abstract_excerpt":"The ability to recover from a fall is an essential feature for a legged robot to navigate in challenging environments robustly. Until today, there has been very little progress on this topic. Current solutions mostly build upon (heuristically) predefined trajectories, resulting in unnatural behaviors and requiring considerable effort in engineering system-specific components. In this paper, we present an approach based on model-free Deep Reinforcement Learning (RL) to control recovery maneuvers of quadrupedal robots using a hierarchical behavior-based controller. The controller consists of fou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07517","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/1901.07517/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":"1901.07517","created_at":"2026-07-05T09:51:23.018513+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.07517v1","created_at":"2026-07-05T09:51:23.018513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07517","created_at":"2026-07-05T09:51:23.018513+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZWBDHE27W7X","created_at":"2026-07-05T09:51:23.018513+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZWBDHE27W7XIZYK","created_at":"2026-07-05T09:51:23.018513+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZWBDHE2","created_at":"2026-07-05T09:51:23.018513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08925","citing_title":"SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZWBDHE27W7XIZYKBJ6TMESKF2","json":"https://pith.science/pith/CZWBDHE27W7XIZYKBJ6TMESKF2.json","graph_json":"https://pith.science/api/pith-number/CZWBDHE27W7XIZYKBJ6TMESKF2/graph.json","events_json":"https://pith.science/api/pith-number/CZWBDHE27W7XIZYKBJ6TMESKF2/events.json","paper":"https://pith.science/paper/CZWBDHE2"},"agent_actions":{"view_html":"https://pith.science/pith/CZWBDHE27W7XIZYKBJ6TMESKF2","download_json":"https://pith.science/pith/CZWBDHE27W7XIZYKBJ6TMESKF2.json","view_paper":"https://pith.science/paper/CZWBDHE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.07517&json=true","fetch_graph":"https://pith.science/api/pith-number/CZWBDHE27W7XIZYKBJ6TMESKF2/graph.json","fetch_events":"https://pith.science/api/pith-number/CZWBDHE27W7XIZYKBJ6TMESKF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZWBDHE27W7XIZYKBJ6TMESKF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZWBDHE27W7XIZYKBJ6TMESKF2/action/storage_attestation","attest_author":"https://pith.science/pith/CZWBDHE27W7XIZYKBJ6TMESKF2/action/author_attestation","sign_citation":"https://pith.science/pith/CZWBDHE27W7XIZYKBJ6TMESKF2/action/citation_signature","submit_replication":"https://pith.science/pith/CZWBDHE27W7XIZYKBJ6TMESKF2/action/replication_record"}},"created_at":"2026-07-05T09:51:23.018513+00:00","updated_at":"2026-07-05T09:51:23.018513+00:00"}