{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SPD7NZXQ2LUUBSYRP7FCULXMK2","short_pith_number":"pith:SPD7NZXQ","schema_version":"1.0","canonical_sha256":"93c7f6e6f0d2e940cb117fca2a2eec568cf55c88895a532bc82d4eaa71d61eed","source":{"kind":"arxiv","id":"2409.15780","version":4},"attestation_state":"computed","paper":{"title":"A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gijeong Kim, Hae-Won Park, Yong-Hoon Lee","submitted_at":"2024-09-24T06:22:28Z","abstract_excerpt":"This work introduces a model-free reinforcement learning framework that enables various modes of motion (quadruped, tripod, or biped) and diverse tasks for legged robot locomotion. We employ a motion-style reward based on a relaxed logarithmic barrier function as a soft constraint, to bias the learning process toward the desired motion style, such as gait, foot clearance, joint position, or body height. The predefined gait cycle is encoded in a flexible manner, facilitating gait adjustments throughout the learning process. Extensive experiments demonstrate that KAIST HOUND, a 45 kg robotic sys"},"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":"2409.15780","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-24T06:22:28Z","cross_cats_sorted":[],"title_canon_sha256":"596a6598205b7acbdafc58ef761a555d99a6d4528cc3080f61d911481e2e67cb","abstract_canon_sha256":"646868e298d8aaf7b071061fcd737104b45f5923733ebf179dd2e21c78be8984"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:39.172989Z","signature_b64":"SBzbyL04Mxr6LiXn+V8u1mhQRubvu3oi2uDOwnPSFNUNlCLQ1GZ8QIrcwaakIxfF5e9KG6uR8rg0luo4719dDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93c7f6e6f0d2e940cb117fca2a2eec568cf55c88895a532bc82d4eaa71d61eed","last_reissued_at":"2026-07-05T11:00:39.172468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:39.172468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gijeong Kim, Hae-Won Park, Yong-Hoon Lee","submitted_at":"2024-09-24T06:22:28Z","abstract_excerpt":"This work introduces a model-free reinforcement learning framework that enables various modes of motion (quadruped, tripod, or biped) and diverse tasks for legged robot locomotion. We employ a motion-style reward based on a relaxed logarithmic barrier function as a soft constraint, to bias the learning process toward the desired motion style, such as gait, foot clearance, joint position, or body height. The predefined gait cycle is encoded in a flexible manner, facilitating gait adjustments throughout the learning process. Extensive experiments demonstrate that KAIST HOUND, a 45 kg robotic sys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15780","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/2409.15780/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":"2409.15780","created_at":"2026-07-05T11:00:39.172530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15780v4","created_at":"2026-07-05T11:00:39.172530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15780","created_at":"2026-07-05T11:00:39.172530+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPD7NZXQ2LUU","created_at":"2026-07-05T11:00:39.172530+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPD7NZXQ2LUUBSYR","created_at":"2026-07-05T11:00:39.172530+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPD7NZXQ","created_at":"2026-07-05T11:00:39.172530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12222","citing_title":"Learning Impact-Rich Rotational Maneuvers via Centroidal Velocity Rewards and Sim-to-Real Techniques: A One-Leg Hopper Flip Case Study","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SPD7NZXQ2LUUBSYRP7FCULXMK2","json":"https://pith.science/pith/SPD7NZXQ2LUUBSYRP7FCULXMK2.json","graph_json":"https://pith.science/api/pith-number/SPD7NZXQ2LUUBSYRP7FCULXMK2/graph.json","events_json":"https://pith.science/api/pith-number/SPD7NZXQ2LUUBSYRP7FCULXMK2/events.json","paper":"https://pith.science/paper/SPD7NZXQ"},"agent_actions":{"view_html":"https://pith.science/pith/SPD7NZXQ2LUUBSYRP7FCULXMK2","download_json":"https://pith.science/pith/SPD7NZXQ2LUUBSYRP7FCULXMK2.json","view_paper":"https://pith.science/paper/SPD7NZXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15780&json=true","fetch_graph":"https://pith.science/api/pith-number/SPD7NZXQ2LUUBSYRP7FCULXMK2/graph.json","fetch_events":"https://pith.science/api/pith-number/SPD7NZXQ2LUUBSYRP7FCULXMK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPD7NZXQ2LUUBSYRP7FCULXMK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPD7NZXQ2LUUBSYRP7FCULXMK2/action/storage_attestation","attest_author":"https://pith.science/pith/SPD7NZXQ2LUUBSYRP7FCULXMK2/action/author_attestation","sign_citation":"https://pith.science/pith/SPD7NZXQ2LUUBSYRP7FCULXMK2/action/citation_signature","submit_replication":"https://pith.science/pith/SPD7NZXQ2LUUBSYRP7FCULXMK2/action/replication_record"}},"created_at":"2026-07-05T11:00:39.172530+00:00","updated_at":"2026-07-05T11:00:39.172530+00:00"}