{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NFDLMRXQFLJNRJEGWZV6FULLX4","short_pith_number":"pith:NFDLMRXQ","schema_version":"1.0","canonical_sha256":"6946b646f02ad2d8a486b66be2d16bbf11d093728da6fe6cf711f9e3758bb6ec","source":{"kind":"arxiv","id":"2504.00614","version":2},"attestation_state":"computed","paper":{"title":"Learning Bipedal Locomotion on Gear-Driven Humanoid Robot Using Foot-Mounted IMUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Masaya Kinoshita, Norio Nagatsuka, Sotaro Katayama, Yuta Koda","submitted_at":"2025-04-01T10:11:55Z","abstract_excerpt":"Sim-to-real reinforcement learning (RL) for humanoid robots with high-gear ratio actuators remains challenging due to complex actuator dynamics and the absence of torque sensors. To address this, we propose a novel RL framework leveraging foot-mounted inertial measurement units (IMUs). Instead of pursuing detailed actuator modeling and system identification, we utilize foot-mounted IMU measurements to enhance rapid stabilization capabilities over challenging terrains. Additionally, we propose symmetric data augmentation dedicated to the proposed observation space and random network distillatio"},"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":"2504.00614","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-01T10:11:55Z","cross_cats_sorted":[],"title_canon_sha256":"698912d96f9eacd0205fc60499459c5a26a6c25b5022f3847f75bfb315806fd8","abstract_canon_sha256":"a762eeded2107f7ab341a20786469e9fd5efd819fd0a28377744950fc297ed0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:37.740805Z","signature_b64":"5Ibhnw4Vqg7O7Jr6ksB9CAS50ZSViBYw/EbjhK4rdnRBNa+hZ+XhS/6r44ZARy406hxVoxfrM7jljBjVYXn1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6946b646f02ad2d8a486b66be2d16bbf11d093728da6fe6cf711f9e3758bb6ec","last_reissued_at":"2026-07-05T10:47:37.740299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:37.740299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Bipedal Locomotion on Gear-Driven Humanoid Robot Using Foot-Mounted IMUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Masaya Kinoshita, Norio Nagatsuka, Sotaro Katayama, Yuta Koda","submitted_at":"2025-04-01T10:11:55Z","abstract_excerpt":"Sim-to-real reinforcement learning (RL) for humanoid robots with high-gear ratio actuators remains challenging due to complex actuator dynamics and the absence of torque sensors. To address this, we propose a novel RL framework leveraging foot-mounted inertial measurement units (IMUs). Instead of pursuing detailed actuator modeling and system identification, we utilize foot-mounted IMU measurements to enhance rapid stabilization capabilities over challenging terrains. Additionally, we propose symmetric data augmentation dedicated to the proposed observation space and random network distillatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00614","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/2504.00614/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":"2504.00614","created_at":"2026-07-05T10:47:37.740367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00614v2","created_at":"2026-07-05T10:47:37.740367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00614","created_at":"2026-07-05T10:47:37.740367+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFDLMRXQFLJN","created_at":"2026-07-05T10:47:37.740367+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFDLMRXQFLJNRJEG","created_at":"2026-07-05T10:47:37.740367+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFDLMRXQ","created_at":"2026-07-05T10:47:37.740367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23445","citing_title":"Quantifying and Visualizing Sim-to-Real Gaps: Physics-Guided Regularization for Reproducibility","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFDLMRXQFLJNRJEGWZV6FULLX4","json":"https://pith.science/pith/NFDLMRXQFLJNRJEGWZV6FULLX4.json","graph_json":"https://pith.science/api/pith-number/NFDLMRXQFLJNRJEGWZV6FULLX4/graph.json","events_json":"https://pith.science/api/pith-number/NFDLMRXQFLJNRJEGWZV6FULLX4/events.json","paper":"https://pith.science/paper/NFDLMRXQ"},"agent_actions":{"view_html":"https://pith.science/pith/NFDLMRXQFLJNRJEGWZV6FULLX4","download_json":"https://pith.science/pith/NFDLMRXQFLJNRJEGWZV6FULLX4.json","view_paper":"https://pith.science/paper/NFDLMRXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00614&json=true","fetch_graph":"https://pith.science/api/pith-number/NFDLMRXQFLJNRJEGWZV6FULLX4/graph.json","fetch_events":"https://pith.science/api/pith-number/NFDLMRXQFLJNRJEGWZV6FULLX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFDLMRXQFLJNRJEGWZV6FULLX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFDLMRXQFLJNRJEGWZV6FULLX4/action/storage_attestation","attest_author":"https://pith.science/pith/NFDLMRXQFLJNRJEGWZV6FULLX4/action/author_attestation","sign_citation":"https://pith.science/pith/NFDLMRXQFLJNRJEGWZV6FULLX4/action/citation_signature","submit_replication":"https://pith.science/pith/NFDLMRXQFLJNRJEGWZV6FULLX4/action/replication_record"}},"created_at":"2026-07-05T10:47:37.740367+00:00","updated_at":"2026-07-05T10:47:37.740367+00:00"}