{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LU3DCVIUWX5S6TTJSMSNCGOJ63","short_pith_number":"pith:LU3DCVIU","schema_version":"1.0","canonical_sha256":"5d36315514b5fb2f4e699324d119c9f6c643b3289764f10860a7209909e958c8","source":{"kind":"arxiv","id":"2309.15442","version":1},"attestation_state":"computed","paper":{"title":"Template Model Inspired Task Space Learning for Robust Bipedal Locomotion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ayonga Hereid, Bowen Weng, Guillermo A. Castillo, Shunpeng Yang, Wei Zhang","submitted_at":"2023-09-27T07:06:02Z","abstract_excerpt":"This work presents a hierarchical framework for bipedal locomotion that combines a Reinforcement Learning (RL)-based high-level (HL) planner policy for the online generation of task space commands with a model-based low-level (LL) controller to track the desired task space trajectories. Different from traditional end-to-end learning approaches, our HL policy takes insights from the angular momentum-based linear inverted pendulum (ALIP) to carefully design the observation and action spaces of the Markov Decision Process (MDP). This simple yet effective design creates an insightful mapping betwe"},"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":"2309.15442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-27T07:06:02Z","cross_cats_sorted":[],"title_canon_sha256":"8c40a0273baa17a53618a47a60b3ad4d9ffda5e2f305e189d3ebd2f3a5811d43","abstract_canon_sha256":"5c2c7b349e8dd6c40c0cf7c6b74cab2f3cc95a864ac6dd666a19c3d1df0f0118"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:45.925566Z","signature_b64":"8X1tL2AvmlwpdRzZq9VVQmxgF91/mU55K9mqnm3+ElJ9heEC9d9N/xrREkYMWDLIfpIf/WuceQ2hoocofF46Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d36315514b5fb2f4e699324d119c9f6c643b3289764f10860a7209909e958c8","last_reissued_at":"2026-07-05T06:54:45.925075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:45.925075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Template Model Inspired Task Space Learning for Robust Bipedal Locomotion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ayonga Hereid, Bowen Weng, Guillermo A. Castillo, Shunpeng Yang, Wei Zhang","submitted_at":"2023-09-27T07:06:02Z","abstract_excerpt":"This work presents a hierarchical framework for bipedal locomotion that combines a Reinforcement Learning (RL)-based high-level (HL) planner policy for the online generation of task space commands with a model-based low-level (LL) controller to track the desired task space trajectories. Different from traditional end-to-end learning approaches, our HL policy takes insights from the angular momentum-based linear inverted pendulum (ALIP) to carefully design the observation and action spaces of the Markov Decision Process (MDP). This simple yet effective design creates an insightful mapping betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15442","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/2309.15442/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":"2309.15442","created_at":"2026-07-05T06:54:45.925131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15442v1","created_at":"2026-07-05T06:54:45.925131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15442","created_at":"2026-07-05T06:54:45.925131+00:00"},{"alias_kind":"pith_short_12","alias_value":"LU3DCVIUWX5S","created_at":"2026-07-05T06:54:45.925131+00:00"},{"alias_kind":"pith_short_16","alias_value":"LU3DCVIUWX5S6TTJ","created_at":"2026-07-05T06:54:45.925131+00:00"},{"alias_kind":"pith_short_8","alias_value":"LU3DCVIU","created_at":"2026-07-05T06:54:45.925131+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LU3DCVIUWX5S6TTJSMSNCGOJ63","json":"https://pith.science/pith/LU3DCVIUWX5S6TTJSMSNCGOJ63.json","graph_json":"https://pith.science/api/pith-number/LU3DCVIUWX5S6TTJSMSNCGOJ63/graph.json","events_json":"https://pith.science/api/pith-number/LU3DCVIUWX5S6TTJSMSNCGOJ63/events.json","paper":"https://pith.science/paper/LU3DCVIU"},"agent_actions":{"view_html":"https://pith.science/pith/LU3DCVIUWX5S6TTJSMSNCGOJ63","download_json":"https://pith.science/pith/LU3DCVIUWX5S6TTJSMSNCGOJ63.json","view_paper":"https://pith.science/paper/LU3DCVIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15442&json=true","fetch_graph":"https://pith.science/api/pith-number/LU3DCVIUWX5S6TTJSMSNCGOJ63/graph.json","fetch_events":"https://pith.science/api/pith-number/LU3DCVIUWX5S6TTJSMSNCGOJ63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LU3DCVIUWX5S6TTJSMSNCGOJ63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LU3DCVIUWX5S6TTJSMSNCGOJ63/action/storage_attestation","attest_author":"https://pith.science/pith/LU3DCVIUWX5S6TTJSMSNCGOJ63/action/author_attestation","sign_citation":"https://pith.science/pith/LU3DCVIUWX5S6TTJSMSNCGOJ63/action/citation_signature","submit_replication":"https://pith.science/pith/LU3DCVIUWX5S6TTJSMSNCGOJ63/action/replication_record"}},"created_at":"2026-07-05T06:54:45.925131+00:00","updated_at":"2026-07-05T06:54:45.925131+00:00"}