{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WC62WIACSQ7ECXXEM6C7ENAZPV","short_pith_number":"pith:WC62WIAC","schema_version":"1.0","canonical_sha256":"b0bdab2002943e415ee46785f234197d780615c83f1ef3f312677bf3cd994f51","source":{"kind":"arxiv","id":"2407.10353","version":1},"attestation_state":"computed","paper":{"title":"UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Huy Ha, Jie Tan, Shuran Song, Yihuai Gao, Zipeng Fu","submitted_at":"2024-07-14T23:03:23Z","abstract_excerpt":"We introduce UMI-on-Legs, a new framework that combines real-world and simulation data for quadruped manipulation systems. We scale task-centric data collection in the real world using a hand-held gripper (UMI), providing a cheap way to demonstrate task-relevant manipulation skills without a robot. Simultaneously, we scale robot-centric data in simulation by training whole-body controller for task-tracking without task simulation setups. The interface between these two policies is end-effector trajectories in the task frame, inferred by the manipulation policy and passed to the whole-body cont"},"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":"2407.10353","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-14T23:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"f56641bc1adfe455ceafa47233eb295c040a3cbf74644305d7e61e51f923fbf0","abstract_canon_sha256":"e9ce6189ec555765f800b7e20f6290c6adac44d524de069b4cb4028bc6df1e5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:58.606666Z","signature_b64":"+dB/fLmmxk7CyE4zx6nO+871JAr99AwuZYB6GZgOwXVOgJQWEKMI0FC+tY6YwtgZo+GVlS/XtbZLK1I43cSlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0bdab2002943e415ee46785f234197d780615c83f1ef3f312677bf3cd994f51","last_reissued_at":"2026-07-05T08:43:58.606234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:58.606234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Huy Ha, Jie Tan, Shuran Song, Yihuai Gao, Zipeng Fu","submitted_at":"2024-07-14T23:03:23Z","abstract_excerpt":"We introduce UMI-on-Legs, a new framework that combines real-world and simulation data for quadruped manipulation systems. We scale task-centric data collection in the real world using a hand-held gripper (UMI), providing a cheap way to demonstrate task-relevant manipulation skills without a robot. Simultaneously, we scale robot-centric data in simulation by training whole-body controller for task-tracking without task simulation setups. The interface between these two policies is end-effector trajectories in the task frame, inferred by the manipulation policy and passed to the whole-body cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10353","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/2407.10353/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":"2407.10353","created_at":"2026-07-05T08:43:58.606296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10353v1","created_at":"2026-07-05T08:43:58.606296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10353","created_at":"2026-07-05T08:43:58.606296+00:00"},{"alias_kind":"pith_short_12","alias_value":"WC62WIACSQ7E","created_at":"2026-07-05T08:43:58.606296+00:00"},{"alias_kind":"pith_short_16","alias_value":"WC62WIACSQ7ECXXE","created_at":"2026-07-05T08:43:58.606296+00:00"},{"alias_kind":"pith_short_8","alias_value":"WC62WIAC","created_at":"2026-07-05T08:43:58.606296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24466","citing_title":"FT-WBC: Learning Fault-Tolerant Whole-Body Control for Legged Loco-Manipulation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24208","citing_title":"Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12965","citing_title":"EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24466","citing_title":"FT-WBC: Learning Fault-Tolerant Whole-Body Control for Legged Loco-Manipulation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17300","citing_title":"HCLM: A Hierarchical Framework for Cooperative Loco-Manipulation with Dual Quadrupeds","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08547","citing_title":"R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11218","citing_title":"Humanoid Whole-Body Badminton via Multi-Stage Reinforcement Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05855","citing_title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":160,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03452","citing_title":"BifrostUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27224","citing_title":"Learning Tactile-Aware Quadrupedal Loco-Manipulation Policies","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27224","citing_title":"Learning Tactile-Aware Quadrupedal Loco-Manipulation Policies","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00078","citing_title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14089","citing_title":"UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13001","citing_title":"XRZero-G0: Pushing the Frontier of Dexterous Robotic Manipulation with Interfaces, Quality and Ratios","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07335","citing_title":"TAMEn: Tactile-Aware Manipulation Engine for Closed-Loop Data Collection in Contact-Rich Tasks","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WC62WIACSQ7ECXXEM6C7ENAZPV","json":"https://pith.science/pith/WC62WIACSQ7ECXXEM6C7ENAZPV.json","graph_json":"https://pith.science/api/pith-number/WC62WIACSQ7ECXXEM6C7ENAZPV/graph.json","events_json":"https://pith.science/api/pith-number/WC62WIACSQ7ECXXEM6C7ENAZPV/events.json","paper":"https://pith.science/paper/WC62WIAC"},"agent_actions":{"view_html":"https://pith.science/pith/WC62WIACSQ7ECXXEM6C7ENAZPV","download_json":"https://pith.science/pith/WC62WIACSQ7ECXXEM6C7ENAZPV.json","view_paper":"https://pith.science/paper/WC62WIAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10353&json=true","fetch_graph":"https://pith.science/api/pith-number/WC62WIACSQ7ECXXEM6C7ENAZPV/graph.json","fetch_events":"https://pith.science/api/pith-number/WC62WIACSQ7ECXXEM6C7ENAZPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WC62WIACSQ7ECXXEM6C7ENAZPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WC62WIACSQ7ECXXEM6C7ENAZPV/action/storage_attestation","attest_author":"https://pith.science/pith/WC62WIACSQ7ECXXEM6C7ENAZPV/action/author_attestation","sign_citation":"https://pith.science/pith/WC62WIACSQ7ECXXEM6C7ENAZPV/action/citation_signature","submit_replication":"https://pith.science/pith/WC62WIACSQ7ECXXEM6C7ENAZPV/action/replication_record"}},"created_at":"2026-07-05T08:43:58.606296+00:00","updated_at":"2026-07-05T08:43:58.606296+00:00"}