{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7HWP7Z77ZXPD7WHP6FZV4R3ZC4","short_pith_number":"pith:7HWP7Z77","schema_version":"1.0","canonical_sha256":"f9ecffe7ffcdde3fd8eff1735e4779173cb42e2751c2ed172fd4fa0b28b82119","source":{"kind":"arxiv","id":"2409.11146","version":3},"attestation_state":"computed","paper":{"title":"MI-HGNN: Morphology-Informed Heterogeneous Graph Neural Network for Legged Robot Contact Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Daniel Butterfield, Lu Gan, Nai-Jen Cheng, Sandilya Sai Garimella","submitted_at":"2024-09-17T12:55:37Z","abstract_excerpt":"We present a Morphology-Informed Heterogeneous Graph Neural Network (MI-HGNN) for learning-based contact perception. The architecture and connectivity of the MI-HGNN are constructed from the robot morphology, in which nodes and edges are robot joints and links, respectively. By incorporating the morphology-informed constraints into a neural network, we improve a learning-based approach using model-based knowledge. We apply the proposed MI-HGNN to two contact perception problems, and conduct extensive experiments using both real-world and simulated data collected using two quadruped robots. Our"},"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":"2409.11146","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-17T12:55:37Z","cross_cats_sorted":[],"title_canon_sha256":"21b6f55b4fad07c8e4d1a2fa95ea38382ef1152e41cb89bcc6c8f31a2457521a","abstract_canon_sha256":"2dba22548001daa0ebb00fb5beb6b28d5bf2bbaae4ab82f60ee05411cbafd16d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:39.159469Z","signature_b64":"iMAXl6hEfzCrYe1HXs5QMJWU/e0CnUapxM4Z5JBBFM2jF5jhFYf8RyJeqHOUQQXNbShF5k1xEN4soYpfQ4mNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9ecffe7ffcdde3fd8eff1735e4779173cb42e2751c2ed172fd4fa0b28b82119","last_reissued_at":"2026-07-05T10:43:39.159011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:39.159011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MI-HGNN: Morphology-Informed Heterogeneous Graph Neural Network for Legged Robot Contact Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Daniel Butterfield, Lu Gan, Nai-Jen Cheng, Sandilya Sai Garimella","submitted_at":"2024-09-17T12:55:37Z","abstract_excerpt":"We present a Morphology-Informed Heterogeneous Graph Neural Network (MI-HGNN) for learning-based contact perception. The architecture and connectivity of the MI-HGNN are constructed from the robot morphology, in which nodes and edges are robot joints and links, respectively. By incorporating the morphology-informed constraints into a neural network, we improve a learning-based approach using model-based knowledge. We apply the proposed MI-HGNN to two contact perception problems, and conduct extensive experiments using both real-world and simulated data collected using two quadruped robots. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11146","kind":"arxiv","version":3},"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/2409.11146/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":"2409.11146","created_at":"2026-07-05T10:43:39.159070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11146v3","created_at":"2026-07-05T10:43:39.159070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11146","created_at":"2026-07-05T10:43:39.159070+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HWP7Z77ZXPD","created_at":"2026-07-05T10:43:39.159070+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HWP7Z77ZXPD7WHP","created_at":"2026-07-05T10:43:39.159070+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HWP7Z77","created_at":"2026-07-05T10:43:39.159070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05287","citing_title":"Morphologically Symmetric Reinforcement Learning for Ambidextrous Bimanual Manipulation","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7HWP7Z77ZXPD7WHP6FZV4R3ZC4","json":"https://pith.science/pith/7HWP7Z77ZXPD7WHP6FZV4R3ZC4.json","graph_json":"https://pith.science/api/pith-number/7HWP7Z77ZXPD7WHP6FZV4R3ZC4/graph.json","events_json":"https://pith.science/api/pith-number/7HWP7Z77ZXPD7WHP6FZV4R3ZC4/events.json","paper":"https://pith.science/paper/7HWP7Z77"},"agent_actions":{"view_html":"https://pith.science/pith/7HWP7Z77ZXPD7WHP6FZV4R3ZC4","download_json":"https://pith.science/pith/7HWP7Z77ZXPD7WHP6FZV4R3ZC4.json","view_paper":"https://pith.science/paper/7HWP7Z77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11146&json=true","fetch_graph":"https://pith.science/api/pith-number/7HWP7Z77ZXPD7WHP6FZV4R3ZC4/graph.json","fetch_events":"https://pith.science/api/pith-number/7HWP7Z77ZXPD7WHP6FZV4R3ZC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HWP7Z77ZXPD7WHP6FZV4R3ZC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HWP7Z77ZXPD7WHP6FZV4R3ZC4/action/storage_attestation","attest_author":"https://pith.science/pith/7HWP7Z77ZXPD7WHP6FZV4R3ZC4/action/author_attestation","sign_citation":"https://pith.science/pith/7HWP7Z77ZXPD7WHP6FZV4R3ZC4/action/citation_signature","submit_replication":"https://pith.science/pith/7HWP7Z77ZXPD7WHP6FZV4R3ZC4/action/replication_record"}},"created_at":"2026-07-05T10:43:39.159070+00:00","updated_at":"2026-07-05T10:43:39.159070+00:00"}