{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MRHYWJRHHBKVMDGUQLPFV24C44","short_pith_number":"pith:MRHYWJRH","schema_version":"1.0","canonical_sha256":"644f8b26273855560cd482de5aeb82e7386c47b2d728b8e18280f8afecd4b701","source":{"kind":"arxiv","id":"2503.09010","version":2},"attestation_state":"computed","paper":{"title":"HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chenghao Sun, Gang Han, Hao Cheng, Jiahang Cao, Jian Tang, Jiaxu Wang, Jingkai Sun, Lingfeng Zhang, Lin Wang, Qiang Zhang, Renjing Xu, Wei Cui, Wen Zhao, Yijie Guo, Yujie Chen, Zhang Zhang","submitted_at":"2025-03-12T02:59:21Z","abstract_excerpt":"The perceptual system design for humanoid robots poses unique challenges due to inherent structural constraints that cause severe self-occlusion and limited field-of-view (FOV). We present HumanoidPano, a novel hybrid cross-modal perception framework that synergistically integrates panoramic vision and LiDAR sensing to overcome these limitations. Unlike conventional robot perception systems that rely on monocular cameras or standard multi-sensor configurations, our method establishes geometrically-aware modality alignment through a spherical vision transformer, enabling seamless fusion of 360 "},"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":"2503.09010","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-12T02:59:21Z","cross_cats_sorted":[],"title_canon_sha256":"06e5ad0b826fa1b1db588e688ea8b46ce4b6c31c8f8bc84736bdf020814d81c7","abstract_canon_sha256":"ce2593fddd2366556ae46ca23e4811d0873f223f99912f8b81202165f977f23e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:33.853173Z","signature_b64":"+7EloP/aBHcxMNlIjzeMiVQSR20/Ew4VG8Day8bGDsY0spQgxxYD46g1WRUfQUVFzm6ssEOGHFVs3d7DGHttDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"644f8b26273855560cd482de5aeb82e7386c47b2d728b8e18280f8afecd4b701","last_reissued_at":"2026-07-05T10:30:33.852499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:33.852499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chenghao Sun, Gang Han, Hao Cheng, Jiahang Cao, Jian Tang, Jiaxu Wang, Jingkai Sun, Lingfeng Zhang, Lin Wang, Qiang Zhang, Renjing Xu, Wei Cui, Wen Zhao, Yijie Guo, Yujie Chen, Zhang Zhang","submitted_at":"2025-03-12T02:59:21Z","abstract_excerpt":"The perceptual system design for humanoid robots poses unique challenges due to inherent structural constraints that cause severe self-occlusion and limited field-of-view (FOV). We present HumanoidPano, a novel hybrid cross-modal perception framework that synergistically integrates panoramic vision and LiDAR sensing to overcome these limitations. Unlike conventional robot perception systems that rely on monocular cameras or standard multi-sensor configurations, our method establishes geometrically-aware modality alignment through a spherical vision transformer, enabling seamless fusion of 360 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09010","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/2503.09010/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":"2503.09010","created_at":"2026-07-05T10:30:33.852572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09010v2","created_at":"2026-07-05T10:30:33.852572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09010","created_at":"2026-07-05T10:30:33.852572+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRHYWJRHHBKV","created_at":"2026-07-05T10:30:33.852572+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRHYWJRHHBKVMDGU","created_at":"2026-07-05T10:30:33.852572+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRHYWJRH","created_at":"2026-07-05T10:30:33.852572+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30367","citing_title":"FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00510","citing_title":"OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05405","citing_title":"Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13476","citing_title":"RobotPan: A 360$^\\circ$ Surround-View Robotic Vision System for Embodied Perception","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRHYWJRHHBKVMDGUQLPFV24C44","json":"https://pith.science/pith/MRHYWJRHHBKVMDGUQLPFV24C44.json","graph_json":"https://pith.science/api/pith-number/MRHYWJRHHBKVMDGUQLPFV24C44/graph.json","events_json":"https://pith.science/api/pith-number/MRHYWJRHHBKVMDGUQLPFV24C44/events.json","paper":"https://pith.science/paper/MRHYWJRH"},"agent_actions":{"view_html":"https://pith.science/pith/MRHYWJRHHBKVMDGUQLPFV24C44","download_json":"https://pith.science/pith/MRHYWJRHHBKVMDGUQLPFV24C44.json","view_paper":"https://pith.science/paper/MRHYWJRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09010&json=true","fetch_graph":"https://pith.science/api/pith-number/MRHYWJRHHBKVMDGUQLPFV24C44/graph.json","fetch_events":"https://pith.science/api/pith-number/MRHYWJRHHBKVMDGUQLPFV24C44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRHYWJRHHBKVMDGUQLPFV24C44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRHYWJRHHBKVMDGUQLPFV24C44/action/storage_attestation","attest_author":"https://pith.science/pith/MRHYWJRHHBKVMDGUQLPFV24C44/action/author_attestation","sign_citation":"https://pith.science/pith/MRHYWJRHHBKVMDGUQLPFV24C44/action/citation_signature","submit_replication":"https://pith.science/pith/MRHYWJRHHBKVMDGUQLPFV24C44/action/replication_record"}},"created_at":"2026-07-05T10:30:33.852572+00:00","updated_at":"2026-07-05T10:30:33.852572+00:00"}