{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FU5ZF6UDJGSMJAD6FCNO4EGW7C","short_pith_number":"pith:FU5ZF6UD","schema_version":"1.0","canonical_sha256":"2d3b92fa8349a4c4807e289aee10d6f899d5ec62565bdc88b28052fa525bd044","source":{"kind":"arxiv","id":"2412.04453","version":2},"attestation_state":"computed","paper":{"title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"An-Chieh Cheng, Erdem B{\\i}y{\\i}k, Hongxu Yin, Jan Kautz, Sifei Liu, Xiaolong Wang, Xueyan Zou, Yandong Ji, Zaitian Gongye, Zhaojing Yang","submitted_at":"2024-12-05T18:58:17Z","abstract_excerpt":"This paper proposes to solve the problem of Vision-and-Language Navigation with legged robots, which not only provides a flexible way for humans to command but also allows the robot to navigate through more challenging and cluttered scenes. However, it is non-trivial to translate human language instructions all the way to low-level leg joint actions. We propose NaVILA, a 2-level framework that unifies a Vision-Language-Action model (VLA) with locomotion skills. Instead of directly predicting low-level actions from VLA, NaVILA first generates mid-level actions with spatial information in the fo"},"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":"2412.04453","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-05T18:58:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f08bdd47958755ab5ae5006f28e0301391b35c6dddc6633a3ebc66a22c23b5c9","abstract_canon_sha256":"d2ae6a848dd8698001749dd085901d8d05b5f937084dad3434d976cdf75a7f05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:23.554060Z","signature_b64":"5ViAIY6VK6NdJ5bR3G7XTm8CJNcAaP+0vltmnItsFZVFz9RTJ1aMb3kcGFZDSuN/456/UJNF9oiNWdGgfcqfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3b92fa8349a4c4807e289aee10d6f899d5ec62565bdc88b28052fa525bd044","last_reissued_at":"2026-07-05T10:15:23.553445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:23.553445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"An-Chieh Cheng, Erdem B{\\i}y{\\i}k, Hongxu Yin, Jan Kautz, Sifei Liu, Xiaolong Wang, Xueyan Zou, Yandong Ji, Zaitian Gongye, Zhaojing Yang","submitted_at":"2024-12-05T18:58:17Z","abstract_excerpt":"This paper proposes to solve the problem of Vision-and-Language Navigation with legged robots, which not only provides a flexible way for humans to command but also allows the robot to navigate through more challenging and cluttered scenes. However, it is non-trivial to translate human language instructions all the way to low-level leg joint actions. We propose NaVILA, a 2-level framework that unifies a Vision-Language-Action model (VLA) with locomotion skills. Instead of directly predicting low-level actions from VLA, NaVILA first generates mid-level actions with spatial information in the fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04453","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/2412.04453/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":"2412.04453","created_at":"2026-07-05T10:15:23.553528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04453v2","created_at":"2026-07-05T10:15:23.553528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04453","created_at":"2026-07-05T10:15:23.553528+00:00"},{"alias_kind":"pith_short_12","alias_value":"FU5ZF6UDJGSM","created_at":"2026-07-05T10:15:23.553528+00:00"},{"alias_kind":"pith_short_16","alias_value":"FU5ZF6UDJGSMJAD6","created_at":"2026-07-05T10:15:23.553528+00:00"},{"alias_kind":"pith_short_8","alias_value":"FU5ZF6UD","created_at":"2026-07-05T10:15:23.553528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":42,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22424","citing_title":"FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21398","citing_title":"BIT-Nav: Brain-Inspired Trajectory Memory for Embodied Navigation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20905","citing_title":"Vesta: A Generalist Embodied Reasoning Model","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20458","citing_title":"Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18426","citing_title":"VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01754","citing_title":"Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12603","citing_title":"From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10495","citing_title":"Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07244","citing_title":"Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03175","citing_title":"Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01565","citing_title":"Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01621","citing_title":"Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17249","citing_title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30367","citing_title":"FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28760","citing_title":"Vision-Language Models for Deployable Social Robot Navigation: Bridging Semantic Reasoning and Low-Level Control","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25646","citing_title":"G-DRAGON: Geospatial Reasoning and Dynamic Planning for Retrieval-Augmented Outdoor Navigation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27807","citing_title":"SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27582","citing_title":"Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00104","citing_title":"PEACE: A Planner-Executor Agent with Constraint Enforcement for UAVs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28237","citing_title":"POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04468","citing_title":"NVILA: Efficient Frontier Visual Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2504.16054","citing_title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22036","citing_title":"GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22816","citing_title":"AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17249","citing_title":"SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C","json":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C.json","graph_json":"https://pith.science/api/pith-number/FU5ZF6UDJGSMJAD6FCNO4EGW7C/graph.json","events_json":"https://pith.science/api/pith-number/FU5ZF6UDJGSMJAD6FCNO4EGW7C/events.json","paper":"https://pith.science/paper/FU5ZF6UD"},"agent_actions":{"view_html":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C","download_json":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C.json","view_paper":"https://pith.science/paper/FU5ZF6UD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04453&json=true","fetch_graph":"https://pith.science/api/pith-number/FU5ZF6UDJGSMJAD6FCNO4EGW7C/graph.json","fetch_events":"https://pith.science/api/pith-number/FU5ZF6UDJGSMJAD6FCNO4EGW7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/action/storage_attestation","attest_author":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/action/author_attestation","sign_citation":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/action/citation_signature","submit_replication":"https://pith.science/pith/FU5ZF6UDJGSMJAD6FCNO4EGW7C/action/replication_record"}},"created_at":"2026-07-05T10:15:23.553528+00:00","updated_at":"2026-07-05T10:15:23.553528+00:00"}