{"paper":{"title":"NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"NavOne reformulates vision-language navigation as one-step global path planning via direct dense path probability prediction on pre-built top-down maps.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenxi Zheng, Dijia Zhan, Jie Tang, Jinyi Li, Shaoyu Huang, Xuemiao Xu, Yong Li","submitted_at":"2026-05-07T14:16:58Z","abstract_excerpt":"Existing Vision-Language Navigation (VLN) methods typically adopt an egocentric, step-by-step paradigm, which struggles with error accumulation and limits efficiency. While recent approaches attempt to leverage pre-built environment maps, they often rely on incrementally updating memory graphs or scoring discrete path proposals, which restricts continuous spatial reasoning and creates discrete bottlenecks. We propose Top-Down VLN (TD-VLN), reformulating navigation as a one-step global path planning problem on pre-built top-down maps, supported by our newly constructed R2R-TopDown dataset. To s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"NavOne achieves state-of-the-art performance among map-based VLN methods, with a planning-stage speedup of 8x over existing map-based baselines and 80x over egocentric methods, enabling highly efficient global navigation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The approach assumes the availability of pre-built top-down maps and that direct prediction of dense path probabilities on these maps can effectively solve the navigation task without the error accumulation issues of step-by-step methods.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"NavOne enables one-step global navigation planning on top-down maps using a unified multi-modal framework, achieving state-of-the-art results and up to 80x speedup on the new R2R-TopDown dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"NavOne reformulates vision-language navigation as one-step global path planning via direct dense path probability prediction on pre-built top-down maps.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5c86ceeacc539a6a65e9c8933b3d15f0ec77576f2e3ee8d0baf20845aae204b8"},"source":{"id":"2605.06317","kind":"arxiv","version":3},"verdict":{"id":"0be83d16-86ba-499c-aa7f-36a4049af79e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T00:44:32.395108Z","strongest_claim":"NavOne achieves state-of-the-art performance among map-based VLN methods, with a planning-stage speedup of 8x over existing map-based baselines and 80x over egocentric methods, enabling highly efficient global navigation.","one_line_summary":"NavOne enables one-step global navigation planning on top-down maps using a unified multi-modal framework, achieving state-of-the-art results and up to 80x speedup on the new R2R-TopDown dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The approach assumes the availability of pre-built top-down maps and that direct prediction of dense path probabilities on these maps can effectively solve the navigation task without the error accumulation issues of step-by-step methods.","pith_extraction_headline":"NavOne reformulates vision-language navigation as one-step global path planning via direct dense path probability prediction on pre-built top-down maps."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.06317/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:19.465290Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:48:58.703983Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d53de2d18b7638cf92a753f05c131a011f7616d8fe72529ea4a2d3d8b609cd82"},"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"}