Metraipolis › archive › dc_eabe2eea31aa

SparseNav: Instruction-conditioned Sparse Semantic Perception for Training-Free Vision-Language Navigation — arXiv:2609.26408

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26408
License (as archived): CC0-1.0
Archived: 2026-10-08T16:43:56.245Z
SHA-256 of the archived text: 92d67bb4016c2f259b93f5d8cb28cedcac5fa14e23a25373fae236a44796fcde
Stable URL of this page: https://metraipolis.com/documento/dc_eabe2eea31aa

How to cite

SparseNav: Instruction-conditioned Sparse Semantic Perception for Training-Free Vision-Language Navigation — arXiv:2609.26408 — arXiv (en), https://arxiv.org/abs/2609.26408 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eabe2eea31aa (Metraipolis archive dc_eabe2eea31aa, sha256 92d67bb4016c2f259b93f5d8cb28cedcac5fa14e23a25373fae236a44796fcde)

BibTeX

@misc{dceabe2eea31aa,
  title = {SparseNav: Instruction-conditioned Sparse Semantic Perception for Training-Free Vision-Language Navigation — arXiv:2609.26408},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26408},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eabe2eea31aa; sha256 92d67bb4016c2f259b93f5d8cb28cedcac5fa14e23a25373fae236a44796fcde},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26408. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Map-based vision-language navigation (VLN) relies on persistent spatial representations to connect language understanding with geometric planning. However, acquiring semantics beyond the needs of the current instruction can introduce unnecessary perception cost and irrelevant annotations. Continuously accumulating unrelated objects may not only waste computation, but also clutter the visual-spatial representation consumed by the vision-language model (VLM) planner. To address this problem, we present SparseNav, a training-free framework that follows a less-is-more principle for semantic navigation. SparseNav persistently maintains a lightweight geometric bird's-eye-view (BEV) map and sparse landmark memory, acquiring new semantics on demand using the active sub-instruction to decide what is worth grounding. An instruction manager first tracks navigation progress and identifies the active landmark query. An instruction-conditioned perception mechanism then invokes open-vocabulary segmentation when the queried landmark is visible and its metric location can inform the next decision. The resulting landmark memory supports VLM selection among hybrid frontier and local directional waypoint candidates. Without any additional training, SparseNav achieves success rates of 42.8% on R2R-CE and 40.7% on RxR-CE, both on the Val-Unseen splits. Controlled ablations examine semantic perception strategies and the contributions of individual framework components. Furthermore, we successfully deployed SparseNav on a Unitree Go2 quadruped equipped with an Intel RealSense D455 RGB-D camera for geometric mapping and landmark grounding and a Livox MID-360 LiDAR for localization, without a prebuilt map. We validated its effectiveness across multiple indoor environments using instruction-conditioned waypoint navigation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.26408 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T15:56:53.497Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).