Metraipolis › archive › dc_e47d3ebdd210

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation — arXiv:2608.30935

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.30935
License (as archived): CC0-1.0
Archived: 2026-10-17T07:55:10.070Z
SHA-256 of the archived text: 5a491fbf061bfaf724bdfe5c1dde6c50f15021e5ba51a1e2a674666766d36608
Stable URL of this page: https://metraipolis.com/documento/dc_e47d3ebdd210

How to cite

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation — arXiv:2608.30935 — arXiv (en), https://arxiv.org/abs/2608.30935 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e47d3ebdd210 (Metraipolis archive dc_e47d3ebdd210, sha256 5a491fbf061bfaf724bdfe5c1dde6c50f15021e5ba51a1e2a674666766d36608)

BibTeX

@misc{dce47d3ebdd210,
  title = {LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation — arXiv:2608.30935},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30935},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e47d3ebdd210; sha256 5a491fbf061bfaf724bdfe5c1dde6c50f15021e5ba51a1e2a674666766d36608},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30935. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments. Modern vision-language models (VLMs) already encode spatial priors for visual grounding, spatial reasoning, and pointing, but these capabilities are rarely elicited directly for robot control. Existing navigation systems instead rely on task- or embodiment-specific components, fragmenting perception, reasoning, and action while offering limited generalization. Here we present LightNav-0, a compact generalist embodied navigation model that elicits the spatial intelligence of a pretrained VLM and aligns it with navigation, without task-specific prediction heads. LightNav-0 represents diverse navigation tasks through a unified token interface: dual-channel pointing expresses task-, scene-, and embodiment-agnostic spatial intent, while a residual vector-quantized action tokenizer maps this intent to precise, embodiment-specific trajectories. Together with temporally aware visual history compression, ER mid-training, supervised fine-tuning, and reinforcement learning, this formulation supports instruction following, open-vocabulary object navigation, and visual tracking within a single model. The navigation training corpus spans 2K+ scenes and 4K+ hours of embodied navigation data. LightNav-ER, the embodied-reasoning checkpoint used to initialize LightNav-0, attains the highest complete-set average across 8 embodied-reasoning benchmarks, while LightNav-0 achieves state-of-the-art monocular success rates across all 10 public navigation simulation settings. Real-world evaluations further demonstrate zero-shot generalization across robot embodiments, diverse scenes, and static and dynamic targets. These results establish compact VLMs as a unified and transferable backbone for generalist embodied navigation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.30935 — 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 2026-10-17T07:28:26.924Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).