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

• URL: http://arxiv.org/abs/2608.30935v2
• Date: Wed, 09 Sep 2026 04:40:36 GMT
• Title: LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
• Abstract summary: Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments.<n>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.
• Score: 52.91080323083409
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System [96.69286664036143]
  We present Qwen-RobotNav, a scalable navigation model built on Qwen-RobotNav.<n>We train Qwen-RobotNav on 15.6M samples; co-training with vision-language data prevents the collapse into reactive action-sequence mappers.<n>Qwen-RobotNav sets new state-of-the-art results across major navigation benchmarks.
  arXiv  Detail & Related papers  (2026-06-16T16:17:44Z)
• AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness [5.851139427049915]
  Zero-shot vision-and-language navigation in continuous environments (VLN-CE) has recently become feasible with large vision-language models (VLMs)<n>In this paper, we rethink zero-shot VLN-CE as an agentic interface between the VLM and the environment.<n>We present AgenticNav, a lightweight navigation harness that exposes action, depth, and memory as callable tools.
  arXiv  Detail & Related papers  (2026-06-09T08:43:05Z)
• What Limits Vision-and-Language Navigation ? [18.423144111320592]
  StereoNav is a robust Vision-Language-Action framework designed to enhance real-world navigation consistency.<n>Experiments on R2R-CE and RxR-CE demonstrate that StereoNav achieves state-of-the-art egocentric RGB performance.
  arXiv  Detail & Related papers  (2026-05-13T10:41:24Z)
• OpenFrontier: General Navigation with Visual-Language Grounded Frontiers [54.661157616245966]
  Open-world navigation requires robots to make decisions in complex everyday environments.<n>Recent advances in vision--language navigation (VLN) and vision--language--action (VLA) models enable end-to-end policies conditioned on natural language.<n>We propose OpenFrontier, a training-free navigation framework that seamlessly integrates diverse vision--language prior models.
  arXiv  Detail & Related papers  (2026-03-05T17:02:22Z)
• AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild [62.47761809929869]
  Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations.<n>Current VLN research for unmanned aerial vehicles (UAVs) relies on detailed, pre-specified instructions to guide the UAV along predetermined routes.<n>We propose AutoFly, an end-to-end Vision-Language-Action model for autonomous UAV navigation.
  arXiv  Detail & Related papers  (2026-02-10T11:08:07Z)
• Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks [24.690910258151693]
  Existing models for embodied navigation fall short of serving as practical generalists in the real world.<n>We present Uni-NaVid, the first video-based vision-language-action model designed to unify diverse embodied navigation tasks.<n>Uni-NaVid achieves this by the input and output data configurations for all commonly used embodied navigation tasks.
  arXiv  Detail & Related papers  (2024-12-09T05:55:55Z)
• GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation [65.71524410114797]
  GOAT-Bench is a benchmark for the universal navigation task GO to AnyThing (GOAT) In GOAT, the agent is directed to navigate to a sequence of targets specified by the category name, language description, or image. We benchmark monolithic RL and modular methods on the GOAT task, analyzing their performance across modalities.
  arXiv  Detail & Related papers  (2024-04-09T20:40:00Z)
• Learning Navigational Visual Representations with Semantic Map Supervision [85.91625020847358]
  We propose a navigational-specific visual representation learning method by contrasting the agent's egocentric views and semantic maps. Ego$2$-Map learning transfers the compact and rich information from a map, such as objects, structure and transition, to the agent's egocentric representations for navigation.
  arXiv  Detail & Related papers  (2023-07-23T14:01:05Z)
• NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models [17.495162643127003]
  We introduce the NavGPT to reveal the reasoning capability of GPT models in complex embodied scenes. NavGPT takes the textual descriptions of visual observations, navigation history, and future explorable directions as inputs to reason the agent's current status. We show that NavGPT is capable of generating high-quality navigational instructions from observations and actions along a path.
  arXiv  Detail & Related papers  (2023-05-26T14:41:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.