mlsanityData to 14 Oct 2026

Embodied Navigation Foundation Model

arXiv 2509.12129 ↗First posted 15 Sep 2025cs.ROcited by 72

Not on the map. Why?

Abstract (arXiv)

Navigation is a fundamental capability in embodied AI, representing the intelligence required to perceive and interact within physical environments following language instructions. Despite significant progress in large Vision-Language Models (VLMs), which exhibit remarkable zero-shot performance on general vision-language tasks, their generalization ability in embodied navigation remains largely confined to narrow task settings and embodiment-specific architectures. In this work, we introduce a cross-embodiment and cross-task Navigation Foundation Model (NavFoM), trained on eight million navigation samples that encompass quadrupeds, drones, wheeled robots, and vehicles, and spanning diverse tasks such as vision-and-language navigation, object searching, target tracking, and autonomous driving. NavFoM employs a unified architecture that processes multimodal navigation inputs from varying camera configurations and navigation horizons. To accommodate diverse camera setups and temporal horizons, NavFoM incorporates identifier tokens that embed camera view information of embodiments and the temporal context of tasks. Furthermore, to meet the demands of real-world deployment, NavFoM controls all observation tokens using a dynamically adjusted sampling strategy under a limited token length budget. Extensive evaluations on public benchmarks demonstrate that our model achieves state-of-the-art or highly competitive performance across multiple navigation tasks and embodiments without requiring task-specific fine-tuning. Additional real-world experiments further confirm the strong generalization capability and practical applicability of our approach.

Key facts. Cited by 72 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Sep 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 64.

72 papers.

Sort:

By area:

  1. 2025VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluationcited by 19
  2. 2025TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Trackingcited by 17
  3. 2025LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integrationcited by 14
  4. 2026AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Controlcited by 11
  5. 2026Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigationcited by 11
  6. 2026Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation Systemcited by 11
  7. 2026VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memorycited by 10
  8. 2026TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environmentscited by 10
  9. 2026Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigationcited by 10
  10. 2026SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigationcited by 9
  11. 2026AgentVLN: Towards Agentic Vision-and-Language Navigationcited by 9
  12. 2026Dual-Anchoring: Addressing State Drift in Vision-Language Navigationcited by 7
38 more
  1. 2025D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigationcited by 5
  2. 2026textscNaVIDA: Vision-Language Navigation with Inverse Dynamics Augmentationcited by 5
  3. 2026One Agent to Guide Them All: Empowering MLLMs for Vision-and-Language Navigation via Explicit World Representationcited by 5
  4. 2026CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Modelscited by 5
  5. 2026Vesta: A Generalist Embodied Reasoning Modelcited by 5
  6. 2026ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AIcited by 5
  7. 2026ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigationcited by 4
  8. 2026FineCog-Nav: Integrating Fine-grained Cognitive Modules for Zero-shot Multimodal UAV Navigationcited by 4
  9. 2025MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learningcited by 3
  10. 2025UrbanVLA: A Vision-Language-Action Model for Urban Micromobilitycited by 3
  11. 2026World Models as Group Actionscited by 3
  12. 2026Planning-aligned Token Compression for Long-Context Autonomous Drivingcited by 3
  13. 2026SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoningcited by 3
  14. 2026Robostral Navigatecited by 3
  15. 2026HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harnesscited by 3
  16. 2025Efficient-VLN: A Simple yet Strong Baseline for Efficient Vision-Language Navigationcited by 2
  17. 2026Does Peer Observation Help? Vision-Sharing Collaboration for Vision-Language Navigationcited by 2
  18. 2026SpatialAnt: Autonomous Zero-Shot Robot Navigation via Active Scene Reconstruction and Visual Anticipationcited by 2
  19. 2026GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigationcited by 2
  20. 2026POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigationcited by 2
  21. 2026Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigationcited by 2
  22. 2026GroundControl: Anticipating Navigation Failures in Vision-Language Agents via Trajectory-Consistent Uncertainty Estimatescited by 2
  23. 2026WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLNcited by 2
  24. 2026Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filteringcited by 1
  25. 2026SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigationcited by 1
  26. 2026What Limits Vision-and-Language Navigation ?cited by 1
  27. 2026Think Like a Pilot: Fine-Grained Long-Horizon UAV Navigationcited by 1
  28. 2026USS: Unifying Spatial-Semantic Prompting for End to End Embodied Visual Trackingcited by 1
  29. 2026Image2Sim: Scaling Embodied Navigation via Generative Neural Simulatorcited by 1
  30. 2026A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigationcited by 1
  31. 2026Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigationcited by 1
  32. 2026UrbanGround: From Local Perception to Spatial Agency in a Real-Scale Citycited by 1
  33. 2026Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigationcited by 1
  34. 2026LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigationcited by 1
  35. 2026TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Modelcited by 1
  36. 2025FlightDiffusion: Revolutionising Autonomous Drone Training with Diffusion Models Generating FPV Videocited by 0
  37. 2026Exploring Spatial Intelligence from a Generative Perspectivecited by 0
  38. 2026Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Inductioncited by 0

50 most cited of 72 All 72 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
  2. 2025NavBench: Probing Multimodal Large Language Models for Embodied Navigation
  3. 2025FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning
  4. 2025NaviTrace: Evaluating Embodied Navigation of Vision-Language Models
  5. 2025Nav-R1: Reasoning and Navigation in Embodied Scenes
  6. 2025Embodied4C: Measuring What Matters for Embodied Vision-Language Navigation
  7. 2024NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
  8. 2025NavA3: Understanding Any Instruction, Navigating Anywhere, Finding Anything