# Skytopia: Monocular Drone Navigation with Action-Conditioned Latent World Models

arXiv: https://arxiv.org/abs/2609.26007 · HTML: https://mlsanity.com/paper/2609.26007/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 42 of its 45 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Placed in

- World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/)

## Builds on (most cited first, 30 of 42)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Learning High-Speed Flight in the Wild](https://mlsanity.com/paper/2110.05113/) (2021)
- [Rapid Exploration for Open-World Navigation with Latent Goal Models](https://mlsanity.com/paper/2104.05859/) (2021)
- [Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology](https://mlsanity.com/paper/2410.07087/) (2024)
- [Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs](https://mlsanity.com/paper/2407.07775/) (2024)
- [Embodied Navigation Foundation Model](https://mlsanity.com/paper/2509.12129/) (2025)
- [ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints](https://mlsanity.com/paper/2202.11271/) (2022)
- [NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance](https://mlsanity.com/paper/2505.08712/) (2025)
- [Openfly: A comprehensive platform for aerial vision-language navigation](https://mlsanity.com/paper/2502.18041/) (2025)
- [World Model for Robot Learning: A Comprehensive Survey](https://mlsanity.com/paper/2605.00080/) (2026)
- [Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physics](https://mlsanity.com/paper/2407.10648/) (2024)
- [NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2506.23468/) (2025)
- [Hierarchical Planning with Latent World Models](https://mlsanity.com/paper/2604.03208/) (2026)
- [OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation](https://mlsanity.com/paper/2509.19480/) (2025)
- [Grounding Video Models to Actions through Goal Conditioned Exploration](https://mlsanity.com/paper/2411.07223/) (2024)
- [NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation](https://mlsanity.com/paper/2504.10003/) (2025)
- [Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models](https://mlsanity.com/paper/2504.10041/) (2025)
- [Grounded Vision-Language Navigation for UAVs with Open-Vocabulary Goal Understanding](https://mlsanity.com/paper/2506.10756/) (2025)

## Abstract (arXiv)

Monocular drone navigation requires reaching a goal in an unseen environment from a single forward-facing camera, which offers few cues for depth and scale. World models address this by modelling how observations evolve under actions, but they are built to be executed: the prediction is produced at deployment and fed back into action generation at every control step. We argue that what a policy needs from a world model is not the prediction but the representation required to produce it: in flight the executed action explains almost all of the change between observations, so prediction reduces to reprojecting a static scene under a known displacement. We therefore introduce skytopia, a policy built on an action-conditioned latent world model, and the 3D Gaussian Splatting platform on which it is trained. A forward objective predicts the representation of the next observation from the intended motion, and an inverse objective recovers that motion from the predicted transition. Because the prediction never reaches action generation, the predictor is discarded and one policy serves point-goal, image-goal, and goal-free navigation. Simulation experiments show that skytopia outperforms every baseline under all three specifications, attaining 57.8%, 66.0%, and 49.0% success rate, while discarding the predictor removes 59.4% of the inference cost. The same policy is subsequently deployed on a physical drone without fine-tuning and reaches goals in indoor, open outdoor, and woodland environments.