# Feeling Terrain Before Crossing: World Models for Off-Road Navigation

arXiv: https://arxiv.org/abs/2609.19863 · HTML: https://mlsanity.com/paper/2609.19863/

## 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 26 of its 30 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments](https://mlsanity.com/paper/2301.04195/) (2023)
- [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)
- [TartanDrive: A Large-Scale Dataset for Learning Off-Road Dynamics Models](https://mlsanity.com/paper/2205.01791/) (2022)
- [Fast Traversability Estimation for Wild Visual Navigation](https://mlsanity.com/paper/2305.08510/) (2023)
- [WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation](https://mlsanity.com/paper/2503.02247/) (2025)
- [How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversability](https://mlsanity.com/paper/2209.10788/) (2022)
- [TartanDrive 2.0: More Modalities and Better Infrastructure to Further Self-Supervised Learning Research in Off-Road Driving Tasks](https://mlsanity.com/paper/2402.01913/) (2024)
- [AstraNav-World: World Model for Foresight Control and Consistency](https://mlsanity.com/paper/2512.21714/) (2025)
- [Learned Perceptive Forward Dynamics Model for Safe and Platform-aware Robotic Navigation](https://mlsanity.com/paper/2504.19322/) (2025)
- [An Efficient and Multi-Modal Navigation System with One-Step World Model](https://mlsanity.com/paper/2601.12277/) (2026)
- [RAE-NWM: Navigation World Model in Dense Visual Representation Space](https://mlsanity.com/paper/2603.09241/) (2026)
- [WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation](https://mlsanity.com/paper/2606.04907/) (2026)
- [NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation](https://mlsanity.com/paper/2606.13494/) (2026)
- [Efficient Image-Goal Navigation with Representative Latent World Model](https://mlsanity.com/paper/2511.11011/) (2025)
- [NavThinker: Action-Conditioned World Models for Coupled Prediction and Planning in Social Navigation](https://mlsanity.com/paper/2603.15359/) (2026)
- [ProNav: Proprioceptive Traversability Estimation for Legged Robot Navigation in Outdoor Environments](https://mlsanity.com/paper/2307.09754/) (2023)
- [Traversability-aware Adaptive Optimization for Path Planning and Control in Mountainous Terrain](https://mlsanity.com/paper/2404.03274/) (2024)
- [Learning Vehicle Dynamics from Cropped Image Patches for Robot Navigation in Unpaved Outdoor Terrains](https://mlsanity.com/paper/2309.02745/) (2023)
- [Learning When to Jump for Off-road Navigation](https://mlsanity.com/paper/2602.00877/) (2026)
- [CanonNav: Disentangling Navigation Behavior from Camera Geometry in Cross-Platform Visual Navigation](https://mlsanity.com/paper/2608.30242/) (2026)

## Abstract (arXiv)

Navigation world models plan by foresight, predicting the future that each candidate action sequence produces and selecting the best, rather than mapping observations to actions directly. Unlike urban settings where a predicted scene is a sufficient proxy, off-road navigation hinges on the robot--terrain interaction, so the prediction must cover not only what the camera will see but what the robot will feel. However, existing scene-focused models do not predict how much the robot will slip, tilt or shake along a planned trajectory. Proprioception captures these dynamics directly and, when used as input, improves the prediction of the physical future. We present Feel-WM, the first off-road navigation world model that conditions on proprioception and predicts what the robot will feel alongside what the camera will see. The physical future takes the form of a future proprioceptive state and a failure risk, both learned from the robot's own experience without human labels. The planner rolls out the physical future alongside the scene and weighs the predicted failure risk against goal similarity in a separable score. Experiments on real off-road data and in simulation demonstrate that Feel-WM outperforms visual-only navigation world models in open-loop planning and closed-loop rough-terrain navigation across wheeled and legged platforms. Deployed on a Husky on mountain trails, Feel-WM plans onboard, predicts rough ground ahead and steers around it, completing courses that an end-to-end policy fails.