# X-MOBILITY: End-To-End Generalizable Navigation via World Modeling

arXiv: https://arxiv.org/abs/2410.17491 · HTML: https://mlsanity.com/paper/2410.17491/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Placed in

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

## Builds on (most cited first, 6 of 6)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving](https://mlsanity.com/paper/2311.17918/) (2023)
- [DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving](https://mlsanity.com/paper/2309.09777/) (2023)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [ADriver-I: A General World Model for Autonomous Driving](https://mlsanity.com/paper/2311.13549/) (2023)

## Built on by (most cited first, 16 of 16)

- [A Comprehensive Survey on World Models for Embodied AI](https://mlsanity.com/paper/2510.16732/) (2025)
- [CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos](https://mlsanity.com/paper/2411.17820/) (2024)
- [A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI](https://mlsanity.com/paper/2505.01458/) (2025)
- [From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning](https://mlsanity.com/paper/2507.22028/) (2025)
- [TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments](https://mlsanity.com/paper/2602.02459/) (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)
- [World-Action Models for Robot Learning and Control: A Survey](https://mlsanity.com/paper/2609.16074/) (2026)
- [Latent World Models with Monotone Planning Costs for Image-Goal Navigation](https://mlsanity.com/paper/2608.09073/) (2026)
- [Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI](https://mlsanity.com/paper/2510.04978/) (2025)
- [AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation](https://mlsanity.com/paper/2604.24086/) (2026)
- [Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation](https://mlsanity.com/paper/2510.23258/) (2025)
- [Schr"odinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation](https://mlsanity.com/paper/2512.21201/) (2025)
- [AttentionSwarm: Reinforcement Learning with Attention Control Barier Function for Crazyflie Drones in Dynamic Environments](https://mlsanity.com/paper/2503.07376/) (2025)
- [CrossTracer: Cross-Embodiment Navigation via VLA Model Reasoning and Trace Residuals Adapting](https://mlsanity.com/paper/2608.06688/) (2026)
- [Visual Cue Guided Video Planning for Generalizable Robot Navigation](https://mlsanity.com/paper/2609.16737/) (2026)

## Abstract (arXiv)

General-purpose navigation in challenging environments remains a significant problem in robotics, with current state-of-the-art approaches facing myriad limitations. Classical approaches struggle with cluttered settings and require extensive tuning, while learning-based methods face difficulties generalizing to out-of-distribution environments. This paper introduces X-Mobility, an end-to-end generalizable navigation model that overcomes existing challenges by leveraging three key ideas. First, X-Mobility employs an auto-regressive world modeling architecture with a latent state space to capture world dynamics. Second, a diverse set of multi-head decoders enables the model to learn a rich state representation that correlates strongly with effective navigation skills. Third, by decoupling world modeling from action policy, our architecture can train effectively on a variety of data sources, both with and without expert policies: off-policy data allows the model to learn world dynamics, while on-policy data with supervisory control enables optimal action policy learning. Through extensive experiments, we demonstrate that X-Mobility not only generalizes effectively but also surpasses current state-of-the-art navigation approaches. Additionally, X-Mobility also achieves zero-shot Sim2Real transferability and shows strong potential for cross-embodiment generalization.