AstraNav-World: World Model for Foresight Control and Consistency

TL;DR

AstraNav-World introduces a unified probabilistic world model that jointly predicts future visuals and actions, enhancing embodied navigation in dynamic environments with improved accuracy and zero-shot real-world adaptation.

Contribution

It presents a novel end-to-end diffusion-based framework that tightly couples visual prediction and action planning, advancing the robustness and transferability of embodied navigation models.

Findings

Improved trajectory accuracy and success rates across benchmarks.

Tight vision-action coupling enhances prediction quality and policy reliability.

Zero-shot real-world adaptation without fine-tuning.

Abstract

Embodied navigation in open, dynamic environments demands accurate foresight of how the world will evolve and how actions will unfold over time. We propose AstraNav-World, an end-to-end world model that jointly reasons about future visual states and action sequences within a unified probabilistic framework. Our framework integrates a diffusion-based video generator with a vision-language policy, enabling synchronized rollouts where predicted scenes and planned actions are updated simultaneously. Training optimizes two complementary objectives: generating action-conditioned multi-step visual predictions and deriving trajectories conditioned on those predicted visuals. This bidirectional constraint makes visual predictions executable and keeps decisions grounded in physically consistent, task-relevant futures, mitigating cumulative errors common in decoupled "envision-then-plan" pipelines. Experiments across diverse embodied navigation benchmarks show improved trajectory accuracy and higher success rates. Ablations confirm the necessity of tight vision-action coupling and unified training, with either branch removal degrading both prediction quality and policy reliability. In real-world testing, AstraNav-World demonstrated exceptional zero-shot capabilities, adapting to previously unseen scenarios without any real-world fine-tuning. These results suggest that AstraNav-World captures transferable spatial understanding and planning-relevant navigation dynamics, rather than merely overfitting to simulation-specific data distribution. Overall, by unifying foresight vision and control within a single generative model, we move closer to reliable, interpretable, and general-purpose embodied agents that operate robustly in open-ended real-world settings.