DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation
2026-08-12 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors address the challenge of navigating drones using visual and language clues by proposing DreamFly, a new method that remembers past observations without leaking future information. They design a system that plans a few steps ahead but only takes the first step before recalculating, which keeps the navigation flexible and responsive. Additionally, they create a way to decide when to stop moving that is separate from choosing actions. Testing on a standard benchmark shows DreamFly performs better than existing methods in both familiar and new environments.
Aerial vision-language navigationDiffusion modelsHistorical memoryReceding-horizon planningStop probabilityEmbodied agentsVisual representationNavigation errorOpenFly benchmark
Authors
Yan Deng, Fei Xu
Abstract
Aerial vision-language navigation (VLN) requires an embodied agent to integrate visual evidence over time, plan future actions, and determine when it has reached a navigation goal under partial observability. Although recent VLA models offer a promising perception-to-action paradigm, adapting them to aerial navigation remains challenging due to limited historical context, short planning horizons, and unreliable implicit termination. To address these challenges, we propose DreamFly, a diffusion-based aerial VLN framework built on Dream-VLA. DreamFly introduces a causally aligned historical memory that augments the current visual representation using only observations preceding the current decision step, enabling temporal reasoning without future information leakage. We further formulate navigation as receding-horizon diffusion planning, where the policy predicts a $K$-step action chunk but executes only the first action before replanning. This plan-$K$, execute-one strategy uses future actions as auxiliary planning targets while preserving closed-loop visual feedback. Finally, LiteStop estimates the stop probability directly from action logits at the initial all-mask state, decoupling explicit termination from action generation. Experiments on the OpenFly benchmark demonstrate consistent improvements in seen and unseen environments. DreamFly achieves 32.04%/29.46% SR and 28.22%/23.54% SPL on the test-seen/test-unseen splits, respectively, outperforming all compared methods on both metrics while attaining the lowest navigation error. These results demonstrate the effectiveness of jointly modeling historical context, future action structure, and explicit termination for aerial VLN.