FreqNav: Stage-Wise Frequency Routing for Object-Oriented Aerial Vision-Language Navigation

Published August 4, 2026 · Category: Robotics

Overview

arXiv:2608.00970v1 Announce Type: new Abstract: Object-oriented aerial vision-and-language navigation (VLN) requires searching for a described target and landing on it precisely, under long-horizon and closed-loop control. Guided by a target-descriptive instruction during navigation, perceptual priorities dynamically evolve: early-stage exploration prioritizes low-frequency spatial layout, and then shifts to high-frequency target details. Existing VLN methods model the varying perceptual requirements across navigation stages with identical visual tokens, leading to interference from irrelevant objects and background clutter. To this end, we therefore formulate long-horizon aerial navigation as a frequencypreference shift from spatial structure to local detail and propose FreqNav, a lightweight frequency-routing adaptive perception framework. Under a fixed computational budget, FreqNav dynamically reallocates visual tokens across frequency components according to the current navigation stage. A Frequency Token Router selects stage-relevant visual representations from dual-view observations, while a Phase-dependent Grounding Module anchors visual evidence through explicit supervision. A Diffusion Transformer then predicts smooth trajectories for continuous control. Experiments show that FreqNav outperforms strong baselines while achieving approximately 3x faster inference. Real-world deployment further demonstrates its effectiveness, efficiency, and practical potential for long-horizon aerial autonomy.

Source

Originally published at arxiv.org.

Related Articles

• ReTouch: Empowering Contact-Rich Dexterous Manipulation with Online-Refined Tactile Prediction
• Hermite Curves as Trajectory Priors for Vision-Language-Action Models
• ProtoAct: Turning Wet-Lab Protocols into Embodied Robotic Actions