---
title: "FSD-VLN：面向航空长距离视觉语言导航的快慢双系统模型"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.08359v1"
permalink: "https://feed.astralor.com/items/itm_b95fb85acdb34d1c87565e2c"
published: "2026-07-09T11:17:04.000Z"
score: 76
channel: "tech"
tags: ["FSD-VLN","快慢系统","扩散Transformer","无人机自主导航","视觉语言导航"]
---

# FSD-VLN：面向航空长距离视觉语言导航的快慢双系统模型

## AI 点评

> 这篇论文为解决无人机长距离导航中的动作延迟问题提供了一个优雅的范式转换——将认知科学中的快慢系统引入AI，而不仅仅是堆叠更大的模型。对于从事机器人学、视觉语言导航或嵌入式AI的读者，其中的时间感知优化器和DiT应用值得深入研究。同时也提醒我们：有时解耦反而是通向实时智能的关键。

## 速览

该论文提出FSD-VLN，一种快慢双系统架构，旨在解决航空长距离视觉语言导航中全局语义理解与低延迟动作生成的结构错配问题。框架包含提取稳定语义先验的慢流和基于DiT的跨时间动作分布建模快流，并引入时间感知自适应优化器稳定长序列训练。在低空模拟实验中，导航成功率提升至两倍，单动作推理延迟和总任务时间降低超50%，验证了解耦语义与控制建模的有效性。

## 关键点

- 提出快慢双系统架构，解耦语义推理与低延迟飞行控制。
- 快流采用Diffusion Transformer（DiT）生成跨时间一致的动作序列。
- 引入时间感知自适应优化器，减少长序列训练中的梯度振荡。
- 在未见场景中导航成功率较现有最优方法提升2倍，延迟降低50%以上。

## 全文

Vision-Language Navigation (VLN) enables UAV autonomous navigation in unknown environments by mapping language instructions to real-time visual inputs. Compared with GPS-dependent or pre-programmed navigation, VLN supports intuitive human-machine interaction and stronger environmental adaptability, requiring tight integration of high-level semantic reasoning and low-latency flight control.Existing methods suffer from structural misalignment between global multimodal understanding and sequential action generation, causing jittery trajectories and severe decision latency for long-horizon aerial navigation. To solve this issue, we propose FSD-VLN, a fast-slow dual-system architecture disentangling semantic reasoning and low-latency flight command generation.The framework has two asynchronous branches: a slow stream extracting stable semantic priors from pre-trained vision-language models, and a Diffusion Transformer (DiT) fast stream modeling cross-temporal action distributions to produce consistent flight outputs. We further introduce a time-aware adaptive optimizer to stabilize long-sequence training and reduce gradient oscillation.Large-scale low-altitude simulation experiments show FSD-VLN achieves up to 2X higher navigation success rates on unseen scenes than SOTA methods, while cutting single-action inference delay and total task runtime by over 50%. Our work validates the benefit of decoupled semantic-control modeling and provides a practical paradigm for long-horizon aerial VLN.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_b95fb85acdb34d1c87565e2c