FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation

• URL: http://arxiv.org/abs/2607.08359v1
• Date: Thu, 09 Jul 2026 11:17:04 GMT
• Title: FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation
• Abstract summary: Vision-Language Navigation (VLN) is an autonomous navigation in unknown environments by mapping language instructions to real-time visual inputs.<n>Existing methods suffer from structural misalignment between global multimodal understanding and sequential action generation.<n>We propose FSD-VLN, a fast-slow dual-system architecture disentangling semantic reasoning and low-altitude flight command generation.
• Score: 33.92221208368759
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• FreqNav: Stage-Wise Frequency Routing for Object-Oriented Aerial Vision-Language Navigation [20.62861089679206]
  We propose a lightweight adaptive perception framework for long-horizon aerial navigation.<n>FreqNav dynamically reallocates visual tokens across frequency components according to the current navigation stage.<n>Experiments show that FreqNav outperforms strong baselines while achieving approximately 3x faster inference.
  arXiv  Detail & Related papers  (2026-08-02T03:49:54Z)
• DynFly: Dynamic-Aware Continuous Trajectory Generation for UAV Vision-Language Navigation in Urban Environments [55.73595346639892]
  We propose DynFly to bridge high-level navigation reasoning and executable UAV motion.<n>DynFly represents expert trajectories in B-spline control-point space and employs a Spline-DiT generator to learn conditional trajectory generation.<n>Experiments on the OpenUAV UAV-VLN benchmark show that DynFly improves both navigation performance and trajectory quality.
  arXiv  Detail & Related papers  (2026-06-30T13:33:48Z)
• Think Like a Pilot: Fine-Grained Long-Horizon UAV Navigation [22.062997228195815]
  Language-guided UAV agents must execute long-horizon semantic instructions while producing smooth, physically feasible continuous flight commands.<n>We introduce textbfFLIGHT, a textbfFine-grained textbfLong-horizon textbfInstruction-textbfGuided benchmark for textbfHybrid UAV navigation and reasoning textbfTasks.<n>To endow the UAV agent with the capability of real-time in-flight reasoning over task execution status and mission planning, we
  arXiv  Detail & Related papers  (2026-06-05T02:23:05Z)
• SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation [19.9336847486232]
  We introduce SEDualVLN, a spatially-enhanced dual-system Vision-Language Navigation framework.<n>System 1 is a VLM model enhanced with both global and local spatial awareness, used for action generation.<n>System 2 integrates a general MLLM with a mapping module, wherein the MLLM plans waypoints by leveraging top-down views of the real-time 3D map.
  arXiv  Detail & Related papers  (2026-05-17T04:12:56Z)
• MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving [54.57163800903507]
  We present MindVLA-U1, the first unified streaming VLA architecture for autonomous driving.<n>A unified VLM backbone produces AR language tokens and flow-matching continuous action trajectories in a single forward pass over one shared representation.<n>On the long-tail WOD-E2E benchmark, MindVLA-U1 surpasses experienced human drivers for the first time.
  arXiv  Detail & Related papers  (2026-05-12T18:09:42Z)
• History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation [18.716145266309802]
  Vision-Language Navigation (LNV) enables robots to follow natural-language instructions in visually grounded environments, serving as a key capability for embodied robotic systems.<n>Recent Vision-Language-Action-Models have demonstrated strong navigation performance, but their computational latency that limits real-time deployment.<n>We propose a training-free vision-language framework tailored to VLN-based VLN.
  arXiv  Detail & Related papers  (2026-03-06T17:03:16Z)
• AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge [49.66156306240961]
  High latency breaks the control loop, rendering powerful models unsafe for real-time deployment.<n>We propose AsyncVLA, an asynchronous control framework that decouples semantic reasoning from reactive execution.<n>AsyncVLA achieves a 40% higher success rate than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-13T21:31:19Z)
• Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation [45.54638103934175]
  We propose DualVLN, a vision-language navigation system that integrates high-level reasoning with low-level action execution.<n>System 1 "moves fast" by leveraging both explicit pixel goals and latent features from System 2 to generate smooth and accurate trajectories.<n>System outperforms prior methods across all VLN benchmarks and real-world experiments demonstrate robust long-horizon planning and real-time adaptability.
  arXiv  Detail & Related papers  (2025-12-09T02:29:36Z)
• DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation [73.80968452950854]
  Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces.<n>Existing VLN-CE approaches typically use a two-stage waypoint planning framework.<n>We propose DAgger Diffusion Navigation (DifNav) as an end-to-end optimized VLN-CE policy.
  arXiv  Detail & Related papers  (2025-08-13T02:51:43Z)
• VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning [77.34267241692706]
  Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions.<n>We propose VLN-R1, an end-to-end framework that leverages Large Vision-Language Models (LVLM) to directly translate egocentric video streams into continuous navigation actions.
  arXiv  Detail & Related papers  (2025-06-20T17:59:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.