Last-Meter Precision Navigation for UAVs: A Diffusion-Refined Aerial Visual Servoing Approach

• URL: http://arxiv.org/abs/2607.04352v1
• Date: Sun, 05 Jul 2026 15:16:44 GMT
• Title: Last-Meter Precision Navigation for UAVs: A Diffusion-Refined Aerial Visual Servoing Approach
• Abstract summary: Last-meter precision navigation for UAVs is challenging due to scale ambiguity, rotation discontinuities, and the need for fine-grained spatial reasoning.<n>We propose DreamNav, a coarse-to-fine diffusion-refined aerial visual servoing framework.<n>Experiments show DreamNav outperforms strong visual servoing and foundation model baselines in accuracy and generalization, with zero-shot transfer to unseen scenes.
• Score: 18.42619895752036
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we study the last-meter precision navigation for UAVs, e.g., autonomously reaching a target within the final 10 meters using monocular vision. This task is challenging due to scale ambiguity, rotation discontinuities, and the need for fine-grained spatial reasoning. Existing methods often fail under large viewpoint changes or lack generalization to unseen environments. To this end, we propose DreamNav, a coarse-to-fine diffusion-refined aerial visual servoing framework. In the first coarse-estimation stage, a robust regression policy employs a trigonometric parameterization to predict rotation by jointly modeling sine and cosine components, effectively mitigating optimization instabilities caused by angular periodicity. Given this coarse estimate, the second diffusion-refined stage utilizes a pre-trained world model to simulate future visual observations for candidate actions, selecting the trajectory that minimizes visual discrepancy with the target through a process of visual imagination. To support rigorous evaluation, we contribute PairUAV, a large-scale benchmark comprising 4.8 million image pairs across 72 scenes, curated from the University-1652 dataset. Extensive experiments show DreamNav outperforms strong visual servoing and foundation model baselines in accuracy and generalization, with zero-shot transfer to unseen scenes.

Related papers

• AirAlign: Geometry-Aware Relative Pose Alignment for UAV Last-Meter Navigation [20.21278599561095]
  AirAlign is a framework for RGB-only image-pair relative pose alignment for UAVs.<n>AirAlign uses a pretrained visual geometry reconstruction model as the backbone.<n>Experiments on the PairUAV challenge demonstrate the effectiveness and robustness of our method.
  arXiv  Detail & Related papers  (2026-08-22T11:32:41Z)
• Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation [24.310993695214094]
  We propose SWAM (Spatial-perceiving World Action Model), a task-centric joint observation-action generation framework.<n>Given start and goal RGB observations, SWAM performs single-pass inference to simultaneously generate intermediate RGB-D sequences and corresponding action trajectories.<n>We show that SWAM significantly outperforms state-of-the-art two-stage planners in success rate, trajectory accuracy, and inference efficiency.
  arXiv  Detail & Related papers  (2026-06-29T07:43:47Z)
• WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation [31.539730066120374]
  Visual navigation requires generating smooth and collision-free trajectories under complex geometric and physical constraints.<n>We propose WAM-Nav, a Latent World-Action Model for embodied visual navigation that jointly learns action generation and latent visual foresight.
  arXiv  Detail & Related papers  (2026-06-03T14:05:19Z)
• AgenticDiffusion: Agentic Diffusion-based Path Planning for Vision-Based UAV Navigation [2.186077977059593]
  Indoor UAV navigation requires efficient exploration, scene understanding, and reliable trajectory execution under limited field-of-view observations.<n>We propose AgenticDiffusion, a multi-view UAV navigation framework that coordinates language-guided reasoning, open-vocabulary target grounding, vision-based diffusion planning, and NMPC.<n>The framework was validated in four real-world UAV navigation scenarios involving adaptive viewpoint selection, multi-stage mission execution, long-horizon navigation, and safe landing-site selection.
  arXiv  Detail & Related papers  (2026-06-02T18:18:35Z)
• Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation [51.286599397552756]
  We present Bearing-UAV, a vision-driven cross-view navigation method that jointly predicts UAV absolute location and heading from neighboring features.<n>We also present Bearing-UAV-90k, a benchmark for evaluating cross-view localization and navigation.
  arXiv  Detail & Related papers  (2026-03-23T16:17:39Z)
• Visual Autoregressive Modelling for Monocular Depth Estimation [69.01449528371916]
  We propose a monocular depth estimation method based on visual autoregressive ( VAR) priors.<n>Our method adapts a large-scale text-to-image VAR model and introduces a scale-wise conditional upsampling mechanism.<n>We report state-of-the-art performance in indoor benchmarks under constrained training conditions, and strong performance when applied to outdoor datasets.
  arXiv  Detail & Related papers  (2025-12-27T17:08:03Z)
• Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space [48.19308247102762]
  We propose ANWM, an aerial navigation world model that predicts future visual observations conditioned on past frames and actions.<n> ANWM is trained on 4-DoF UAV trajectories and introduces a physics-inspired module: Future Frame Projection.<n> Empirical results demonstrate that ANWM significantly outperforms existing world models in long-distance visual forecasting and improves UAV navigation success rates in large-scale environments.
  arXiv  Detail & Related papers  (2025-12-26T06:22:39Z)
• Extrapolated Urban View Synthesis Benchmark [53.657271730352214]
  Photo simulators are essential for the training and evaluation of vision-centric autonomous vehicles (AVs)<n>At their core is Novel View Synthesis (NVS), a capability that generates diverse unseen viewpoints to accommodate the broad and continuous pose distribution of AVs.<n>Recent advances in radiance fields, such as 3D Gaussian Splatting, achieve photorealistic rendering at real-time speeds and have been widely used in modeling large-scale driving scenes.<n>We will release the data to help advance self-driving and urban robotics simulation technology.
  arXiv  Detail & Related papers  (2024-12-06T18:41:39Z)
• Open-World Drone Active Tracking with Goal-Centered Rewards [62.21394499788672]
  Drone Visual Active Tracking aims to autonomously follow a target object by controlling the motion system based on visual observations.<n>We propose DAT, the first open-world drone active air-to-ground tracking benchmark.<n>We also propose GC-VAT, which aims to improve the performance of drone tracking targets in complex scenarios.
  arXiv  Detail & Related papers  (2024-12-01T09:37:46Z)
• Vectorized Representation Dreamer (VRD): Dreaming-Assisted Multi-Agent Motion-Forecasting [2.2020053359163305]
  We introduce VRD, a vectorized world model-inspired approach to the multi-agent motion forecasting problem. Our method combines a traditional open-loop training regime with a novel dreamed closed-loop training pipeline. Our model achieves state-of-the-art performance on the single prediction miss rate metric.
  arXiv  Detail & Related papers  (2024-06-20T15:34:17Z)
• RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation [50.35403070279804]
  3D occupancy prediction is an emerging task that aims to estimate the occupancy states and semantics of 3D scenes using multi-view images. We propose RadOcc, a Rendering assisted distillation paradigm for 3D Occupancy prediction.
  arXiv  Detail & Related papers  (2023-12-19T03:39:56Z)
• Distributed Variable-Baseline Stereo SLAM from two UAVs [17.513645771137178]
  In this article, we employ two UAVs equipped with one monocular camera and one IMU each, to exploit their view overlap and relative distance measurements. In order to control the glsuav agents autonomously, we propose a decentralized collaborative estimation scheme. We demonstrate the effectiveness of the approach at high altitude flights of up to 160m, going significantly beyond the capabilities of state-of-the-art VIO methods.
  arXiv  Detail & Related papers  (2020-09-10T12:16:10Z)

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.