SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion

• URL: http://arxiv.org/abs/2606.27876v2
• Date: Tue, 30 Jun 2026 06:25:43 GMT
• Title: SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion
• Abstract summary: spatial intelligence is essential for low-altitude unmanned aerial vehicle (UAV) perception, collaboration, and navigation.<n>We introduce SpatialUAV, a real low-altitude UAV benchmark covering semantic discrimination, spatial relation, aerial-aerial collaboration, aerial-ground collaboration, and motion understanding.<n>We show that current models remain far from human-level performance, with pronounced bottlenecks in cross-view association, structured grounding, geometric reasoning, and temporal viewpoint understanding.
• Score: 76.8430169655641
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatial intelligence is essential for low-altitude unmanned aerial vehicle (UAV) perception, collaboration, and navigation. However, existing UAV benchmarks often emphasize image-level recognition, single-view understanding, or narrow answer formats, leaving 3D spatial inference, multi-view collaboration, scene dynamics, and diverse task formulations insufficiently evaluated. To address these gaps, we introduce SpatialUAV, a real low-altitude UAV benchmark comprising 4,331 curated instances across 14 fine-grained task types, covering semantic discrimination, spatial relation, aerial--aerial collaboration, aerial--ground collaboration, and motion understanding. SpatialUAV organizes all samples into a unified visual-input--question--answer schema, while supporting seven input configurations and nine answer formats, including option labels, region identifiers, geometric values, cross-view correspondences, and free-form motion descriptions. To ensure reliable and grounded evaluation, our data construction pipeline integrates detector-assisted regions, depth supervision, metadata-derived rules, extensive manual annotation, blind filtering, and multi-turn human validation, together with task-specific metrics for heterogeneous outputs. Evaluating representative vision-language models across three categories, we show that current models remain far from human-level performance, with pronounced bottlenecks in cross-view association, structured grounding, geometric reasoning, and temporal viewpoint understanding. These results offer empirical guidance for advancing low-altitude UAV spatial intelligence. Code and data are available at https://github.com/Hyu-Zhang/SpatialUAV.

Related papers

• Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory [69.51256305550844]
  We propose PSC-AVDN, a training-free framework that tightly couples a three-stage Parsing-Search-Confirmation reasoning pipeline with a Structured Spatial Memory.<n> PSC-AVDN establishes new state-of-the-art performance in the training-free setting, matching or surpassing several finetuned methods.
  arXiv  Detail & Related papers  (2026-07-13T13:14:20Z)
• Unifying UAV Cross-View Geo-Localization via 3D Geometric Perception [51.687842983240564]
  Cross-view geo-localization for Unmanned Aerial Vehicles (UAVs) remains challenging due to the severe geometric discrepancy between oblique UAV imagery and satellite maps.<n>We propose a geometry-aware UAV geo-localization framework that explicitly models the 3D scene geometry to unify coarse place recognition and fine-grained pose estimation.<n>Our method significantly outperforms state-of-the-art baselines, achieving robust meter-level localization accuracy and improved generalization in complex urban environments.
  arXiv  Detail & Related papers  (2026-04-02T08:08:41Z)
• HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks [73.62053624331227]
  Huge-Bench is a benchmark for High-Level UAV Vision-Language-Action tasks.<n>It comprises 4 real-world digital twin scenes, 8 high-level tasks, and 2.56M meters of trajectories.<n>We introduce process-oriented and collision-aware metrics to assess process fidelity, terminal accuracy, and safety.
  arXiv  Detail & Related papers  (2026-03-20T10:08:42Z)
• UAVScenes: A Multi-Modal Dataset for UAVs [45.752766099526525]
  UAVScenes is a large-scale dataset designed to benchmark various tasks across both 2D and 3D modalities.<n>We enhance this dataset by providing manually labeled semantic annotations for both frame-wise images and LiDAR point clouds.<n>These additions enable a wide range of UAV perception tasks, including segmentation, depth estimation, 6-DoF localization, place recognition, and novel view synthesis.
  arXiv  Detail & Related papers  (2025-07-30T06:29:52Z)
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models [68.46716645478661]
  Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content.<n>Current VLMs excel primarily at egocentric spatial reasoning (from the camera's perspective) but fail to generalize to allocentric viewpoints.<n>We introduce ViewSpatial-Bench, the first comprehensive benchmark designed specifically for multi-viewpoint spatial localization recognition evaluation.
  arXiv  Detail & Related papers  (2025-05-27T17:59:26Z)
• More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV [58.89234732689013]
  CODrone is a comprehensive oriented object detection dataset for UAVs that accurately reflects real-world conditions.<n>It also serves as a new benchmark designed to align with downstream task requirements.<n>We conduct a series of experiments based on 22 classical or SOTA methods to rigorously evaluate CODrone.
  arXiv  Detail & Related papers  (2025-04-28T17:56:02Z)
• AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations [51.44608822712786]
  Visual grounding aims to localize target objects in an image based on natural language descriptions.<n>AerialVG poses new challenges, emphe.g., appearance-based grounding is insufficient to distinguish among multiple visually similar objects.<n>We introduce the first AerialVG dataset, consisting of 5K real-world aerial images, 50K manually annotated descriptions, and 103K objects.
  arXiv  Detail & Related papers  (2025-04-10T15:13:00Z)
• Griffin: Aerial-Ground Cooperative Detection and Tracking Dataset and Benchmark [15.405137983083875]
  Aerial-ground cooperation offers a promising solution by integrating UAVs' aerial views with ground vehicles' local observations.<n>This paper presents a comprehensive solution for aerial-ground cooperative 3D perception through three key contributions.
  arXiv  Detail & Related papers  (2025-03-10T07:00:07Z)
• UAVDB: Point-Guided Masks for UAV Detection and Segmentation [0.03464344220266879]
  We present UAVDB, a new benchmark dataset for UAV detection and segmentation.<n>It is built upon a point-guided weak supervision pipeline.<n>UAVDB captures UAVs at diverse scales, from visible objects to near-single-pixel instances.
  arXiv  Detail & Related papers  (2024-09-09T13:27:53Z)
• UCDNet: Multi-UAV Collaborative 3D Object Detection Network by Reliable Feature Mapping [14.401624713578737]
  Multi-UAV collaborative 3D object detection can perceive and comprehend complex environments. We propose an unparalleled camera-based multi-UAV collaborative 3D object detection paradigm called UCDNet. We show our method increases 4.7% and 10% mAP respectively compared to the baseline.
  arXiv  Detail & Related papers  (2024-06-07T05:27:32Z)
• Self-aligned Spatial Feature Extraction Network for UAV Vehicle Re-identification [3.449626476434765]
  Vehicles with same color and type show extremely similar appearance from the UAV's perspective. Recent works tend to extract distinguishing information by regional features and component features. In order to extract efficient fine-grained features and avoid tedious annotating work, this letter develops an unsupervised self-aligned network.
  arXiv  Detail & Related papers  (2022-01-08T14:25:54Z)

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.