Research

Paper

TESTING March 20, 2026

HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks

Authors

Jingyu Guo, Ziye Chen, Ziwen Li, Zhengqing Gao, Jiaxin Huang, Hanlue Zhang, Fengming Huang, Yu Yao, Tongliang Liu, Mingming Gong

Abstract

Existing UAV vision-language navigation (VLN) benchmarks have enabled language-guided flight, but they largely focus on long, step-wise route descriptions with goal-centric evaluation, making them less diagnostic for real operations where brief, high-level commands must be grounded into safe multi-stage behaviors. We present HUGE-Bench, a benchmark for High-Level UAV Vision-Language-Action (HL-VLA) tasks that tests whether an agent can interpret concise language and execute complex, process-oriented trajectories with safety awareness. HUGE-Bench comprises 4 real-world digital twin scenes, 8 high-level tasks, and 2.56M meters of trajectories, and is built on an aligned 3D Gaussian Splatting (3DGS)-Mesh representation that combines photorealistic rendering with collision-capable geometry for scalable generation and collision-aware evaluation. We introduce process-oriented and collision-aware metrics to assess process fidelity, terminal accuracy, and safety. Experiments on representative state-of-the-art VLA models reveal significant gaps in high-level semantic completion and safe execution, highlighting HUGE-Bench as a diagnostic testbed for high-level UAV autonomy.

Metadata

arXiv ID: 2603.19822
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-20
Fetched: 2026-03-23 16:54

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.19822v1</id>\n    <title>HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks</title>\n    <updated>2026-03-20T10:08:42Z</updated>\n    <link href='https://arxiv.org/abs/2603.19822v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.19822v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Existing UAV vision-language navigation (VLN) benchmarks have enabled language-guided flight, but they largely focus on long, step-wise route descriptions with goal-centric evaluation, making them less diagnostic for real operations where brief, high-level commands must be grounded into safe multi-stage behaviors. We present HUGE-Bench, a benchmark for High-Level UAV Vision-Language-Action (HL-VLA) tasks that tests whether an agent can interpret concise language and execute complex, process-oriented trajectories with safety awareness. HUGE-Bench comprises 4 real-world digital twin scenes, 8 high-level tasks, and 2.56M meters of trajectories, and is built on an aligned 3D Gaussian Splatting (3DGS)-Mesh representation that combines photorealistic rendering with collision-capable geometry for scalable generation and collision-aware evaluation. We introduce process-oriented and collision-aware metrics to assess process fidelity, terminal accuracy, and safety. Experiments on representative state-of-the-art VLA models reveal significant gaps in high-level semantic completion and safe execution, highlighting HUGE-Bench as a diagnostic testbed for high-level UAV autonomy.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-20T10:08:42Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Jingyu Guo</name>\n    </author>\n    <author>\n      <name>Ziye Chen</name>\n    </author>\n    <author>\n      <name>Ziwen Li</name>\n    </author>\n    <author>\n      <name>Zhengqing Gao</name>\n    </author>\n    <author>\n      <name>Jiaxin Huang</name>\n    </author>\n    <author>\n      <name>Hanlue Zhang</name>\n    </author>\n    <author>\n      <name>Fengming Huang</name>\n    </author>\n    <author>\n      <name>Yu Yao</name>\n    </author>\n    <author>\n      <name>Tongliang Liu</name>\n    </author>\n    <author>\n      <name>Mingming Gong</name>\n    </author>\n  </entry>"
}