Benchmark Radar
AI BENCHMARK PROFILE

SpatialUAV

General AIMultimodal PerceptionHyu-Zhang

Evaluates spatial intelligence in low-altitude UAV scenarios across 14 task types covering semantic discrimination, spatial relations, collaboration, and motion understanding, with 7 input configurations and 9 answer formats.

Released
2026-06-26
Readiness
Runnable
Primary field
General AI

Why it matters

Targets under-evaluated 3D spatial and multi-view reasoning in UAV benchmarks, revealing bottlenecks in cross-view association and geometric reasoning for current VLMs.

Motivation

Spatial intelligence is essential for low-altitude unmanned aerial vehicle (UAV) perception, collaboration, and navigation.

Primary resources

Benchmark Radar records only publicly supported details and links back to primary sources for verification.