SOURCE-LINKED INTELLIGENCE

ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Active perception is essential for robotic manipulation when fixed viewpoints leave task-relevant information occluded or unobserved. However, enabling vision-language-action (VLA) models to reason across changing viewpoints and actively acquire informative observations remains challenging. We present ActiveScale, a framework that advances active perception through coordinated model, data, and hardware designs. Our model augments a VLA with historical video observations and explicit camera-pose supervision, using per-frame pose tokens and a lightweight prediction head to associate observations

Read original source ↗ Open in workspace

recordType

paper

region

Global