SOURCE-LINKED INTELLIGENCE

LEAP: Learning Emergent Active Perception for Quadruped Navigation

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Active perception allows autonomous agents to select their viewpoints rather than passively process the viewpoints given to them, enabling them to target where to reduce uncertainty about their environment. Learned systems typically encourage this behavior with hand-designed proxy objectives, such as coverage or curiosity bonuses, that may conflict with the task. In this work, we propose a method to learn emergent active perception (LEAP) without augmentation of the task objective. We formulate the problem of goal-oriented navigation over hazardous terrains with goals that must be discovered v

Read original source ↗ Open in workspace

recordType

paper

region

Global