LEAP: Learning Emergent Active Perception for Quadruped Navigation

2026-09-15

AI Summary

本文提出LEAP方法，通过目标导向导航和自我中心信念图来学习主动感知，以解决四足机器人在危险地形中导航的问题。

Abstract

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 visually. We then propose an architecture for navigation policies with active perception, and train them on a terrain curriculum where task pressure alone leads to the emergence of gaze control. Key to this emergence, LEAP works on a gaze-invariant representation that integrates depth images into egocentric belief maps. We validate its performance in held-out evaluation scenarios, where it achieves a 92.7% success rate, compared to 74.2% for scripted or 34.5% for passive perception, and comes within 4.6 points of a privileged oracle. We validate that LEAP navigation policies, unchanged, can be directly applied to steering quadrupedal locomotion policies in physics simulation.

Problem

• active perception
• quadruped navigation
• goal-oriented navigation
• hazardous terrains

Innovation

• active perception
• gaze-invariant representation
• emergence
• quadruped navigation
• terrain curriculum