外观
论文arXiv 2609.176281 个月前
LEAP：用于四足导航的涌现式主动感知学习
原文链接：LEAP: Learning Emergent Active Perception for Quadruped Navigation（arXiv 2609.17628 · 发布日期：2026-09-15）
LEAP: Learning Emergent Active Perception for Quadruped Navigation
LEAP针对危险地形中需视觉发现目标的导航，通过自我中心信念地图学习主动感知，并在留出场景和物理仿真四足运动中验证。
核心要点
- 主动感知可选择视角降低环境不确定性，但手工代理目标可能与任务冲突。
- LEAP不增设任务目标外奖励，在地形课程训练中仅由任务压力促成凝视控制涌现。
- 方法将深度图整合为自我中心信念地图，形成凝视不变表征以支持导航策略。
- 留出场景成功率92.7%，高于脚本式74.2%和被动感知34.5%，并接近特权oracle。
验证范围与局限：验证范围为留出评估场景，以及物理仿真中直接用于转向四足运动策略。
英文摘要 (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.
作者：Ü. Bora Gökbakan, Stéphane Caron, Philippe Souères
来源
本页事实对应的公开页面，以原文为准。