基于视觉强化学习的仿真人形机器人涌现式主动感知与灵巧性
Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning
AI总结：
本研究提出视觉驱动的仿真人形机器人全身灵巧控制框架PDC，仅靠第一视角视觉无需特权状态信息，单个策略即可完成多项家务任务，还能涌现主动搜索类人行为，为相关领域打通感知-行动循环提供关键支撑。
摘要：
人类行为从根本上由视觉感知塑造——我们与世界互动的能力依赖于主动收集相关信息并相应调整自身动作。寻找物体、伸手取物以及手眼协调等行为会自然地从我们的感知系统结构中涌现。受这些原理启发，我们提出了Perceptive Dexterous Control（感知灵巧控制，简称PDC），这是一种用于仿真人形机器人的视觉驱动全身灵巧控制框架。PDC仅依靠第一视角视觉来指定任务，能够通过视觉线索实现物体搜索、目标放置和技能选择，无需依赖特权状态信息（例如物体的3D位置与几何形状）。这种“感知即接口”的范式支持学习单个策略来执行多项家务任务，包括伸手、抓取、放置以及铰接物体操作。我们还表明，通过强化学习从头训练可以产生主动搜索等涌现行为。这些结果证明了视觉驱动控制与复杂任务如何催生类人行为，并且可作为打通感知-行动循环的关键要素，应用于动画、机器人技术和具身AI领域。
英文摘要：
Human behavior is fundamentally shaped by visual perception -- our ability to interact with the world depends on actively gathering relevant information and adapting our movements accordingly. Behaviors like searching for objects, reaching, and hand-eye coordination naturally emerge from the structure of our sensory system. Inspired by these principles, we introduce Perceptive Dexterous Control (PDC), a framework for vision-driven dexterous whole-body control with simulated humanoids. PDC operates solely on egocentric vision for task specification, enabling object search, target placement, and skill selection through visual cues, without relying on privileged state information (e.g., 3D object positions and geometries). This perception-as-interface paradigm enables learning a single policy to perform multiple household tasks, including reaching, grasping, placing, and articulated object manipulation. We also show that training from scratch with reinforcement learning can produce emergent behaviors such as active search. These results demonstrate how vision-driven control and complex tasks induce human-like behaviors and can serve as the key ingredients in closing the perception-action loop for animation, robotics, and embodied AI.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
