A pivotal challenge in robotics is achieving fast, safe, and robust dexterous grasping across a diverse range of objects, an important goal within industrial applications. However, existing methods often have very limited speed, dexterity, and generality, along with limited or no hardware safety guarantees. In this work, we introduce DextrAH-G, a depth-based dexterous grasping policy trained entirely in simulation that combines reinforcement learning, geometric fabrics, and teacher-student distillation. We address key challenges in joint arm-hand policy learning, such as high-dimensional observation and action spaces, the sim2real gap, collision avoidance, and hardware constraints. DextrAH-G enables a 23 motor arm-hand robot to safely and continuously grasp and transport a large variety of objects at high speed using multi-modal inputs including depth images, allowing generalization across object geometry. Videos at https://sites.google.com/view/dextrah-g.

翻译：机器人学中的一个关键挑战是实现快速、安全且鲁棒的灵巧抓取，以应对多样化的物体，这是工业应用中的一个重要目标。然而，现有方法通常在速度、灵巧性和泛化能力方面非常有限，并且对硬件安全性缺乏或仅有有限的保证。在本工作中，我们提出了DextrAH-G，这是一种完全在仿真中训练的基于深度的灵巧抓取策略，它结合了强化学习、几何织物和师生蒸馏。我们解决了联合臂手策略学习中的关键挑战，例如高维观测和动作空间、仿真到现实的差距、碰撞避免以及硬件约束。DextrAH-G使得一个具有23个电机的臂手机器人能够安全、连续地高速抓取和运输大量不同物体，并利用包括深度图像在内的多模态输入，从而实现对物体几何形状的泛化。视频请访问 https://sites.google.com/view/dextrah-g。