DextrAH-G: Pixels-to-Action Dexterous Arm-Hand Grasping with Geometric Fabrics

Links

Key Takeaway

DextrAH-G is a safe, continuously reacting pixels-to-action policy that achieves state-of-the-art dexterous grasping in the real world and was trained entirely in simulation using RL and teacher-student distillation with a geometric fabric controller.

Abstract

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 depth inputs, generalizing across object geometry.

Grasp-and-Transport Videos (all 1x speed)

Continuous Grasp-and-Transport of 28 Unique Objects (1x speed)

BibTeX

@article{anonymous}