One of the most important, yet challenging, skills for a dexterous robot is grasping a diverse range of objects. Much of the prior work has been limited by speed, generality, or reliance on depth maps and object poses. In this paper, we introduce DextrAH-RGB, a system that can perform dexterous arm-hand grasping end-to-end from RGB image input. We train a privileged fabric-guided policy (FGP) in simulation through reinforcement learning that acts on a geometric fabric controller to dexterously grasp a wide variety of objects. We then distill this privileged FGP into a RGB-based FGP strictly in simulation using photorealistic tiled rendering. To our knowledge, this is the first work that is able to demonstrate robust sim2real transfer of an end2end RGB-based policy for complex, dynamic, contact-rich tasks such as dexterous grasping. DextrAH-RGB is competitive with depth-based dexterous grasping policies, and generalizes to novel objects with unseen geometry, texture, and lighting conditions in the real world. Videos of our system grasping a diverse range of unseen objects are available at \url{this https URL}.
View on arXiv@article{singh2025_2412.01791,
title={ DextrAH-RGB: Visuomotor Policies to Grasp Anything with Dexterous Hands },
author={ Ritvik Singh and Arthur Allshire and Ankur Handa and Nathan Ratliff and Karl Van Wyk },
journal={arXiv preprint arXiv:2412.01791},
year={ 2025 }
}