H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation

Human hands possess remarkable dexterity and have long served as a source of inspiration for robotic manipulation. In this work, we propose a human Hand-Informed visual representation learning framework to solve difficult Dexterous manipulation tasks (H-InDex) with reinforcement learning. Our framework consists of three stages: (i) pre-training representations with 3D human hand pose estimation, (ii) offline adapting representations with self-supervised keypoint detection, and (iii) reinforcement learning with exponential moving average BatchNorm. The last two stages only modify 0.36% parameters of the pre-trained representation in total, ensuring the knowledge from pre-training is maintained to the full extent. We empirically study 12 challenging dexterous manipulation tasks and find that H-InDex largely surpasses strong baseline methods and the recent visual foundation models for motor control. Code is available at yanjieze.com/H-InDex. * Model params: ResNet-50 (24 M), ViT-B (86 M), ViT-S (22 M) Normalized Average Score H-InDex (ResNet-50) RRL (ResNet-50) R3M (ResNet-50) VC-1 (ViT-B) MVP (ViT-S)