DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness
This addresses the problem of universal robotic dexterous grasping for general-purpose embodied intelligent robots, representing a strong specific gain rather than a foundational advancement.
The paper tackles the challenge of generating high-quality grasping poses for dexterous hands across diverse objects by integrating physical constraints into a diffusion-based generative model, achieving state-of-the-art performance on open datasets and introducing a new dataset with over 3.4 million grasping poses for 15k objects.
A dexterous hand capable of grasping any object is essential for the development of general-purpose embodied intelligent robots. However, due to the high degree of freedom in dexterous hands and the vast diversity of objects, generating high-quality, usable grasping poses in a robust manner is a significant challenge. In this paper, we introduce DexGrasp Anything, a method that effectively integrates physical constraints into both the training and sampling phases of a diffusion-based generative model, achieving state-of-the-art performance across nearly all open datasets. Additionally, we present a new dexterous grasping dataset containing over 3.4 million diverse grasping poses for more than 15k different objects, demonstrating its potential to advance universal dexterous grasping. The code of our method and our dataset will be publicly released soon.