GraspXL: Generating Grasping Motions for Diverse Objects at Scale

TL;DR

GraspXL is a scalable policy learning framework that synthesizes diverse, high-quality grasping motions for a wide range of objects without requiring expensive 3D hand-object interaction data.

Contribution

It unifies multiple grasping objectives across diverse objects and hand morphologies, enabling robust motion generation without 3D interaction data, and scales to over 500k unseen objects.

Findings

Achieves 82.2% success rate on unseen objects

Generates diverse grasps per object

Works with different dexterous hands

Abstract

Human hands possess the dexterity to interact with diverse objects such as grasping specific parts of the objects and/or approaching them from desired directions. More importantly, humans can grasp objects of any shape without object-specific skills. Recent works synthesize grasping motions following single objectives such as a desired approach heading direction or a grasping area. Moreover, they usually rely on expensive 3D hand-object data during training and inference, which limits their capability to synthesize grasping motions for unseen objects at scale. In this paper, we unify the generation of hand-object grasping motions across multiple motion objectives, diverse object shapes and dexterous hand morphologies in a policy learning framework GraspXL. The objectives are composed of the graspable area, heading direction during approach, wrist rotation, and hand position. Without requiring any 3D hand-object interaction data, our policy trained with 58 objects can robustly synthesize diverse grasping motions for more than 500k unseen objects with a success rate of 82.2%. At the same time, the policy adheres to objectives, which enables the generation of diverse grasps per object. Moreover, we show that our framework can be deployed to different dexterous hands and work with reconstructed or generated objects. We quantitatively and qualitatively evaluate our method to show the efficacy of our approach. Our model, code, and the large-scale generated motions are available at https://eth-ait.github.io/graspxl/.