NeuralGrasps: Learning Implicit Representations for Grasps of Multiple Robotic Hands

TL;DR

NeuralGrasps introduces a neural implicit representation that encodes and transfers grasping skills across multiple robotic hands, enabling improved grasp transfer, learning from humans, and 6D pose estimation from partial data.

Contribution

It proposes a shared latent space for grasps of different robotic hands using implicit 3D shape representations, facilitating grasp transfer and real-world grasping applications.

Findings

Shared latent space effectively encodes grasps across multiple hands.

Grasp transfer between different robotic hands is successfully demonstrated.

Implicit shape representations improve 6D pose estimation from partial data.

Abstract

We introduce a neural implicit representation for grasps of objects from multiple robotic hands. Different grasps across multiple robotic hands are encoded into a shared latent space. Each latent vector is learned to decode to the 3D shape of an object and the 3D shape of a robotic hand in a grasping pose in terms of the signed distance functions of the two 3D shapes. In addition, the distance metric in the latent space is learned to preserve the similarity between grasps across different robotic hands, where the similarity of grasps is defined according to contact regions of the robotic hands. This property enables our method to transfer grasps between different grippers including a human hand, and grasp transfer has the potential to share grasping skills between robots and enable robots to learn grasping skills from humans. Furthermore, the encoded signed distance functions of objects and grasps in our implicit representation can be used for 6D object pose estimation with grasping contact optimization from partial point clouds, which enables robotic grasping in the real world.