RobotFingerPrint: Unified Gripper Coordinate Space for Multi-Gripper Grasp Synthesis and Transfer

TL;DR

This paper presents UGCS, a unified spherical coordinate-based grasp representation that enables effective grasp synthesis and transfer across different robot grippers and objects, validated through extensive experiments.

Contribution

Introduction of UGCS, a novel unified coordinate space for grasp synthesis and transfer across diverse grippers and objects, enhancing generalization and transferability.

Findings

Effective grasp synthesis with stable, diverse grasps demonstrated in simulation and real-world.

Successful grasp transfer across different grippers and objects, including human demonstrations.

UGCS improves grasp planning flexibility and transfer accuracy.

Abstract

We introduce a novel grasp representation named the Unified Gripper Coordinate Space (UGCS) for grasp synthesis and grasp transfer. Our representation leverages spherical coordinates to create a shared coordinate space across different robot grippers, enabling it to synthesize and transfer grasps for both novel objects and previously unseen grippers. The strength of this representation lies in the ability to map palm and fingers of a gripper and the unified coordinate space. Grasp synthesis is formulated as predicting the unified spherical coordinates on object surface points via a conditional variational autoencoder. The predicted unified gripper coordinates establish exact correspondences between the gripper and object points, which is used to optimize grasp pose and joint values. Grasp transfer is facilitated through the point-to-point correspondence between any two (potentially unseen) grippers and solved via a similar optimization. Extensive simulation and real-world experiments showcase the efficacy of the unified grasp representation for grasp synthesis in generating stable and diverse grasps. Similarly, we showcase real-world grasp transfer from human demonstrations across different objects.