Grasping by parallel shape matching

TL;DR

This paper introduces a fast, robust shape-matching approach for robotic grasping that leverages GPU parallelization and a novel cost function, achieving high success rates and low computation times.

Contribution

It formulates grasping as a shape matching problem optimized with AS-ICP, incorporating tool center point and collision checking for improved robustness.

Findings

87.3% grasp success rate on diverse objects

Average computation time of 0.926 seconds

Effective in real-world robotic manipulation scenarios

Abstract

Grasping is essential in robotic manipulation, yet challenging due to object and gripper diversity and real-world complexities. Traditional analytic approaches often have long optimization times, while data-driven methods struggle with unseen objects. This paper formulates the problem as a rigid shape matching between gripper and object, which optimizes with Annealed Stein Iterative Closest Point (AS-ICP) and leverages GPU-based parallelization. By incorporating the gripper's tool center point and the object's center of mass into the cost function and using a signed distance field of the gripper for collision checking, our method achieves robust grasps with low computational time. Experiments with the Kinova KG3 gripper show an 87.3% success rate and 0.926 s computation time across various objects and settings, highlighting its potential for real-world applications.