Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimator

TL;DR

This paper introduces a fast, differentiable force closure estimator for grasp synthesis that generates diverse, stable grasps with arbitrary hand structures without training data, overcoming limitations of existing methods.

Contribution

It presents a novel, efficient force closure estimation method that enables optimization-based grasp synthesis for arbitrary hand structures without requiring training data.

Findings

The method tests force closure within milliseconds.

It effectively synthesizes diverse, stable grasps.

Validated across six different experimental settings.

Abstract

Existing grasp synthesis methods are either analytical or data-driven. The former one is oftentimes limited to specific application scope. The latter one depends heavily on demonstrations, thus suffers from generalization issues; e.g., models trained with human grasp data would be difficult to transfer to 3-finger grippers. To tackle these deficiencies, we formulate a fast and differentiable force closure estimation method, capable of producing diverse and physically stable grasps with arbitrary hand structures, without any training data. Although force closure has commonly served as a measure of grasp quality, it has not been widely adopted as an optimization objective for grasp synthesis primarily due to its high computational complexity; in comparison, the proposed differentiable method can test a force closure within milliseconds. In experiments, we validate the proposed method's efficacy in 6 different settings.