Synthesizing Diverse and Physically Stable Grasps with Arbitrary Hand Structures using Differentiable Force Closure Estimator
This addresses generalization issues in robotic grasp synthesis for various hand designs, though it is incremental as it builds on existing force closure concepts.
The paper tackles the problem of generating diverse and physically stable grasps for arbitrary hand structures by developing a fast and differentiable force closure estimation method, achieving force closure tests within milliseconds without requiring training data.
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.