DiPGrasp: Parallel Local Searching for Efficient Differentiable Grasp Planning

TL;DR

DiPGrasp is a fast, differentiable grasp planner that uses parallel local search and gradient optimization, enabling efficient grasp planning across various applications and robot hand types.

Contribution

This work introduces DiPGrasp, a novel parallel local search-based grasp planner that is fast, differentiable, and adaptable to different robot grippers, filling a gap in existing grasp planning methods.

Findings

Outperforms classic planners in speed and quality for dataset generation

Enables instant mask-conditioned grasp planning from 3D perception models

Effectively refines neural network-based grasp predictions in real-world experiments

Abstract

Grasp planning is an important task for robotic manipulation. Though it is a richly studied area, a standalone, fast, and differentiable grasp planner that can work with robot grippers of different DOFs has not been reported. In this work, we present DiPGrasp, a grasp planner that satisfies all these goals. DiPGrasp takes a force-closure geometric surface matching grasp quality metric. It adopts a gradient-based optimization scheme on the metric, which also considers parallel sampling and collision handling. This not only drastically accelerates the grasp search process over the object surface but also makes it differentiable. We apply DiPGrasp to three applications, namely grasp dataset construction, mask-conditioned planning, and pose refinement. For dataset generation, as a standalone planner, DiPGrasp has clear advantages over speed and quality compared with several classic planners. For mask-conditioned planning, it can turn a 3D perception model into a 3D grasp detection model instantly. As a pose refiner, it can optimize the coarse grasp prediction from the neural network, as well as the neural network parameters. Finally, we conduct real-world experiments with the Barrett hand and Schunk SVH 5-finger hand. Video and supplementary materials can be viewed on our website: \url{https://dipgrasp.robotflow.ai}.