Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

DiPGrasp: Parallel Local Searching for Efficient Differentiable Grasp Planning

Wenqiang Xu, Jieyi Zhang, Tutian Tang, Zhenjun Yu, Yutong Li, Cewu Lu

TL;DR

DiPGrasp introduces a fast, differentiable grasp planner for high-DOF dexterous hands by coupling a force-based, differentiable surface-matching metric with gradient-based optimization and parallel sampling. It supports multiple gripper DOFs, provides collision-aware optimization through a barrier term and simple collision checks, and leverages a gripper weighting map to bias toward palmar and fingertip regions. The authors validate design through three applications—grasp dataset construction, mask-conditioned planning, and pose refinement—demonstrating faster search and higher-quality grasps than baselines, with real-world tests on Barrett and Schunk SVH hands. The work highlights practical impact for fast grasp generation, dataset production, and integration with learning-based perception systems, while also outlining avenues for robustness and broader differentiable manipulation frameworks.

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}.

DiPGrasp: Parallel Local Searching for Efficient Differentiable Grasp Planning

TL;DR

DiPGrasp introduces a fast, differentiable grasp planner for high-DOF dexterous hands by coupling a force-based, differentiable surface-matching metric with gradient-based optimization and parallel sampling. It supports multiple gripper DOFs, provides collision-aware optimization through a barrier term and simple collision checks, and leverages a gripper weighting map to bias toward palmar and fingertip regions. The authors validate design through three applications—grasp dataset construction, mask-conditioned planning, and pose refinement—demonstrating faster search and higher-quality grasps than baselines, with real-world tests on Barrett and Schunk SVH hands. The work highlights practical impact for fast grasp generation, dataset production, and integration with learning-based perception systems, while also outlining avenues for robustness and broader differentiable manipulation frameworks.

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}.
Paper Structure (34 sections, 9 equations, 5 figures, 4 tables, 1 algorithm)

This paper contains 34 sections, 9 equations, 5 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Analytical Dexterous Grasp Planner
  4. Data-driven Dexterous Grasp Planner
  5. Force-based Surface Matching Metric
  6. Geometry-based Surface Matching
  7. Force-based Surface Matching
  8. DiPGrasp
  9. Optimizing Grasp Pose with A Gradient-based Solver
  10. Collision Handling
  11. Barrier Term
  12. Collision Check
  13. Parallel Sampling
  14. Gripper Weighting Map
  15. Experiments
  16. ...and 19 more sections

Figures (5)

  • Figure 1: DiPGrasp can (a) work with robot grippers with different DOFs. (b-c) It can produce high-DOF grasp poses efficiently from the observed point cloud and guide the execution in the real world.
  • Figure 2: DiPGrasp pipeline. DiPGrasp takes a point cloud with normal as input. It first samples locations on the point cloud (red dot) and initializes the pose accordingly. Then it operates the differentiable optimization process to generate the grasps.
  • Figure 3: (a) Collision check. Some points on the object surface are in collision (in red) with the bounding box, which represents the fingertip. (b) Left: Gripper weighting map can be automatically generated by ray casting. Right: Finger links like fingertips can easily be singled out according to the kinematic structure. (Darker area means bigger weight)
  • Figure 4: Grasp planning results. Upper: Original object models. Middle: Sampled grasp planning results for visualization. The grasp poses in the display are randomly selected from the valid grasp poses in the Bottom row. Bottom: Distribution of the grasp planning results. Green means a valid grasp is found towards this point. Black means no valid grasp found.
  • Figure 5: Pose refinement. Even though the neural network prediction is extremely coarse, we still can progressively make it a better grasp with DiPGrasp.