Reconfigurable Design for Omni-adaptive Grasp Learning

Fang Wan, Haokun Wang, Jiyuan Wu, Yujia Liu, Sheng Ge +1 more
2/29/2020
cs.ROcs.LG

Official code: bionicdl-sustech/DeepClawBenchmark (13 stars, last commit 2020-05-08).

Abstract

The engineering design of robotic grippers presents an ample design space for optimization towards robust grasping. In this paper, we adopt the reconfigurable design of the robotic gripper using a novel soft finger structure with omni-directional adaptation, which generates a large number of possible gripper configurations by rearranging these fingers. Such reconfigurable design with these omni-adaptive fingers enables us to systematically investigate the optimal arrangement of the fingers towards robust grasping. Furthermore, we adopt a learning-based method as the baseline to benchmark the effectiveness of each design configuration. As a result, we found that a 3-finger and 4-finger radial configuration is the most effective one achieving an average 96\% grasp success rate on seen and novel objects selected from the YCB dataset. We also discussed the influence of the frictional surface on the finger to improve the grasp robustness.

View on arXivView PDF

Code Implementations(1)

bionicdl-sustech/DeepClawBenchmarkOfficial100%
136PythonAug 22, 20196 years ago

Similar Papers

Fin-QD: A Computational Design Framework for Soft Grippers: Integrating MAP-Elites and High-fidelity FEM

87% match2023

Exploiting High Quality Tactile Sensors for Simplified Grasping

86% match2022

Bayesian optimization for robust robotic grasping using a sensorized compliant hand

84% match2024

From Power to Precision: Learning Fine-grained Dexterity for Multi-fingered Robotic Hands

83% match2025

EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment

82% match1 repo132025

DMFC-GraspNet: Differentiable Multi-Fingered Robotic Grasp Generation in Cluttered Scenes

81% match2023

Cite this paper

@article{wan2020reconfigurable,
  title  = {Reconfigurable Design for Omni-adaptive Grasp Learning},
  author = {Fang Wan and Haokun Wang and Jiyuan Wu and Yujia Liu and Sheng Ge and Chaoyang Song},
  year   = {2020},
  eprint = {2003.01582},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2003.01582}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2003.01582.svg)](https://codeofpaper.com/paper/2003.01582)

Discussion