Dexterous grasp data augmentation based on grasp synthesis with fingertip workspace cloud and contact-aware sampling
🤖 AI Summary
Efficiently generating grasp data adaptable to arbitrary dexterous hand morphologies remains a key bottleneck in data-driven grasping. This work proposes a grasp data augmentation framework leveraging a small number of teleoperated demonstrations: it employs AutoWS to automatically generate fingertip workspace point clouds that inherently encode hand-structure information, thereby circumventing inverse kinematics computation; combined with a contact-aware sampling strategy (FSG), it enables human-like, real-time grasp pose generation. The approach is highly generalizable, requiring no redesign for specific hand architectures. In YCB object grasping experiments, it significantly outperforms existing methods, achieving notable improvements in both successful grasp rate and generation speed.
Application Category
📝 Abstract
Robotic grasping is a fundamental yet crucial component of robotic applications, as effective grasping often serves as the starting point for various tasks. With the rapid advancement of neural networks, data-driven approaches for robotic grasping have become mainstream. However, efficiently generating grasp datasets for training remains a bottleneck. This is compounded by the diverse structures of robotic hands, making the design of generalizable grasp generation methods even more complex. In this work, we propose a teleoperation-based framework to collect a small set of grasp pose demonstrations, which are augmented using FSG--a Fingertip-contact-aware Sampling-based Grasp generator. Based on the demonstrated grasp poses, we propose AutoWS, which automatically generates structured workspace clouds of robotic fingertips, embedding the hand structure information directly into the clouds to eliminate the need for inverse kinematics calculations. Experiments on grasping the YCB objects show that our method significantly outperforms existing approaches in both speed and valid pose generation rate. Our framework enables real-time grasp generation for hands with arbitrary structures and produces human-like grasps when combined with demonstrations, providing an efficient and robust data augmentation tool for data-driven grasp training.
Problem
Research questions and friction points this paper is trying to address.
dexterous grasp
data augmentation
grasp synthesis
robotic hand
grasp dataset
Innovation
Methods, ideas, or system contributions that make the work stand out.
grasp synthesis
fingertip workspace cloud
contact-aware sampling
data augmentation
teleoperation-based demonstration
🔎 Similar Papers
No similar papers found.
