Grasping by Hanging: a Learning-Free Grasping Detection Method for Previously Unseen Objects

TL;DR

This paper introduces a learning-free, three-stage grasping detection method that enables robots to pick up previously unseen objects by analyzing hanging mechanics, detecting 6D poses, and ranking grasp candidates, outperforming learning-based methods.

Contribution

The proposed approach is a novel learning-free method that predicts grasping poses without training data, closely mimicking human natural grasping actions for unseen objects.

Findings

Higher grasping accuracy and stability than state-of-the-art methods

Effective on thin and flat objects

Eliminates need for training data

Abstract

This paper proposes a novel learning-free three-stage method that predicts grasping poses, enabling robots to pick up and transfer previously unseen objects. Our method first identifies potential structures that can afford the action of hanging by analyzing the hanging mechanics and geometric properties. Then 6D poses are detected for a parallel gripper retrofitted with an extending bar, which when closed forms loops to hook each hangable structure. Finally, an evaluation policy qualities and rank grasp candidates for execution attempts. Compared to the traditional physical model-based and deep learning-based methods, our approach is closer to the human natural action of grasping unknown objects. And it also eliminates the need for a vast amount of training data. To evaluate the effectiveness of the proposed method, we conducted experiments with a real robot. Experimental results indicate that the grasping accuracy and stability are significantly higher than the state-of-the-art learning-based method, especially for thin and flat objects.