SGDN: Segmentation-Based Grasp Detection Network For Unsymmetrical Three-Finger Gripper

TL;DR

This paper introduces SGDN, a novel pixel-level grasp detection network tailored for unsymmetrical three-finger robotic grippers, utilizing RGB images and a new grasp representation to improve accuracy.

Contribution

The paper proposes a pixel-level grasp representation and a specialized network architecture for unsymmetrical three-finger grippers, enhancing grasp detection accuracy.

Findings

Achieved 96.8% accuracy on image-wise split

Achieved 92.27% accuracy on object-wise split

Outperformed state-of-the-art methods on the Cornell dataset

Abstract

In this paper, we present Segmentation-Based Grasp Detection Network (SGDN) to predict a feasible robotic grasping for a unsymmetrical three-finger robotic gripper using RGB images. The feasible grasping of a target should be a collection of grasp regions with the same grasp angle and width. In other words, a simplified planar grasp representation should be pixel-level rather than region-level such as five-dimensional grasp representation.Therefore, we propose a pixel-level grasp representation, oriented base-fixed triangle. It is also more suitable for unsymmetrical three-finger gripper which cannot grasp symmetrically when grasping some objects, the grasp angle is at [0, 2{\pi}) instead of [0, {\pi}) of parallel plate gripper.In order to predict the appropriate grasp region and its corresponding grasp angle and width in the RGB image, SGDN uses DeepLabv3+ as a feature extractor, and uses a three-channel grasp predictor to predict feasible oriented base-fixed triangle grasp representation of each pixel.On the re-annotated Cornell Grasp Dataset, our model achieves an accuracy of 96.8% and 92.27% on image-wise split and object-wise split respectively, and obtains accurate predictions consistent with the state-of-the-art methods.