Efficient End-to-End 6-Dof Grasp Detection Framework for Edge Devices with Hierarchical Heatmaps and Feature Propagation

TL;DR

This paper introduces E3GNet, an efficient end-to-end 6-DoF grasp detection network that uses hierarchical heatmaps, enabling real-time performance on edge devices and achieving high success rates in cluttered environments.

Contribution

The paper proposes a novel, computationally efficient network architecture for 6-DoF grasp detection that is suitable for deployment on edge devices, outperforming previous methods in speed and accuracy.

Findings

Achieves real-time 6-DoF grasp detection on edge devices.

Surpasses previous methods in inference efficiency.

Attains a 94% grasp success rate in real-world tests.

Abstract

6-DoF grasp detection is critically important for the advancement of intelligent embodied systems, as it provides feasible robot poses for object grasping. Various methods have been proposed to detect 6-DoF grasps through the extraction of 3D geometric features from RGBD or point cloud data. However, most of these approaches encounter challenges during real robot deployment due to their significant computational demands, which can be particularly problematic for mobile robot platforms, especially those reliant on edge computing devices. This paper presents an Efficient End-to-End Grasp Detection Network (E3GNet) for 6-DoF grasp detection utilizing hierarchical heatmap representations. E3GNet effectively identifies high-quality and diverse grasps in cluttered real-world environments.Benefiting from our end-to-end methodology and efficient network design, our approach surpasses previous methods in model inference efficiency and achieves real-time 6-Dof grasp detection on edge devices. Furthermore, real-world experiments validate the effectiveness of our method, achieving a satisfactory 94% object grasping success rate.