Single RGB Image 6D Object Grasping System Using Pixel-Wise Voting Network

A robotic system that can autonomously recognize object and grasp it in a real scene with heavy occlusion would be desirable. In this paper, we integrate the techniques of object detection, pose estimation and grasping plan on Kinova Gen3 (KG3), a 7 degrees of freedom (DOF) robotic arm with a low-performance native camera sensor, to implement an autonomous real-time 6 dimensional (6D) robotic grasping system. To estimate the object 6D pose, the pixel-wise voting network (PV-net), is applied in the grasping system. However, the PV-net method can not distinguish the object from its photo through only RGB image input. To meet the demands of a real industrial environment, a rapid analytical method on a point cloud is developed to judge whether the detected object is real or not. In addition, our system shows a stable and robust performance in different installation positions with heavily cluttered scenes.

Automated summary

This paper presents a method for realizing an autonomous real-time 6D robotic grasping system on Kinova Gen3, integrating object detection, pose estimation, and grasping plan techniques. The system utilizes pixel-wise voting network (PV-net) for estimating the object's 6D pose, and a rapid analytical method on point cloud to judge the authenticity of the detected object. The system demonstrates stable and robust performance in various installation positions and heavily cluttered scenes.