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

Micromachines

Chengzhe Zhou¹  Jiamao Li¹  Yasuharu Koike²  Zhongjie Zhang² 

[1] Bionic Vision System Laboratory, Shanghai Institute of Microsystem and Information Technology, Shanghai 200050, China;Institute of Innovative Research, Tokyo Institute of Technology, Yokohama 2268503, Japan;

关键词: 6D pose estimation;    real object judgment;    pixel-wise voting network;    6D grasping robotic system;   

DOI  :  10.3390/mi13020293

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown