Single RGB Image 6D Object Grasping System Using Pixel-Wise Voting Network.
MICROMACHINES 2022;
13:mi13020293. [PMID:
35208417 PMCID:
PMC8878293 DOI:
10.3390/mi13020293]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/26/2021] [Revised: 02/06/2022] [Accepted: 02/08/2022] [Indexed: 11/16/2022]
Abstract
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.
Collapse