A grasps-generation-and-selection convolutional neural network for a digital twin of intelligent robotic grasping. (October 2022)

• Record Type: Journal Article
• Authors: Hu, Weifei; Wang, Chuxuan; Liu, Feixiang; Peng, Xiang; Sun, Pengwen; Tan, Jianrong
• Is Part Of: Robotics and computer-integrated manufacturing. Volume 77(2022)
• Publication Date: 2022-10
• Subjects: Intelligent robotic grasping -- Digital twin -- Convolutional neural network -- Deep learning -- RGB-D image; Robots, Industrial -- Periodicals; Computer integrated manufacturing systems -- Periodicals; Robotics -- Periodicals; Robots industriels -- Périodiques; Productique -- Périodiques; Robotique -- Périodiques; 670.285
• DOI: 10.1016/j.rcim.2022.102371
• Languages: English
• ISSNs: 0736-5845

Abstract

Highlights: A new robotic grasping definition is developed for unknown-object grasping. A new GGS-CNN is proposed for efficient and accurate intelligent robotic grasping. A digital twin of intelligent robotic grasping is developed. Abstract: Robotic grasping plays an essential role in human-machine cooperation in various household and industrial applications. Although humans can instinctively execute grasps in an accurate, stable, and rapid way even under a constantly changing environment, intelligent grasping remains a challenging task for robots. As a prerequisite for grasping, robots need to correctly identify the best grasping location of unknown objects often based on an artificial intelligence approach, which is still a challenging problem. This paper proposes a new grasps-generation-and-selection convolutional neural network (GGS-CNN), which is trained and implemented in a digital twin of intelligent robotic grasping (DTIRG). By defining a grasp with 3-D position, rotation angle, and gripper width, the GGS-CNN generates grasp candidates by transforming the red–green-blue-depth images (RGB-D images) into feature maps and evaluating the quality of selected grasps. The GGS-CNN is trained in the virtual environment and the real world of the DTIRG to detect accurate grasps. In the grasping tests, the proposed GGS-CNN achieves grasping success rates of 96.7% and 93.8% for grasping single objects and cluttered objects, respectively, and obtains the best grasp from the RGB-D image in less than 40 ms.