Object Detection by Combining Two Different CNN Algorithms and Robotic Grasping Control

Abstract

The detection of robot manipulator’s object-grasping point is the most important step in precise handling of object. To grasp object needs some important parameters, which are object’s center coordinates (x, y, z) and width, yaw angle. In this paper, we predict not individual parameters but grasping area by using Segmentation Algorithm. Combining Mask R-CNN algorithm and Fully Convolutional Net algorithm and adding them to ROS, we construct ROS architecture. And, we apply them to control moving robot’s manipulator in grasping objects. So, we can reduce processing time for detecting object and improve applicability of this new method in robotic grasping control.