A Mobile Robotic Arm Grasping System with Autonomous Navigation and Object Detection

In this paper, we propose a mobile robotic arm grasping system suitable for various service requirements in indoor environments. For the task of grasping the given object, both the navigation and the visual recognition positioning are prerequisite. In order to realize the robot's autonomous navigation, the use of Cartographer algorithm is employed to build an unknown environment map. To improve the grasping quality, we develop a grasping system that uses YOLOv4 combined with the GrabCut algorithm for the robotic arm, which can be applied to various objects in different scenarios. First, the YOLOv4 algorithm is introduced to identify and locate the individual objects. Secondly, the output frame can be used as an input of the GrabCut algorithm to segment the objects from the background for calculating the capture orientation. Thirdly, the conversion between the coordinate systems is conducted to acquire the positions of objects, and the obtained information is sent to the robotic arm to complete the grasping task on the Robot Operating System (ROS). The experimental results show that the grasping success rate with the proposed algorithm is close to 92.2%, which is of great significance to the application of in home service robot scenario.