Robotic Arm Intelligent Grasping System for Garbage Recycling

Abstract

The recycling of garbage is an effective way to protect environment. However, garbage recycling is still adopting manual sorting which is of low efficiency and may damage to the health of operators. To improve the efficiency of the garbage recycling, it is considered to use an automated robot system which integrates modern control method of robots and machine vision to replace manual sorting. Using a robotic arm and a RGB-D camera, a visual servo robotic arm grasping system was produced, which mainly depends on tools in robot operating system (ROS). The object recognition kitchen (ORK) in ROS is used to identify and locate the grasping targets. The relationship between the camera coordinate system and the robot coordinate system is established by hand-eye calibration technology. The kinematics calculation and motion planning of the robotic arm are completed with the help of ROS-Moveit!. Through experimental testing, it is estimated that the hand-eye calibration is accurate, and the robotic arm can perfectly grasp the target object.