Key points are not available for this paper at this time.
This paper describes an industrial robotics application, named Gilbreth, for picking up objects of different types from a moving conveyor belt and sorting the objects into bins according to type. The environment, which consists of a moving conveyor belt, a break beam sensor, a 3D camera Kinect sensor, a UR10 industrial robot arm with a vacuum gripper, and different object types such as gears, pulleys, piston rods, was inspired by the NIST ARIAC competition. A first version of the Gilbreth application was implemented leveraging many ROS and ROS-I packages. Gazebo was used to simulate the environment, and six external ROS nodes were implemented to execute the required functions. Experimental measurements of CPU usage and processing times of ROS nodes were obtained. Object recognition required the highest processing times that were on par with the time required for the robot arm to execute its movement between four poses: pick approach, pick, pick retreat and place. A need for enhancing the performance of object recognition and Gazebo simulation was identified.
Zhang et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: