A Feature Reserved Teaching Method for Pick-Place System under Robot Operating System

Abstract

The advent of industry 4.0 has put forward higher requirements for flexible manufacturing. When work changes, the system has to be reprogrammed and the robot needs to follow a specific trajectory to finish the pick and place task. Therefore, it is urgent to find a convenient, and feature reserved teaching method that could adapt to different pick and place tasks. This paper introduces a novel teaching method for the pick-place system under the robot operating system(ROS) without losing valuable features during the human demonstration. This teaching method utilizes only one depth camera to continuously track the object’s 3D position without any marker attached. The 6D pose of the object at the endpoint is estimated to provide extra orientation information. Then, generating the executable path by trajectory key features extraction algorithm and pick-place pose adjustment planning. The robot could follow the path generated to imitate the demonstrated pick-place task. The experiments prove that this teaching method is efficient. The system could not only adapt to the different object’s initial positions but also reserve the key features in teaching.