Programming Robots by Demonstration using Augmented Reality

Abstract

The world is living the fourth industrial revolution, Industry 4.0; marked by the increasing intelligence and automation of manufacturing systems. Nevertheless, there are types of tasks that are too complex or too expensive to be fully automated, it would be more efficient if the machine were able to work with the human, not only by sharing the same workspace but also as useful collaborators. A possible solution to that problem is on human-robot interactions systems, understanding the applications where they can be helpful to implement and what are the challenges they face. In this context a better interaction between the machines and the operators can lead to multiples benefits, like less, better, and easier training, a safer environment for the operator and the capacity to solve problems quicker. The focus of this dissertation is relevant as it is necessary to learn and implement the technologies which most contribute to find solutions for a simpler and more efficient work in industry. This dissertation proposes the development of an industrial prototype of a human machine interaction system through Extended Reality (XR), in which the objective is to enable an industrial operator without any programming experience to program a collaborative robot using the Microsoft HoloLens 2. The system itself is divided into two different parts: the tracking system, which records the operator's hand movement, and the translator of the programming by demonstration system, which builds the program to be sent to the robot to execute the task. The monitoring and supervision system is executed by the Microsoft HoloLens 2, using the Unity platform and Visual Studio to program it. The programming by demonstration system's core was developed in Robot Operating System (ROS). The robots included in this interface are Universal Robots UR5 (collaborative robot) and ABB IRB 2600 (industrial robot). Moreover, the interface was built to easily add other robots.