Implementation of a Natural User Interface to Command a Drone

Abstract

In this work, we propose the use of a Natural User Interface (NUI) through body gestures, using the open source library OpenPose, looking for a more dynamic and intuitive way to control a drone. For the implementation, we use the Robotic Operative System (ROS) to control and manage the different components of the project. Wrapped inside ROS, OpenPose (OP) processes the video obtained in real-time by a commercial drone, allowing to obtain the user's pose. Finally, the keypoints provided by OpenPose are processed and translated, using geometric constraints, to specify high-level commands to the drone. The proposed strategy was implemented in real-time experiments, and validated with different human users through a standard User Experience Questionnaire (UEQ), showing good results in usability and user experience.