Experiences Using MediaPipe to Make the Arms of a Humanoid Robot Imitate a Video-Recorded Dancer Performing a Robot Dance

This paper presents our first results obtained in the direction of using a humanoid robot to perform a robot dance at a level comparable to that of a human dancer. The scope of this first approach is limited to performing an offline analysis of the movements of the arms of the dancer and to replicating these movements with the arms of the robot. To this end, the movements of a dancer performing a static robot dance (without moving the hips or feet) were recorded. These movements were analyzed offline using the MediaPipe BlazePose framework, adapted to the mechanical configuration of the arms of the humanoid robot, and finally reproduced by the robot. Results showed that MediaPipe has some inaccuracies when detecting sudden movements of the dancer’s arms that appeared blurred in the images. In general, the humanoid robot was capable of replicating the movement of the dancer’s arms but was unable to follow the original rhythm of the robotic dance due to acceleration limitations of its actuators.