Shall we dance? A music-driven approach for mobile robots choreography

Dance is a way of artistic expression. It also can be considered a form of communication. Typically, dance relies on the capability that human beings have to synchronize their movements rhythmically to music. In this work, we propose a music-driven approach to enable mobile robots to dance to a given music. We focus on the automatic generation of paths such that robots jointly performs a choreography guided by a song. Although dancing ability of a real person is complex and hard to accomplish, in this paper we aim to associate the robot motion to music and to emulate this typical human activity. We propose a variability function for evaluating the relevance of a block (set of notes) in a particular song, and based on those results, similar blocks are clustered. Finally, we generate customized paths for robots considering the current sound (note) being played and the importance of the block to which this note belongs. We have tested this approach with real robots (e-puck) using different kinds of songs. Results from those experiments indicate that robots can achieve good choreographic performance even if dance steps are automatically generated without previous knowledge of the song style.