Automated Motion Synthesis for Virtual Choreography

摘要

Abstract — In this paper, we present a technique to automatically synthesize dancing moves for arbitrary songs. Our current implementation is for virtual characters, but it is easy to use the same algorithms for entertainer robots, such as robotic dancers, which fits very well to this year’s conference theme. Our technique is based on analyzing a musical tune (can be a song or melody) and synthesizing a motion for the virtual character where the character’s movement synchronizes to the musical beats. In order to analyze beats of the tune, we developed a fast and novel algorithm. Our motion synthesis algorithm analyze library of stock motions and generates new sequences of movements that were not described in the library. We present two algorithms to synchronize dance moves and musical beats: a fast greedy algorithm, and a genetic algorithm. Our experimental results show that we can generate new sequences of dance figures in which the dancer reacts to music and dances in synchronization with the music.