J. Stuart and E. Bradley, "Learning the Grammar of Dance," Proceedings of the ICML (International Conference on Machine Learning), Madison WI; July 1998

Abstract

A common task required of a dancer or athlete is to move from one prescribed body posture to another in a manner that is consistent with a specific style. One can automate this task, for the purpose of computer animations, using simple machine-learning and search techniques. In particular, we find kinesiologically and stylistically consistent interpolation sequences between pairs of body postures using graph-theoretic methods to learn the ``grammar'' of joint movements in a given corpus and then applying memory-bounded A* search to the resulting transition graphs --- using an influence diagram that captures the topology of the human body in order to reduce the search space.

Full paper in postscript (1.8MKB) and pdf (255KB).

If you have trouble downloading and/or printing out this paper, contact Laura Vidal (laurav@cs.colorado.edu) for a reprint.