Force-Based Evolutionary Computation Approach for Automatic Skeletal Motion Learning in Human Animation

The realistic animation of human characters is a hot topic of research in computer graphics, with remarkable applications in computer animation and video games. A current trend is the application of powerful evolutionary computation techniques to meet the needs of increasing sophistication in the field. These techniques are inspired by the principles and mechanisms of biological evolution, such as selection, mutation, recombination, crossover, and so on. A great advantage of such methods is that they do not make any assumption on the problem to be solved. In this paper we present a new evolutionary computation approach for automatic skeletal motion learning in human animation. This approach is intended to generate automatically a sequence of motions on a human skeleton leading to plausible and realistic movements of the human body. This sequence is obtained autonomously (i.e., without human intervention) through an iterative intelligent process where the digital characters learn the optimal values of forces applied to selected bones according to the desired motion routines for proper movement. An illustrative example is discussed in detail to show the performance of this approach. This method can readily be adapted/extended to other skeleton configurations and interesting motions with only minor modifications.