Abstract. While interactive virtual humans are becoming widely used in education, training and delivery of instructions, building the animations required for such interactive characters in a given scenario remains a complex and time consuming work. One of the key problems is that most of the systems controlling virtual humans are mainly based on pre-defined animations which have to be re-built by skilled animators specifically for each scenario. In order to improve this situation this paper proposes a framework based on the direct demonstration of motions via a simplified and easy to wear set of motion capture sensors. The proposed system integrates motion segmentation, clustering and interactive motion blending in order to enable a seamless interface for programming motions by demonstration.