The invention regards a method for controlling motion of an object, such as a robot or virtual avatar. The method comprises the steps of receiving an input motion information describing a current motion of a current motion type and current style, and a target style for a target motion of the current motion type and the target style, transforming, using a first feedforward neural network, FFNN, of a style statistic predictor (1), the input motion information to an output motion information on the basis of the target style, wherein the output motion information describes the target motion, and controlling the motion of the object on the basis of the output motion information, such that the motion type of the motion of the object corresponds to the current motion type and the style of the motion of the object corresponds to the target style. the invention further regards a control unit for controlling the motion of an object that is configured to perform the method according to the inventive method as well as a robot including such a control unit and respective computer program.
展开▼