A support vector rule based method is investigated for the construction of motion controllers via natural language training. It is a two-phase process including motion control information collection from natural language instructions, and motion information condensation with the aid of support vector machine (SVM) theory. Self-organizing fuzzy neural networks are utilized for the collection of control rules, from which support vector rules are extracted to form a final controller to achieve any given control accuracy. In this way, the number of control rules is reduced, and the structure of the controller tidied, making a controller constructed using natural language training more appropriate in practice, and providing a fundamental rule base for high-level robot behavior control. Simulations and experiments on a wheeled robot are carried out to illustrate the effectiveness of the method.