A lazy learning control method using support vector regression
M. Kobayashi, Y. Konishi, H. Ishigaki · 2007
Lazy Learning is a new modeling method using memory-based learning. It is applied to control methods using a modeling technique. This paper proposes a new method that can be applied to position control. This method provides a way of setting the query point. Lazy Learning thus performs as a controller in the proposed method, not as an inverse model of the controlled model as in the conventional method. This paper also describes a new local modeling method of Lazy Learning using Support Vector Regression instead of Linear Weighted Average. The effectiveness of the proposed method is confirmed by computer simulations for position control using a one degree of freedom robot arm with friction.