Neural-Network Static Learning Controller in DCT Subspace

In this note, a static neural-network (NN) learning controller in discrete cosine transform subspace is proposed. The high-dimensional problem of temporal static learning controllers is overcome, paying a little cost of tracking precision lost. Experiments on two joints of a SCARA type robot verify the effectiveness of the proposed approach. A small-size NN may meet the learning control specification and tracking precision can be improved by enlarging the size of the NN.