Adding Active Learning to LWR for Ping-Pong Playing Robot
Yanlong Huang, De Xu, Min Han Tan, Hu Su · IEEE Transactions on Control Systems Technology · 2012
In this brief, we consider the problem of controlling the racket attached to the ping-pong playing robot, so that the incoming ball is returned to a desired position. The maps that are used to calculate the racket's initial parameters are described. They are implemented with the locally weighted regression (LWR). An active learning approach based on the fuzzy cerebellar model articulation controller (FCMAC) is proposed, and then it is added to the LWR, which is regarded as lazy learning. A learning algorithm that is used for updating the experience data in the fuzzy CMAC according to the errors between the actual and desired landing positions is presented. A series of experiments has been performed to demonstrate the applicability of the proposed method.