Spinning pattern classification of table tennis ball's flying trajectory based on fuzzy neural network

摘要

Trajectory prediction plays a very important role in the process of playing table tennis for robot. Its accuracy determines whether the striking action will succeed or not. Since the surfaces of the racket and the table are not absolutely smooth, friction force exists during the contact process of table tennis ball and racket/table, which make the ball's spin. The existence of spinning influences the trajectory of the spinning ball. On the basis of force analysis, how the Magnus force influences the flying trajectory under different spinning patterns is discussed firstly, and then two fuzzy neural network classifiers are designed to estimate the spinning patterns. The experiments with serve machine show the effectiveness of the classifiers.