2012 | OriginalPaper | Buchkapitel
An Adaptive Trajectory Prediction Method for Ping-Pong Robots
verfasst von : Yifeng Zhang, Rong Xiong, Yongsheng Zhao, Jian Chu
Erschienen in: Intelligent Robotics and Applications
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Trajectory prediction is a key issue to a ping-pong robot, many algorithms have been developed. To get more robust and accuracy prediction under different serving conditions, this paper presents a new prediction method. The proposed method establishes two equivalent forms of the dynamic model of flying ball, where the discrete form for state estimation and the continuous form for trajectory prediction. The two forms share the same parameters’ value. According to force analysis, It is found that the model parameters are deeply related to ball’s state (position, velocity) . So we train the model parameters offline respect to ball’s state, instead of setting them to a constant value. This enables the model to be adapted accordingly online. Experimental results show the effectiveness and accuracy of the proposed method for the ball with different velocities.