Design and implementation of a ball-batting robot with optimal batting decision making ability

In this paper, we establish a ball-batting robotic system which consists of a four-joint robot arm with a paddle at its tip, and a high-speed stereovision system. The stereovision system tracks and predicts the trajectory of a flying ball. Then the robot hits the flying ball with the paddle and sends the rebounding ball to a desired location. An optimal batting decision making algorithm is proposed which determines the 'best' impact time, position, and paddle velocity to ensure the arrival of the rebounding ball at the desired location. Experiments are conducted repeatedly and the results demonstrate that the performance of the ball-batting robot is similar to that of non-professional human players.