Deep reinforcement learning rotation speed prediction method and system for table tennis robot

Abstract

The invention provides a deep reinforcement learning rotation speed prediction method and system for a table tennis robot. The prediction method comprises: normalizing a table tennis ball coming position sequence at equal time intervals; inputting the normalized sequence into a deep LSTM network; inputting the obtained state vector of the LSTM into an incident rotation estimation deep neural network to obtain an incident rotation speed; calculating reward feedback of deep reinforcement learning; combining the ping-pong ball coming position sequence, the ping-pong ball incident rotation speed and the reward feedback in the current ball hitting process into one-time ball hitting memory, and storing the one-time ball hitting memory into a memory bank; and randomly selecting at least one memory from a memory bank, inputting the state vector of the LSTM and the incident rotation speed of the table tennis ball into a reward feedback estimation deep neural network, outputting reward feedbackestimation, and performing back propagation and parameter updating on the incident rotation estimation deep neural network and the reward feedback estimation deep neural network. The ball returning device can accurately return the ball when coping with the rotating ball.

Description

technical field [0001] The application belongs to the technical field of table tennis robots, and in particular relates to a method and system for predicting rotation speed through deep reinforcement learning of table tennis robots. Background technique [0002] Table tennis robot refers to an automatic device that can hit the table tennis ball on the opponent's hemispherical table after rebounding from one's hemispherical table. It can realize multi-round table tennis sparring competitions, and can be widely used in professional athletes' training and hobbies. interaction with readers. [0003] At this stage, many research institutions at home and abroad have realized the goal of table tennis robots hitting the ball. However, table tennis robots still generally have the deficiency of not being able to accurately return the ball to a rotating ball with a faster speed. The existing control of table tennis robot's hitting motion rarely considers the rotation speed of the tabl...

AI Technical Summary

Problems solved by technology

This kind of auxiliary gimbal system is relatively complex, and requires a high frame rate of the camera, and cannot effectively estimate the rotation speed when local features cannot be captured by the camera (such as a trademark on the back of a table tennis ball).

Images