AUTHOR=Xu Teng , Tang Lijun 
  
TITLE=Adoption of Machine Learning Algorithm-Based Intelligent Basketball Training Robot in Athlete Injury Prevention
  
JOURNAL=Frontiers in Neurorobotics
  
VOLUME=Volume 14 - 2020
  
YEAR=2021
  
URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.620378
  
DOI=10.3389/fnbot.2020.620378
  
ISSN=1662-5218
  
ABSTRACT=To effectively prevent sports injuries caused by collisions in basketball training, machine learning algorithm is applied to intelligent robot for path planning, aiming to realize efficient shooting and reduce collisions. Combined with the basketball motion trajectory model, the sport recognition in basketball training is analyzed. The mathematical model of the basketball motion trajectory of the shooting motion is established, and the factors affecting the shooting are analyzed. Based on which, the machine learning-based improved Q-Learning algorithm is proposed, the path planning of the moving robot is realized, and the obstacle avoidance behavior is accomplished effectively. In the path planning, the principle of fuzzy controller is applied, and the obstacle ultrasonic signals acquired around the robot are taken as input, to make sure the obstacles are avoided effectively. Finally, the robot is able to approach the target point while avoiding obstacles. Through the simulation experiment, the obstacle avoidance path obtained by the improved Q-Learning algorithm is flatter, which proves the algorithm is more suitable for the obstacle avoidance of the robot. It only takes about 250 seconds for the robot to find the obstacle avoidance path to the target state for the first time, which is far lower than the 700 seconds of the previous original algorithm. The fuzzy controller applied to the basketball robot can effectively avoid the obstacles encountered in the robot movement process, and the motion trajectory curve obtained is relatively smooth.