PEMANFAATAN METODE WAVELET PADA ROBOT SEPAKBOLA BERBASIS MACHINE LEARNING GOOGLE TENSORFLOW

Abstract

Humanoid Football robot that will be investigated is a wheeled model developed with the ability to predict or prediction in a football field with high accuracy and image resolution. This robot is expected to be able to keep the goal for up to 25 minutes with a cruising reach of 100 m. Also, the robot can monitor or monitor the desired area so that it can keep the goal from attacks from the opposing robot. This robot is expected to complete prediction missions towards the ball and autonomous monitoring without being controlled by the pilot. Robot control is carried out by a Ground Control Station (GCS) computer. The goalkeeper's robot process uses Google TensorFlow's machine learning technology that is integrated with the wavelet method to enable this robot to keep the goalposts from the area effectively and efficiently. Keywords: robot, machine learning, prediction, Ground Control Station, wavelet method