<![CDATA[Research on wheeled soccer robots has been developed especially for the accuracy of the object detection and classification. This paper solves the problem for ball's position and arrival time prediction also its navigation to block the ball. Previous research used Single Layer Neural Network (SLNN) and Two Layer Neural Network (TLNN) methods. This paper propose a Modified Two-Layer Neural Network (MTLNN) algorithm for increasing the prediction accuracy for ball’s position and its arrival time, also Goalkeeper Robot Navigation (GKRN) algorithm for its navigation. The algorithm was created by modifying the TLNN architecture in the number of nodes to eight inputs and two outputs, with the number of hidden being designed as needed. The accuracy of the prediction greatly affects ball blockade because it is used to navigate the robot. The GKRN algorithm was created by modifying the membership function of the Fuzzy Inferences System (FIS), which is adjusted to the robot's needs. The results showed an increase in prediction accuracy from up to 20 times better for ball position and 4 times better for the arrival time of the ball. Overall, the navigation system obtained a successful rate of 90% for blocking the ball.]]>
Copyrights © 2020
