Rudy Dikairono

Visual ball tracking and prediction with unique segmented area on soccer robot

Object detection and tracking system has been developed by several researchers. This paper present algorithm for visual ball detection and ball estimation for goalie (goalkeeper) robot. The ball is captured by a camera with a fish-eye lens and processed for detection and tracking. Images from fish-eye camera are curved images. Images are thresholded to Hue Saturation Value (HSV). The system can predict goal area and ball position with multilayer backpropagation neural network (BPNN). The BPNN inputs are x and y axis of the ball. The BPNN outputs are goal area prediction and ball area prediction. The training data is unique segmented area. According to the changes of previous ball distance, the system will predict the direction of the next ball position. The achievement result (unique kernel 3×3, MSE <0.001, 30 samples data) for ball position prediction is 76.67%. The achievement result (unique kernel 3×3, MSE <0.001, 30 samples data) for goal area prediction is 100%.

Motion planning simulator for holonomic robot soccer platform

This paper presents a soccer robot simulator which is built base on holonomic wheeled soccer robot platform. The platform is self-made with specifications based on Middle Sized League RoboCup rules. The simulator is built for multi-operating systems that can be run on Windows, Mac or Linux operating system. The use of simulators can speed up the development of algorithms for wheeled soccer robots because algorithmic testing can be done in the simulator before being implemented in actual robots. Time and cost saving are the huge benefits that can be derived from using this simulator. Algorithm A∗ is used for obstacle avoidance testing. The result shows that algorithm programs written in the simulator can be directly implemented into a real soccer robot platform. This simulator has motion planning RMSE equal to 6.5 cm for path planning without obstacle avoidance and RMSE equal to 46.6 cm for path planning with obstacle avoidance algorithm.