ERSOW Robot's Orientation Data Estimation Based on Landmark L-shape Recognition

In this paper, the Robot's Orientation Data Estimation System was created based on Landmark L-shape Recognition to reduce the error value in the robot's orientation data. The estimation system is carried out based on the recognition of unique landmarks on the soccer field in the form of "L"-shaped lines to get the reference distance between the landmarks and the robot. The reference distance is used to get the orientation of the robot above the field according to the perception of the omnidirectional camera. In the orientation of the robot between the angle of -135° to -180°, the largest error value from the orientation of the robot produced by vision is 5.5° and the average error is 1.99°. In the robot orientation between the angles of 135° to 180° it has the largest error value from the robot orientation generated by vision is 4.6° with an average error of 1.77°.