Real time self-localization of omni-vision robot by pattern match system

In this study, we designed an autonomous mobile robot according to the rules of the Federation of International Robot-soccer Association (FIRA) RoboSot category, integrating the techniques of computer vision, real-time image processing, dynamic target tracking, wireless communication, self-localization, motion control, path planning, and control strategy to achieve the contest goal. The real time self-localization scheme of the mobile robot is based on the algorithms extracting white lines from the soccer field featured in the images from the omni-vision system. The proposed algorithm uses the white line distances from 360 degree direction between the robot and the rotation angle of the robot obtained from the gyroscope as a featured vector. The feature vector is compared with the pre-built in patterns of the database. The location of the robot is obtained from the location of the matched pattern with the minimum error of the featured vector. The results demonstrate that the proposed algorithm is accurate, exhibiting a 10 cm (distance) and 1 degree (rotation) position error in a soccer field measuring 750 cm × 550 cm within processing time about 5 milliseconds. The real time self-localization system can be practically implemented in 2014 FIRA Robot Soccer Competition to fulfill the contest requirement.