A fast image processing based robot identification method for Surveyor SRV-1 robots

Abstract

This paper focuses on a barcode pattern based kin recognition, identification and distance evaluation method for mobile-robot swarms. Every robot in the swarm is equipped with a unique, barcode like pattern. The robots capture images of other teammates and then the images are analysed by a Fast Fourier Transformation (FFT) in order to find kin robots on the captured image. After FFT analysis the identification is also possible with our edge detection based identification method. Moreover one of the best features of this method is the capability of estimating the robot-robot distances with a single camera image. Our method was implemented on physical robots and was tested using the Surveyor SRV-1 robot system.