Visual homing: Experimental results on an autonomous robot

Abstract

In this paper a new visual homing algorithm, implemented using the CNN-based vision system called Eye-Ris, is introduced. Design details and experimental results using a roving robot are also presented. The methodology as well as experimental inspiration was drawn by insect, which are able to show superb homing capabilities. In fact, in a variety of natural environments, different insect species are able to localize the nest position by using panoramic visual sensors. Exploiting this localization method, it is possible to implement algorithms which let a robot, endowed with a panoramic camera, come back to a reference position from any starting point in an arena, implementing the so-called visual homing method. If the home is a recharging station, visual homing can help to recharge the battery pack in an autonomous mobile robot, as shown in the paper.