Evaluation of an Experimental Framework for Exploiting Vision in Swarm Robotics

Abstract

Visual feature detection with limited resources of simple robots is an essential requirement for swarm robotic sys-tems. Robots need to localize their position, to determine their orientation, and need to be able to acquire extra infor-mation from their surrounding environment using their sen-sors, while their computational and storage capabilities might be very limited. This paper evaluates the performance of an experimental framework, in which environmental elements such as landmarks and QR-codes are considered as key vi-sual features. The performance is evaluated for environmen-tal light disturbances and distance variations and feature de-tection speed is thoroughly examined. The applicability of the approach is shown in a real robot scenario by using e-puck robots. Finally, the results of applying the approach to a completely different setting, i.e., simulation of pheromones using glowing trail detection, are presented. These results in-dicate the broad applicability range of the developed feature detection techniques.