Visual Bug Algorithm for Simultaneous Robot Homing and Obstacle Avoidance Using Visual Topological Maps in an Unmanned Ground Vehicle

Abstract

AbstractWe introduce a hybrid algorithm for the autonomous navigation of an Unmanned Ground Vehicle (UGV) using visual topological maps. The main contribution of this paper is the combination of the classical bug algorithm with the entropy of digital images captured for the robot. As the entropy of an image is directly related to the presence of a unique object or the presence of different objects inside the image (the lower the entropy of an image, the higher its probability of containing a single object inside it; and conversely, the higher the entropy, the higher its probability of containing several different objects inside it), we propose to implement landmark search and detection using topological maps based on the bug algorithm, where each landmark is considered as the leave point for guide to the robot to reach the target point (robot homing). The robot has the capacity of avoid obstacles in the enviroment using the entropy of images too. After the presentation of the theoretical foundations of the entropy-based search combined with the bug algorithm, the paper ends with the experimental work performed for its validation.KeywordsBug algorithmUnmanned ground vehiclesEntropy searchVisual topological maps