Navigation in large-scale environments using an augmented model of visual homing

Several models have been proposed for visual homing in insects. These work well in small-scale environments but performance usually degrades significantly when the scale of the environment is increased. We address this problem by extending one such algorithm, the average landmark vector (ALV) model, by using a novel approach to waypoint selection during the construction of multi-leg routes for visual homing. The algorithm, guided by observations of insect behaviour, identifies locations on the boundaries between visual locales and uses them as waypoints. Using this approach, a simulated agent is shown to be capable of significantly better autonomous exploration and navigation through large-scale environments than the standard ALV homing algorithm.