In visual navigation, a moving agent equipped with camera is traditionally controlled by an input action and the estimation of features from sensory state (i.e. view) treated as pre-processing step to perform high-level vision tasks. this paper, we present representation learning approach that, instead, considers both inputs. We condition encoded feature transition network on that changes view ...

We present an active vision head-eye system that mimics the low-level visual reflexes of an infant. The software architecture is fast and robust, consisting of very simple modules that interact to correct each other’s errors. The system produces stable output and is designed to be the base framework of a more complete visual system. It tracks objects at 30 Hz with smooth motion, running on a si...

The primate visual system actively selects visual information from the environment for detailed processing through mechanisms of visual attention and saccadic eye movements. This study examines the statistical properties of the scene content selected by active vision. Eye movements were recorded while participants free-viewed digitized images of natural and artificial scenes. Fixation locations...

Evolved active vision control systems have the ability to extract relevant information from an environment in order to solve a specific task [1]. This work has the objective to investigate an obstacle avoidance and navigation systems for space exploration rovers capable of performing autonomous tasks in challenging planetary terrains. The paper presents an evolutionary robotics approach applied...