Complex neural architectures for emerging cognitive abilities in an autonomous system

We propose a novel neural architecture named PerAc which is a systematic way to decompose the control of an autonomous robot in perception and action flows. We first present an application of the PerAc architecture to the simulation of a vision system with a moving eye. Then we propose a second application where the robot learns to return from any starting place to a previously discovered and learned position without any a priori symbolic representation.