Learning efference in CNNs for perception-based navigation control

Action-oriented perception involves complex tasks to be fulfilled in real time. In fact living beings, even the most simple, suitably integrate afferent stimuli, create an abstract, concise representation of environment stimuli and choose it for action-selection purposes. We propose a novel infrastructure, based on CNNs, where the spatial-temporal solutions are linked to the results of the perception stage. In this perspective, a primary role is devoted to the introduction of plasticity to enhance the association stimuli-CNN dynamics-action selection with application to the task of autonomous navigation control.