Towards a learning model for feature integration in attention control

摘要

We present current efforts towards an approach for the integration of features extracted from multi-modal sensors, with which to guide the attentional behavior of robotic agents. The model can be applied in many situations and different tasks including top-down or bottom-up aspects of attention control. Basically, a pre-attention mechanism enhances attentional features that are relevant to the current task according to a weight function that can be learned. Then, an attention shift mechanism can select one between the various activated stimuli, in order for a robot to foveate on it. Also, in this approach, we consider the robot moving resources or to improve the (visual) sensory information.