Trajectories adaptive prediction based on image processing cerebellar model for ocular-motor systems in robotic heads

In this work, a neural controller for delay compensation in image samples detected by an active vision system of robotic heads, in ocular tracking tasks is presented. This control architecture based on CMAC (cerebellar model articulation controller) model has the capacity of learning favored trajectories with less prediction error. This property is very important in robotic tasks of controlling the grasping or assembling of objects by a robotic arm. The main advantage of this cerebellar model is that the output is evaluated by means of a small number of memory cells that implies a high answer speed. Indeed, this visual robotic control avoids (as does the human system) the need to know the kinematics of the process. This prediction module has been integrated in an architecture of visual-motor coordination based on VAM (vector associative maps) models