From visuo-motor development to low-level imitation

We present the rst stages of the developmen-tal course of a robot using vision and a 5 degree of freedom robotic arm. During an exploratory behavior, the robot learns visuo-motor control of its mechanical arm. We show how a simple neu-ral network architecture, combining elementary vision, a self-organized algorithm, and dynamical Neural Fields is able to learn and use proper asso-ciations between vision and arm movements, even if the problem is ill posed (2-D toward 3-D map-ping and also mechanical redundancy between dierent joints). Highlighting the generic aspect of such an architecture, we show as a robotic re-sult that it is used as a basis for simple gestural imitations of humans. Finally we show how the imitative mechanism carries on the developmen-tal course, allowing the acquisition of more and more complex behavioral capabilities. 1