Emergence and Categorization of CoordinatedVisual Behavior Through Embodied

This paper discusses the emergence of sensorimotor coordination for ESCHeR, a 4DOF redundant foveated robot-head, by interaction with its environment. A feedback-error-learning(FEL)-based distributed control provides the system with explorative abilities with re-exes constraining the learning space. A Kohonen network, trained at run-time, categorizes the sensorimotor patterns obtained over ESCHeR's interaction with its environment, enables the reinforcement of frequently executed actions, thus stabilizing the learning activity over time. We explain how the development of ESCHeR's visual abilities (namely gaze xation and saccadic motion), from a context-free reeex-based control process to a context-dependent, pattern-based sensorimotor coordination can be related to the Piagetian 'stage theory'.