My main research interests are in applying the results of the research on human motor control and perception to the creation of cognitive agents, such as for example humanoid robots. My research focuses on various issues in robot learning, especially imitation learning and learning by exploration, where I combine statistical learning techniques and reinforcement learning to increase the efficiency and autonomy of the acquisition of new sensorimotor behaviors. I am also interested in humanoid robot vision with the focus on learning object representations, object recognition, and foveated vision. Finally, I study mechanisms to integrate active perception and manipulation in robots that operate in natural environments.