Sensorimotor representation learning for an "active self" in robots: A model survey

Safe human-robot interactions require robots to be able to learn how to\nbehave appropriately in \\sout{humans' world} \\rev{spaces populated by people}\nand thus to cope with the challenges posed by our dynamic and unstructured\nenvironment, rather than being provided a rigid set of rules for operations. In\nhumans, these capabilities are thought to be related to our ability to perceive\nour body in space, sensing the location of our limbs during movement, being\naware of other objects and agents, and controlling our body parts to interact\nwith them intentionally. Toward the next generation of robots with bio-inspired\ncapacities, in this paper, we first review the developmental processes of\nunderlying mechanisms of these abilities: The sensory representations of body\nschema, peripersonal space, and the active self in humans. Second, we provide a\nsurvey of robotics models of these sensory representations and robotics models\nof the self; and we compare these models with the human counterparts. Finally,\nwe analyse what is missing from these robotics models and propose a theoretical\ncomputational framework, which aims to allow the emergence of the sense of self\nin artificial agents by developing sensory representations through\nself-exploration.\n