Within Reach? Learning to touch objects without prior models

摘要

Human infants learn to manipulate objects in a largely autonomous fashion, starting without precise models of their bodies' kinematics and dynamics. Replicating such learning abilities in robots would make them more flexible and robust and is considered a grand challenge of Developmental Robotics. In this paper, we propose a developmental method that allows a robot to learn to touch an object, while also learning to predict if the object is within reach or not. Importantly, our method does not rely on any forward or inverse kinematics models. Instead it uses a stage-wise learning approach combining deep reinforcement learning and a form of self-supervised learning. In this approach, complex skills such as touching an object or predicting if it is within reach are learned on top of more basic skills such as object fixation and eye-hand-coordination.