Developmental Approach to Spatial Perception for Imitation Learning: Incremental Demonstrator’s View Recovery by Modular Neural Network

Imitation Learning is not simply one of the most promising ways to accelerate the behavior acquisition for humanoid robots but also one of the most interesting cognitive issues to model how we human beings learn to acquire various kinds of behaviors. As the first step towards developmental approach to spatial perception for imitation learning, this paper proposes a method of incremental recovery of the demonstrator’s view using a modular neural network by which the learner can organize spatial perception for the viewbased imitation learning with the demonstrator in different positions and orientations.