Discovery of other individuals by projecting a self-model through imitation

This paper proposes a novel model which enables a humanoid robot infant to discover other individual (e.g. human parent). In this work, the authors define "other individual" as an actor which can be predicted by a self-model. For modeling the developmental process of discovering ability, the following three approaches are employed, (i) Projection of a self-model for predicting other individual\´s actions, (ii) Mediation by a physical object between self and other individual, (iii) Introduction of infant imitation by parent. For creating the self-model of a robot, we apply Recurrent Neural Network with Parametric Bias (RNNPB) model which can learn the robot\´s body dynamics. For the other-model of a human, conventional hierarchical neural networks are attached to the RNNPB model as "conversion modules". Our target task is a moving an object. For evaluation of our model, human discovery experiments by the robot projecting its self-model were conducted. The results demonstrated that our method enabled the robot to predict the human\´s motions, and to estimate the human\´s position fairly accurately, which proved its adequacy.