1P1-E14 Lexical acquisition using the active nature based on saliency
Masaaki Kikuchi, Masaki Ogino, Minoru Asada · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · 2006
This paper proposes a lexical acquisition model which makes use of saliency to associate visual features of observed objects with the labels that is uttered by a caregiver. A robot changes its attention and learning rate based on saliency. Simulation experiments show that the learning model with saliency effectively associate the given labels with the observed features. Moreover, in the experiment with a real humanoid robot, the visual features are represented with self organizing maps which adaptively represents the shape of observed objects independent of the viewpoints.