Grounding action words in the sensorimotor interaction with the world: experiments with a simulated iCub humanoid robot

This paper presents a cognitive robotics model for the study of the embodied representation of action words. The present research will present how a iCub humanoid robot can learn the meaning of action words (i.e. words that represent dynamical events that happen in time) by physically acting on the environment and linking the effects of its own actions with the behaviour observed on the objects before and after the action. The control system of the robot is an artificial neural network trained to manipulate an object through a Back-Propagation Through Time algorithm. We will show that in the presented model the grounding of action words relies directly to the way in which an agent interacts with the environment and manipulates it.

Abstract licence: CC BY

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.