The robot in the mirror

Abstract

Humans maintain a body image of themselves, which plays a central role in controlling bodily movement, planning action, recognising and naming actions performed by others, and requesting or executing commands. This paper explores through experiments with autonomous humanoid robots how such a body image could form. Robots play a situated embodied language game called the Action Game in which they ask each other to perform bodily actions. They start without any prior inventory of names, without categories for visually recognising body movements of others, and without knowing the relation between visual images of motor behaviours carried out by others and their own motor behaviours. Through diagnostic and repair strategies carried out within the context of action games, they progressively self-organise an effective lexicon as well as bi-directional mappings between the visual and the motor domain. The agents thus establish and continuously adapt networks linking perception, body representation, action and language.

The pragmatics of event-driven business processes

“…An interesting line of research explores the possibilities of letting these interactions evolve from certain generic co-orientation capabilities, rather than design them by specification (cf. [20]). …”

The future of content is in ourselves

“…Recently, experiments by Steels and Spranger (Steels & Spranger, 2008) have also exploited reflexive interactions as a way for robots to self-teach how to recognize and interpret gestures performed by other robots (see Figure 17). This last scene echoes the mirror scene of the Marx Brothers, in a context where humans have disappeared, but not reflexion: the key ingredient, so I claim, of the future of Content.…”

Language Grounding in Robots

“…The symbol grounding problem has been plaguing AI for a long time (Steels, 2008). The field has since the very beginning always had two research thrusts.…”