Séminaire VIBOT : The Structuring Role of Language for Robot Perception and Action

Le 13 février, Peter Ford Dominey viendra faire un séminaire au Creusot amphi 8 de Condorcet à 14h.

Title:

The Structuring Role of Language for Robot Perception and Action 

Abstract :

In the context of a robot such as the humanoid iCub, sensory input is of quite high dimension, and thus extracting pertinent information can be challenging.  We can define psychologically-inspired simple perceptual primitives (e.g. contact, motion) that can be directly extracted from the visual signal from the robot cameras, and then use language to label structured sequences of incoming visual primitives to create a simple but robust action recognition system.  The same principle can be applied to motor primitives that can be assembled using language labeling, in order to create a rich repertoire of actions.  This structuring role of language can be applied at successively higher levels, corresponding to shared perceptual-motor plans that allow human robot cooperation.  I will present some of our work in this area, and attempt to identify future opportunities for interaction.

Ajouter au calendrier Tous les événements