Objectif
The goals of MIRROR are:
1) to realize an artificial system learning to communicate with humans by means of body gestures;
2) to investigate the mechanisms used by the brain to learn and represent manipulation acts. The biological starting point is the existence in primates' pre-motor cortex of the mirror neurons that becomes active both during execution of goal directed actions and during the observation of similar actions performed by others.
The goals of MIRROR are:
1) to realize an artificial system learning to communicate with humans by means of body gestures;
2) to investigate the mechanisms used by the brain to learn and represent manipulation acts. The biological starting point is the existence in primates' pre-motor cortex of the mirror neurons that becomes active both during execution of goal directed actions and during the observation of similar actions performed by others.
OBJECTIVES
This unified representation may sub serve the learning of goal directed actions during development and the recognition of motor acts, when visually perceived.
In MIRROR we investigate this ontogenetic pathway in two ways:
1) by realizing a system that learns to move AND to understand movements on the basis of the visually perceived motion and the associated motor commands and
2) by correlated electrophysiological experiments.
DESCRIPTION OF WORK
The project will investigate the association between visual information and motor commands in the learning, representation and understanding of complex manipulative gestures. The reference scenario is that of a person performing goal driven arm/hand gestures such as pointing, scratching a body part, bringing food to the mouth etc. At the end of the project the artefact will be able to learn how to perform and recognize this kind of actions.
We intend to proceed with two different methodologies:
1) implementation and use of an artificial system and
2) electrophysiological and behavioural experiments.
In the initial part of the project the experimental set-ups will be realized namely:
1) the artificial system (robot) and
2) the biological data acquisition.
The robot is composed of a binocular head, a torso, an anthropomorphic arm with a hand. Most of these components are already available and we will concentrate on the realization of an arm with elastic properties (possibly included in the actuators) and with torque/force sensors at the joints. The biological set up will consists, initially, of a "data-glove-like" and a pair of cameras.
Experiments will be carried out to better understand the role of the unified visuomotor representation formed by mirror neurons in learning and recognizing motor acts, and how these acts are matched onto the observer motor repertoire. The degree of modulation of mirror neuron discharge recorded when the monkey sees its own hand will be contrasted with neuronal discharge evoked by observation of other's hand, and during the execution of hand actions without visual feedback. The biological data will guide the artefact implementation.
Finally, the "artificial neurons" of the artefact "brain" will be analysed in terms of motor, visual and visuomotor properties and the data will be compared with those obtained during recording experiments performed in monkey parietal and frontal cortices.
The reference scenario is that o f a person performing goal driven arm/hand gestures such as pointing, picking, grasping etc.
The expected results are:
1) new technologies;
2) an artificial system able to interact with humans using gestures;
3) better understanding of human visuomotor representation and learning.
Champ scientifique (EuroSciVoc)
CORDIS classe les projets avec EuroSciVoc, une taxonomie multilingue des domaines scientifiques, grâce à un processus semi-automatique basé sur des techniques TLN. Voir: https://op.europa.eu/en/web/eu-vocabularies/euroscivoc.
CORDIS classe les projets avec EuroSciVoc, une taxonomie multilingue des domaines scientifiques, grâce à un processus semi-automatique basé sur des techniques TLN. Voir: https://op.europa.eu/en/web/eu-vocabularies/euroscivoc.
- sciences naturellessciences biologiqueszoologiemammalogieprimatologie
- ingénierie et technologiegénie électrique, génie électronique, génie de l’informationingénierie électroniquecapteurscapteurs optiques
Vous devez vous identifier ou vous inscrire pour utiliser cette fonction
Nous sommes désolés... Une erreur inattendue s’est produite.
Vous devez être authentifié. Votre session a peut-être expiré.
Merci pour votre retour d'information. Vous recevrez bientôt un courriel confirmant la soumission. Si vous avez choisi d'être informé de l'état de la déclaration, vous serez également contacté lorsque celui-ci évoluera.
Appel à propositions
Données non disponiblesRégime de financement
CSC -Coordinateur
16126 GENOVA
Italie