Integration and Transfer of Action and Language Knowledge in Robots

 

EU ICT Cognitive Systems and Robotics Integrating Project

fp7-logo.JPG

 

 

 

icub-media-small.jpg   vadim-photo-simulator-Dec2007.JPG

 

 

 

Overview

 

Research Themes and Methodologies

The ITALK project aims to develop artificial embodied agents able to acquire complex behavioural, cognitive, and linguistic skills through individual and social learning. This will be achieved through experiments with the iCub humanoid robot to learn to handle and manipulate objects and tools autonomously, to cooperate and communicate with other robots and humans, and to adapt to changing internal, environmental, and social conditions. 

The project will lead to the development of

·     new theoretical insights, models and scientific explanations of the integration of action, social and linguistic skills to bootstrap cognitive development

·     new interdisciplinary sets of methods for analysing the interaction of language, action and cognition in humans and artificial cognitive agents,

·     new cognitively-plausible engineering principles and approaches for the design of robots with behavioural, cognitive, social and linguistic skills

·     robotic experiments on object manipulation and language with the iCub robot

 

New studies will address the following research themes:

·     Action development and compositionality of action

·     Embodied conceptualisation

·     Social interaction and learning

·     Emergence of language and compositional lexicons

·     Integration and bootstrapping of action, language and cognition

·     Demonstration and testing in humanoid robot iCub

 

Research will be based on the following methodologies

·     Developmental and epigenetic robotics

·     Neural network models of action and language grounding

·     Developmental linguistics

·     Neuroscience of action learning, imitation and gaze following

·     Human-Robot experiments on social learning and interaction

·     Experiments with physical and simulated iCub platform

Consortium

Researchers

·         Adaptive Behaviour & Cognition, University of Plymouth (UK)

·         Humanoid Robotics, Italian Institute of Technology (Genoa)

·         Applied Computer Science, Bielefeld University (Germany)

·         Robotics & Artificial Life, National Research Council Rome (Italy)

·         Adaptive Systems Research, University of Hertfordshire (UK)

·         Department of Business Communication and Information Science, University of Southern Denmark (Denmark)

·         Behavior and Dynamic Cognition, RIKEN Brain Science Institute (Japan)

·         Cognitive Machines, MIT Media Lab (collaborator)

·         Angelo Cangelosi (Coordinator), Tony Belpaeme, Davide Marocco, Vadim Tikhanoff, Martin Peniak, Martin Beck

·         Giorgio Metta, Luciano Fadiga, Giulio Sandini, Francesco Nori, Paola Salmas

·         Gerhard Sagerer, Britta Wrede, Katharina Rohlfing

·         Stefano Nolfi, Elio Tuci, Marco Mirolli, Domenico Parisi, Gianluca Massera

·         Chrystopher Nehaniv, Kerstin Dautenhahn, Joe Saunders

·         Kerstin Fischer, Arne Zeschel

·         Jun Tani, Yuuya Sugita

·         Deb Roy

 

 

 

Contact us: acangelosi@plymouth.ac.uk