Share

IM-CLeVeR: Intrinsically Motivated Cumulative Learning Versatile Robots

Project summary

IM-CLeVeR aims to develop a new methodology for designing robots controllers that can: (1) cumulatively learn new efficient skills through autonomous development based on intrinsic motivations, and (2) reuse such skills for accomplishing multiple, complex, and externally-assigned tasks.

During skill-acquisition, the robots will behave like children at play which acquire skills autonomously on the basis of “intrinsicmotivations”. During skill-exploitation, the robots will exhibit fast learning capabilities and a high versatility in solving tasks defined by external users due to their capacity of flexibly re-using, composing and readapting previously acquired skills.

This overall goal will be pursued investigating three fundamental scientific and technological issues: (1) the mechanisms of abstraction of sensory information; (2) the mechanisms underlying intrinsic motivations, e.g. “curiosity drives” that learn to focus attention and learning capabilities on “zones of proximal development”; (3) hierarchical recursive architectures which permit cumulative learning. The study of theseissues will also be fuelled by a reverse-engineering effort aiming at reproducing with bio-mimetic models theresults of empirical experiments run with monkeys, children, and human adults.

The controllers proposed will be validated with challenging demonstrators based on a single humanoid robotic platform (iCub). As a main outcome, the project will significantly advance the scientific and technological state of the art, both in terms of theory and implementations, in autonomous learning systems and robots. This overall goal will be achieved on the basis of the integrated work of a highly interdisciplinary Consortium involvingleading international neuroscientists, psychologists, roboticists and machine-learning researchers.

Project ID: 
FP7-ICT-IP-231722
Project funding: 
FP - European Framework Programmes
Funding source: 
European Commission
Project Timeframe: 
Thu, 01/01/2009 - Tue, 30/04/2013
ISTC Contact Person: 
Gianluca Baldassarre
Coordinator: 

Gianluca Baldassarre,
Laboratory of Computational Embodied Neuroscience,
Istituto di Scienze e Tecnologie della Cognizione,
Consiglio Nazionale delle Ricerche (LOCEN-ISTC-CNR),
Via San Martino della Battaglia 44, I-00185 Roma, Italy

Partners: 

* Elisabetta Visalberghi (Second group from ISTC-CNR)
  Prof. Andrew Barto (Associate ISTC-CNR)

* UCMB - Universita' Campus Biomedico,
   Italy, Rome
   Principal investigator: Eugenio Guglielmelli, Flavio Keller

* USFD - University of Sheffield,
   UK, Sheffield
   Principal investigators: Peter Redgrave, Kevin Gurney

* FIAS - Frankfurt Institute for Advanced Studies,
   Germany, Frankfurt
   Principal investigator: Jochen Triesh

* UU - University of Ulster,
   UK, Ulster
   Principal investigator: Martin McGuinnity

* AU - Aberystwyth University,
   UK, Aberystwyth
   Principal investigator: Mark Lee

* IDSIA-SUPSI - Scuola Universitaria della Svizzera Italiana,
   Switzerland, Lugano
   Principal investigator: Juergen Schmidhuber

Budget
Project Total Budget: 
7,726,783
Project Total EC Contribution: 
5,899,884
ISTC Total Budget: 
2,151,136
ISTC EC Contribution: 
1,681,479
Keywords:
  • Abstraction, Intrinsic motivations, Hierarchical actions, Hierarchical reinforcement learning;