SOCIAL

  • Info

    Title Self-Organised Societies of Connectionist Intelligent Agents capable of Learning

    Acronym SOCIAL

    Framework FET Open

    Project Number IST-2001-38911

    Start – End Date 01/01/2003 – 31/05/2006

    Duration 41 months

    Instrument / Type FET

    Funding Agency European Union’s Information Society Technologies programme (IST-FET)

    Total Project Funding1.590.000,00 €

    Project Homepage http://daisy.cti.gr/social-spike/

    Status Completed

Description

This project designed and developed teams of co-operating autonomous agents, which could generally be used to expand the action-horizon of humans in inaccessible industrial fluidic applications. Successful collective performance in these missions critically depends upon: (a) accurate environmental perception, (b) a real time decision making and action loop, (c) emergent goal directed social behavior.

Individual agents are composed of:

  • A sensor/actuator subsystem which provides multiple input data and enables real-time navigation.
  • A communication subsystem that supports self-organization of behavior at a social level
  • A computational subsystem which analyzes the information of the sensory channels, controls the actuator subsystems of the agent and initiates and maintains goal-directed individual and social behavior among agents. The computational subsystem is composed of simple connectionist spiking neural networks. The latter are realized in spiking neural hardware, chosen for its ability to meet the real time signal processing imposed by the application context.

The project demonstrates the feasibility of the concept by developing an early prototype; the project progress towards the ultimate goals is measured by implementing and testing successive generations of agents. In accordance with potential application areas, two types of agents have been implemented and tested:

  • Hybrid-agents, exploring micro-environments in simulations.
  • Micro-scale containing reduced versions of the architectures for fault location and repair in actual fluidic environments.

Project Outcomes

In order to meet these requirements, we:

  1. Propose a novel agent architectural design based on modular Spiking Neural Network, which serves as a “blueprint” for agent manufacture
  2. Research direct/indirect communication mechanisms for collaborative societies formation, and agent to environment communication.
  3. Design and develop an accompanying Development Environment, which facilitates the evolution of complex agent SNN architectures- multiagent societies, and the development of successive CAA generations.

PUBLICATIONS

  • O’Flynn, B., Buckley J., Laffey D., Barton J., O’Mathuna S.C. – Simulation, Design, Development and Test of Antennas for Wireless Sensor Network Systems, 30thInternational Conference IMAPS Poland, Cracow, 24-27 Sept. 2006 (TYNDALL)
  • H. Hagras, M. Colley, V. Callaghan, “Collaborating Multi Robotic Agents for Operations in Inaccessible Environments”, Proceedings of the IEE International Conference on Autonomous Systems, pp. 55-76, London, UK, November 2005.
  • Zaharakis, I. D., Kameas, A. D.: “Emergent Phenomena in AmI Spaces” in 1st International EASST-EU Workshop on Future Research Challenges for Software and Services, associated to The European Joint Conferences on Theory and Practice of Software (ETAPS’06), April 1st, 2006, Vienna, Austria (CTI)
  • Stamatis, P., Zaharakis, I. D., Kameas, A. D. “Exploiting Ambient Information into Reactive Agent Architectures”. In Proceedings of 2nd International Conference on Intelligent Environments (IEE06), July 5-6, 2006, Athens, Hellas (CTI)
  • H. Hagras, M. Colley, A. Pounds-Cornish, G. de Souza, V. Callaghan, G. Nikiforidis, C. Argyropoulos, A. Kameas, and F. Murphy. A Collaborating Team of Spiking Neural Network Based Robotic Agents for Inaccessible Fluidic Environments. Proceedings of IEEE International Conference on Systems, Man and Cybernetics. Anonymous. Anonymous. Taipei, Taiwan: 2006. (UESSEX,UOP,CTI,TYNDALL)
  • M. Colley, G. De Souza, H. Hagras, A. Pounds-Cornish, G. Clarke, V. Callaghan, “Towards Developing Micro-scale Robots For Inaccessible Fluidic Environments”, Proceedings of IEEE International Conference on Systems, Man and Cybernetics, pp.5279-5285, The Hague, Holland, October 2004.
  • H. Hagras, A. Pounds-Cornish, M. Colley, V. Callaghan, G. Clarke, “Evolving Spiking Neural Network Controllers for Autonomous Robots”, Proceedings of the 2004 IEEE International Conference on Robotics and Automation, pp. 4620- 4626, New Orleans, USA, April 2004.
  • K.M. Razeeb, S. Bellis, J. Townley, K. Delaney, “Micron Scale Mobile Sensor Modules for In-Line Repair of Dialysis Filters” , BioResearch Day, Bio Research day, Biosciences Institute, UCC, Cork, Ireland, 3rd September 2003.
  • S. Bellis, “Development of Wireless Sensor Networks for Ambient Systems”, Invited talk Wireless Sensor Networks and Applications Dagstuhl Seminar, Dagstuhl, Germany, Mar 15-20, 2004. (See here for slides)
  • C. R. Saha, S. J. Bellis, A. Mathewson and E. M. Popovici, “Performance Enhancement Defect Tolerance in the Cell Matrix Architecture”, 24th International Conference on Microelectronics (MIEL 2004), May 16-19, 2004, University of Nis, Serbia & Montenegro, pp. 777-780.
  • Creating Systems for Ambient Intelligence, Chapter accepted for publication in “Silicon: Evolution and Future of a Technology”, EMRS Silicon book, Springer-Heidelberg, eds. Siffert and Krimmel, July 2004 pp 489-514.
  • S. Bellis, K. M. Razeeb, C. Saha, K. Delaney, C. O’Mathuna, A. Pounds-Cornish, G. de Souza, M. Colley, H. Hagras, G. Clarke, V. Callaghan, C. Argyropoulos, C. Karistianos, G. Nikiforidis,
    FPGA Implementation of Spiking Neural Networks – an Initial Step towards Building Tangible Collaborative Autonomous Agents”,FPT’04, International Conference on Field-Programmable Technology, The University of Queensland, Brisbane, Australia, 6-8 December, 2004, pp. 449-452.
  • S. J. Bellis, K. Delaney, B. O’Flynn, J. Barton, K. M. Razeeb, C. O’Mathuna, “Development of Field Programmable Modular Wireless Sensor Network Nodes for Ambient Systems” , Computer Communications – Accepted for Special Issue on Wireless Sensor Networks, to appear in 2005.

Publicity

Project Presentation in the first year review meeting held in Brussels, January 30th, 2004

Other

Video which shows the basic functionality of the Multi Agent Based Simulation Environment (M.A.S.E.)

Contact

Prof. Dr. Achilles Kameas

kameas cti.gr cti.gr

Tel.: +30 261 0 960491 /- 960300
Fax: +302610960490

N. Kazantzaki Str., 26504 Rion, University Campus of Patras, Greece

Tags

Autonomous agents
micro-environments
collective performance
agent architectural design
Spiking Neural Network