Swarm Intelligence

Swarm Intelligence (SI) is the property of a system whereby the collective behaviours of (unsophisticated) agents interacting locally with their environment cause coherent functional global patterns to emerge. SI provides a basis with which it is possible to explore collective (or distributed) problem solving without centralized control or the provision of a global model. A description of the ideas of coordination without communication can be found on Stan Franklin's coordination page.

A good introduction to the ideas and principles of SI can be found here.

A presentation on Swarm Intelligence -- focussing on the Ant Search foraging behaviour as a metaphor for distributed problem solving -- can be found in the following slides. This presentation has been developed for an 800x600 resolution screen where slides cover 3/4 of the screen. A presentation that deals with multi-swarm problem solving can be found in the following slides. The presentation has been created for an 800x600 resolution screen where slides cover 3/4 of the screen.

Publications

  1. World Scientific Series in Robotics and Intelligent Systems Vol.10.
  2. Intelligent Behaviour in Animals and Robots
  3. Artificial Life: an Overview
  4. Artificial Life IV
  5. Artificial Life V
  6. Fourth European Conference on Artificial Life
  7. Towards a Practice of Autonomous Systems
  8. Turtles, Termites and Traffic Jams
Software
  1. Swarm, an Alife simulation package from the Santa Fe Institute.
  2. Latent Energy Environments by Filippo Menczer and Rik Belew
  3. Many software packages can be found here
Links
  1. Implementation of mobile agents using SI on the MOLE platform.
  2. Complexity, self organization and artificial life.
  3. Useful set of WWW pages related to evolution and behaviour.
  4. Artifical life, ants, genetics, evolution and all that.
  5. Alife Online at Santa Fe.
  6. Distributed Artificial Intelligence and Multi-agent System archive
  7. Artificial life archive with many applets
  8. Complex Systems Virtual Library: Parallel Computation
  9. Complex Systems Virtual Library: Artificial Life
People
  1. GerardoBeni and Susan Hackwood, Electrical Engineering Department, U. California, Riverside
  2. Marco Dorigo, University of Free Brussels, Belgium
  3. Alexis Drogoul, Laboratoire d'Informatique de Paris 6
Groups
  1. NASA work on model-based autonomous systems
  2. Xerox Parc: Dynamics of Computation
  3. COGS (University of Sussex)
  4. Virginia Tech, Robotics and Machine Intelligence Laboratories
Demonstration applets

    A really nice applet for sorting can be found here.

  1. Evolving ant colonies foraging for food
  2. Evolving ants using Genetic Programming for foraging
  3. Simple swarming behaviour
  4. "Boids" - an example of flocking behaviour
This page is under construction and reflects the emerging knowledge of the author on Swarm Intelligence.