Swarm Intelligence

Swarm intelligence is the discipline that deals with natural and artificial systems composed of many individuals that coordinate using decentralized control and self-organization. In particular, the discipline focuses on the collective behaviors that result from the local interactions of the individuals with each other and with their environment. Examples of systems studied by swarm intelligence are colonies of ants and termites, schools of fish, flocks of birds, herds of land animals. Some human artifacts also fall into the domain of swarm intelligence, notably some multi-robot systems, and also certain computer programs that are written to tackle optimization and data analysis problems. The course will present a number of swarm intelligence systems and will give the opportunity to experiment with them.

To let students have a basic understanding of swarm intelligence principles. Learn how to solve an optimization problem and control a swarm of robots using a swarm intelligence technique.

Ex catedra and projects.

References, bibliography, and recommended reading

• Dorigo M. & T. Stützle (2004). Ant Colony Optimization. Cambridge, MA: MIT Press/Bradford Books

• Bonabeau E., M. Dorigo & G. Theraulaz (1999). Swarm Intelligence: From Natural to Artificial Systems. New York, NY: Oxford University Press

• Francesca G. and M. Birattari (2016). Automatic design of robot swarms: Achievements and challenges. Frontiers in Robotics and AI, 3:29

Contacts

• Mauro Birattari - IRIDIA-CoDE CP 194/6 Tel. 02 650 3168 Email: mbiro@ulb.ac.be

• Marco Dorigo - IRIDIA-CoDE CP 194/6 Tel. 02 650 3169 Email: mdorigo@ulb.ac.be

Campus

Solbosch

Method(s) of evaluation

• Project
• Oral examination

Project

Oral examination

• Open question with short answer
• Open question with long development

Project to be carried out individually (not in groups) + oral examination.

Mark calculation method (including weighting of intermediary marks)

The evaluation of the course consists of three parts: two oral examinations and a project evaluation. To pass the course, you must pass each of the three parts separately with a minimum mark of 10/20. If you pass all three parts, your final mark will be computed as the average of the marks obtained in the three parts. If you do not pass all three parts, your final mark will be the lowest mark obtained in any of the three parts.

Language(s) of evaluation

• english