Introducing myself

I am a directeur de recherches (research director) of the fund for scientific research F.R.S.–FNRS of Belgium's Wallonia-Brussels Federation. I am affiliated with IRIDIA, CoDE, Université Libre de Bruxelles, Brussels, Belgium.

I have been awarded an ERC Consolidator Grant by the European Research Council for the project "DEMIURGE: automatic design of robot swarms".

My research focuses mainly on computational intelligence and in particular on the automatic design of swarm intelligence systems and multi-robot systems. My research interests include also metaheuristics and local search methods for combinatorial optimization. I am particularly interested in the application of statistical methods, design of experiments, and machine learning techniques, notably for assessing the performance of algorithms and for fine-tuning their parameters. I am also interested in epistemology and in the philosophical foundations of computational intelligence.

I am an associate editor for Frontiers in Robotics and AI: Multi-Robot Systems, and an academic editor for PeerJ Computer Science. I served as an associate editor for Swarm Intelligence from 2006 to 2019 and I am currently a member of the editorial board. I also served as a member of the organizing committee for 17 international conferences, and as a member of the program committee for more than 50 international conferences in the last five years. From 2002 to 2018, I served as member of the organizing committee of the series of conferences ANTS. Between 2012 and 2015, I chaired for four times the AAAI Video Competition.

Communications Engineering

Automatic design of stigmergy-based behaviours for robot swarms
Muhammad Salman, David Garzón Ramos, and Mauro Birattari
Communications Engineering, 3:30
DOI: 10.1038/s44172-024-00175-7

About this article

We showed that stigmergy-based behaviours for robot swarms can be produced via automatic design: an optimisation process based on simulations generates collective behaviours for a group of robots that can lay and sense artificial pheromones.

This work is a core contribution of the ERC project DEMIURGE.

Nature Communications

Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms
Ken Hasselmann, Antoine Ligot, Julian Ruddick, and Mauro Birattari
Nature Communications, 12:4345
DOI: 10.1038/s41467-021-24642-3

About this article

We compared some of the most popular and advanced neuro-evolutionary methods for the off-line design of robot swarms. The control software they produced performed well in simulation but not on the real robots: The issue to be addressed is the so-called reality-gap problem.

This work is a core contribution of the ERC project DEMIURGE.

Nature Machine Intelligence

Disentangling automatic and semi-automatic approaches to the optimization-based design of control software for robot swarms
Mauro Birattari, Antoine Ligot, and Ken Hasselmann
Nature Machine Intelligence, 2(9):494–499
Read it online: https://rdcu.be/b6aVI
DOI: 10.1038/s42256-020-0215-0

About this article

We contend that two cases should be disentangled in the optimization-based design of robot swarms: semi-automatic design, in which a human designer operates and steers an optimisation process; and (fully) automatic design, in which the optimisation process does not involve, need, or allow any human intervention.

This work is a core conceptual contribution of the ERC project DEMIURGE.

Science Robotics

TS-Swarm
Autonomous task sequencing
in a robot swarm
Lorenzo Garattoni and Mauro Birattari
Science Robotics, 3(20):eaat0430
DOI: 10.1126/scirobotics.aat0430

About this article

We shows that a robot swarm can collectively determine the correct order in which some given tasks must be executed, even if the individual robots comprised in the swarm are unable to do it alone. In a robot swarm, the ability to collectively sequence tasks, which is an albeit simple form of planning, can emerge from the interaction of reactive individual robots.

The research was conducted in the context of the ERC project DEMIURGE.

Science

Science covered our work. See Shandria Sutton's "Simple robots form a chain gang to solve complex problems", doi:10.1126/science.aau8870

See also the video they produced:

ERC Consolidator Grant

The DemiurgeDEMIURGE
Automatic Design of Robot Swarms

The research project "DEMIURGE: automatic design of robot swarms" has been selected for funding by the European Research Council via an ERC Consolidator Grant — principal investigator: Mauro Birattari

The scope of the project is the automatic design of robot swarms. Swarm robotics is an appealing approach to the coordination of large groups of robots. Up to now, robot swarms have been designed via some labor-intensive process. My goal is to advance the state of the art in swarm robotics by developing the DEMIURGE: an intelligent system that is able to design and realize robot swarms in a totally integrated and automatic way.

Lecture on the automatic modular design of robot swarms

In this lecture, I sketch the fundamental concepts of the automatic modular design of collective behaviors for robot swarms and I presents my research.

Course: Swarm Intelligence (INFO-H-414), Université libre de Bruxelles. Acedemic year: 2020-2021.

Swarmanoid the movie

The video "Swarmanoid, the movie" won the Best Video Award at the AAAI-11 AI Video Competition; the Innovative Technology Award at the Robot Film Festival; and the Prix Wernaers 2012 pour la recherche et la diffusion des connaissances.

This video, written and directed by myself and Rehan O'Grady, presents the main results of the Swarmanoid project, a FET-OPEN project funded by the European Commission and coordinated by Marco Dorigo. For more information, see the website of the Swarmanoid project.

Books

SCI197 Tuning Metaheuristics
A machine learning perspective
M. Birattari. Springer, 2009

About this book

The importance of tuning metaheuristics is widely acknowledged. However, there is very little dedicated research on the subject. Typically, scientists and practitioners tune metaheuristics by hand, guided only by their experience and by some rules of thumb. Tuning metaheuristics is often considered to be more of an art than a science.

This book lays the foundations for a scientific approach to tuning metaheuristics. The fundamental intuition that underlies Birattari's approach is that the tuning problem has much in common with the problems that are typically faced in machine learning. By adopting a machine learning perspective, the author gives a formal definition of the tuning problem, develops a generic algorithm for tuning metaheuristics, and defines an appropriate experimental methodology for assessing the performance of metaheuristics.