page d'accueil   sommaire  

Marco DORIGO


coordonnées


Ecole polytechnique de Bruxelles
Marco DORIGO
tel 02 650 31 69, fax 02 650 27 15, Marco.Dorigo@ulb.ac.be
Campus du Solbosch
CP194/06, avenue F.D. Roosevelt 50, 1050 Bruxelles




unités de recherche


CoDE-IRIDIA-Metaheuristiques [CoDE-IRIDIA-Metaheuristics] (IRIDIA-Meta)
CoDE-IRIDIA-Robotique [CoDE-IRIDIA-Robotique] (IRIDIA-Robo)
Service ingénierie de l'informatique et de la décision [Department of Computer and Decision Engineering] (CoDE)



projets


Algorithmes basés sur le comportement collectif des fourmis et intelligence en essaim. [Ant algorithms and swarm intelligence]
Les algorithmes basés sur le comportement collectif des fourmis et l'intelligence en essaim : conception d'algorithmes d'optimisation et de contrôle distribué inspirés par les études du comportement collectif des insectes sociaux.Cette recherche est consacrée à l'étude et à l'utilisation de modèles comportementaux des insectes sociaux en vue d'élaborer des algorithmes distribués. Les applications s'étendent du domaine de la robotique distribuée au dessin graphique et à l'optimisation combinatoire. [Ant algorithms and swarm intelligence : Study and design of novel distributed algorithms for optimization and control inspired by the observation of the collective behavior of social insects. This research is devoted to the study and use of models of the behavior of social insects to design distributed algorithms. Applications range from distributed robotics to graph drawing and combinatorial optimization.]

Métaheuristiques [Metaheuristics]
Etude d'approches métaheuristiques pour la résolution de problèmes d'optimisation discrète. La recherche porte autant sur l'étude exhaustive des techniques classiques ( comme les algorithmes génétiques, le recuit simulé, la recherche tabou, l'optimisation par colonie de fourmis, la recherche locale itérée) que sur le développement de nouvelles métaheuristiques. [Study of metaheuristic approaches to the solution of discrete optimization problems. The research covers both the study of all the major techniques (like genetic algorithms, simulated annealing, tabu search, and colony optimization, iterated local search) and the development of new metaheuristics.]

Robotique collective [Swarm robotics]
Le but de cette recherche à long terme est de développer une méthodologie intégrée pour le développement d'agents autonomes qui interagissent avec un environnement physique. Les principaux sujets de recherche sont : la spécification de comportements cibles, l'élaboration d'interfaces sensorimotrices, la conception d'architectures de contrôle d'agent, l'utilisation d'un algorithme d'apprentissage machine en vue de développer des programmes de contrôle en relation étroite avec l'environnement, l'élaboration de stratégies d'entraînement dépendantes du domaine et l'évaluation des performances. [The long-term research goal is to develop an integrated methodology for the development of autonomous agents that interact with a physical environment. Specific research topics are the specification of target behaviors, the design of sensorimotor interfaces, the design of the agent's control architecture, the use of machine learning algorithm to develop control programs strongly coupled with the environment, the design of domain-dependent training strategies, and the evaluation of performance.]

Métaheuristiques [Metaheuristics]
Etude d'approches métaheuristiques pour la résolution de problèmes d'optimisation discrète. La recherche porte autant sur l'étude exhaustive des techniques classiques (comme les algorithmes génétiques, le recuit simulé, la recherche tabou, l'optimisation par colonie de fourmis, la recherche locale itérée) que sur le développement de nouvelles métaheuristiques. [Study of metaheuristic approaches to the solution of discrete optimization problems. The research covers both the study of all the major techniques (like genetic algorithms, simulated annealing, tabu search, and colony optimization, iterated local search) and the development of new metaheuristics.]

Algorithmes basés sur le comportement collectif des fourmis et l'intelligence en essaim. [Ant algorithms and swarm intelligence]
Conception d'algorithmes d'optimisation et de contrôle distribué inspirés par les études du comportement collectif des insectes sociaux. Cette recherche est consacrée à l'étude et à l'utilisation de modèles comportementaux des insectes sociaux en vue d'élaborer des algorithmes distribués. Les applications s'étendent du domaine de la robotique distribuée au dessin graphique et à l'optimisation combinatoire. [Study and design of novel distributed algorithms for optimization and control inspired by the observation of the collective behavior of social insects. This research is devoted to the study and use of models of the behavior of social insects to design distributed algorithms. Applications range from distributed robotics to graph drawing and combinatorial optimization.]

E-SWARM: Engineering Swarm Intelligence Systems [E-SWARM: Engineering Swarm Intelligence Systems]
E-SWARM est un projet financé par le programme Advanced Grants de l'European Research Council (ERC) de l'Union Européenne (Bourse 246939). Le but de ce projet est de développer un ensemble de méthodes rigoureuses d'ingénierie pour la conception et la réalisation de systèmes artificiels d'intelligence en essaim. [E-SWARM is a project funded by the European Research Council - Advanced Grants program of the European Union (Grant 246939). Its goal is to develop a rigorous engineering methodology for the design and implementation of artificial swarm intelligence systems.]

Swarmanoid: Towards Humanoid Robotics Swarms (2006-2010) [Swarmanoid: Towards Humanoid Robotics Swarms (2006-2010)]
L'objectif scientifique principal de cette recherche est la conception, l'implémentation et le contrôle d'un nouveau type de système robotique distribué. Le système sera composé de petits robots autonomes hétérogènes capables de se connecter dynamiquement. L'ensemble de ces robots constituera ce que l'on appelle un ''swarmanoid''. [The main scientific objective of this research project is the design, implementation and control of a novel distributed robotic system. The system will be made up of heterogeneous, dynamically connected, small autonomous robots. Collectively, these robots will form what we call a ''swarmanoid''.]

Swarm-bots: Swarms of self-assembling artefacts (2001-2005) [Swarm-bots: Swarms of self-assembling artefacts (2001-2005)]
L'objectif scientifique principal du projet Swarm-bots est l'étude d'une nouvelle approche pour la conception et pour l'implémentation d'artefacts capables de s'auto-organiser et de s'auto-assembler. Cette nouvelle approche trouve ses origines dans les récentes études sur l'intelligence en essaim. Il s'agit de l'étude des capacités d'auto-organisation et d'auto-assemblage démontrées par les insectes sociaux et autres sociétés d'animaux. [The main scientific objective of the Swarm-bots project is to study a novel approach to the design and implementation of self-organising and self-assembling artefacts. This novel approach finds its theoretical roots in recent studies in swarm intelligence, that is, in studies of the self-organising and self-assembling capabilities shown by social insects and other animal societies.]



publications


Dorigo M. and U.Schnepf (1993). Genetics-based Machine Learning and Behaviour Based Robotics: A New Synthesis. IEEE Transactions on Systems, Man, and Cybernetics, 23, 1, 141-154.

Dorigo M. and M. Colombetti (1994). Robot Shaping: Developing Autonomous Agents through Learning. Artificial Intelligence, 71, 2, 321-370.

Colombetti M. and M. Dorigo (1994). Training agents to perform sequential behavior. Adaptive behavior, MIT Press, 2, 3, 247-275.

Dorigo M. (1993). Genetic and Non-Genetic Operators in Alecsys. Evolutionary Computation Journal, 1, 2, 151-164, MIT Press.

Dorigo M. (1995). Alecsys and the AutonoMouse: Learning to Control a Real Robot by Distributed Classifier Systems. Machine Learning, 19, 3, 209-240.

Patel M.J., M. Colombetti and M. Dorigo (1995). Evolutionary learning for intelligent automation: A case study. Intelligent Automation and Soft Computing journal, 1, 1, 29-42.

Colombetti M., M.Dorigo and G.Borghi (1996). Behavior Analysis and Training: A Methodology for Behavior Engineering. IEEE Transactions on Systems, Man, and Cybernetics-Part B, 26, 3, in press.

Dorigo M. (1996). Editorial Introduction to the Special Issue on Learning Autonomous Robots. (Editorial) IEEE Transactions on Systems, Man, and Cybernetics-Part B, 26, 3, in press.

Dorigo M. and U. Schnepf (1991). Organisation of Robot Behaviour Through Genetic Learning Processes. Proceedings of the Fifth IEEE International Conference on Advanced Robotics, Pisa, Italy, IEEE Press, 1456-1460.

Dorigo M. and E. Sirtori (1991). Alecsys: A Parallel Laboratory for Learning Classifier Systems. Proceedings of the Fourth International Conference on Genetic Algorithms, San Diego, California, R.K.Belew and L.B.Booker (Eds.), Morgan Kaufmann, 296-302.

Colombetti M. and M. Dorigo (1992). Learning to Control an Autonomous Robot by Distributed Genetic Algorithms. Proceedings of From Animals to Animats, Second International Conference on Simulation of Adaptive Behavior (SAB92), Honolulu, HI, USA, J.-A.Meyer, H.L.Roitblat and S.W.Wilson (Eds.), MIT Press, 305-312.

Dorigo M., M.J. Patel and M. Colombetti (1994). The effect of sensory information on reinforcement learning by a robot arm. Proceedings of ISRAM'94, Fifth International Symposium on Robotics and Manufacturing, August 14-18, 1994, Maui, HI, USA, M.Jamshidi et al. (Eds.), ASME Press, 83-88.

Dorigo M. and M. Colombetti (1994). The role of the trainer in reinforcement learning. Proceedings of MLC-COLT '94 Workshop on Robot Learning, S.Mahadevan et al. (Eds.), July 10th 1994, New Brunswick, NJ, 37-45.

Patel M.J. and M. Dorigo (1994). Adaptive Learning of a Robot Arm. Proceedings of Evolutionary Computing: AISB Workshop, Leeds, U.K., April 1994, Selected Papers, T.C.Fogarty (Ed.), Lecture Notes in Computer Science 865, Springer-Verlag, 180-194.

Colombetti M., M. Dorigo and G. Borghi (1996). Robot shaping: The Hamster experiment. Proceedings of ISRAM'96, Sixth International Symposium on Robotics and Manufacturing, May 28-30, Montpellier, France, M.Jamshidi et al. (Eds.), to appear.

Colombetti M. and M. Dorigo (1996). Evolutionary computation in behavior engineering. In Evolutionary Computation: Theory and Applications, X. Yao (Ed.), World Scientific Publ. Co., Singapore. To appear.



theses


Dorigo, M. The Robot Shaping Approach to Behavior Engineering. Thèse d'Agrégation de l'Enseignement Supérieur, Faculté des Sciences Appliquées, Université Libre de Bruxelles, Belgium, 1995

Dorigo, M., ''The robot shaping approach to behavior engineering'' Dissertation présentée pour l'obtention du grade d'Agrégé de l'Enseignement supérieur auprès de la Faculté des Sciences appliquées, ULB, Bruxelles, 1996

Dorigo M. Optimization, Learning, and Natural Algorithms. Professor Alberto Colorni (directeur), Politecnico di Milano, Italy, 1992

Dorigo, Marco. ''Ottimizzazione, apprendimento automatico, ed algoritmi basati su metafora naturale (Optimization, Learning, and Natural Algorithms)'' Doctorate in Systems and Information Electronic Engineering, Politecnico di Milano, Italy, 1992



prix


ASSOCIATE EDITOR for the IEEE Transactions on Systems, Man, and Cybernetics (since 1993, Vol.23, No.3).

MEMBER OF THE EDITORIAL BOARD of the following international journals: Evolutionary Computation Journal, MIT Press (since 1993, Vol.1, No.1) Adaptive Behavior Journal, MIT Press (since 1996, Vol.4, No.1)

GUEST EDITOR of the following special issues: Special Issue of the IEEE Transactions on Systems, Man, and Cybernetics-Part B on Autonomous Learning Robots (to appear in June 1996, Vol.26, No.3). Special Issue of Adaptive Behavior (MIT Press) on Collective Intelligence (forthcoming).

ORGANIZER of the following conferences: First International Contest on Evolutionary Optimization (ICEO-1), to be held at Nagoya University, Japan (May 20-22, 1996); Second European Workshop On Reinforcement Learning (EWRL-2), Milano, Italy (September 18-19, 1995); First European Workshop On Reinforcement Learning (EWRL-1), Brussels, Belgium (September 27-28, 1994).

EUROPEAN LIAISON CHAIR for the 1995 IEEE Conference on Evolutionary Computation, Perth, Western Australia (November 29 - December 1, 1995).

MEMBER OF THE PROGRAM COMMITTEE for the following conferences and workshops: ICANNGA97 - Third International Conference on Artificial Neural Networks and Genetic Algorithms, to be held at the University of East Anglia, Norwich, UK (April 2-4, 1997). ICEC-PPSN96, Fourth International Conference on Parallel Problem Solving From Nature, to be held in Berlin, Germany (September 22-27, 1996). GP-96 - Genetic Programming 96, to be held at Stanford University, Stanford, California (July 28-31, 1996). IMACS96, to be held at Lille, France (July 9-12, 1996). EVONET/ICML96 - Workshop on Evolving Learning Systems, to be held in Bari, Italy (July 1-2 1996). ROSYCS96 - Romanian Symposium on Computer Science, to be held at University of Iasi, Romania (May 30-June 1, 1996). 1996 IEEE 3rd International Conference on Evolutionary Computation (ICEC96), to be held at Nagoya University, Japan (May 20-22, 1996). 1996 AISB Workshop on Evolutionary Computing, to be held at University of Sussex, Brighton, UK (April 1-2, 1996 prix@28=INVITED SPEAKER at the following conferences: ROSYCS96 - Romanian Symposium on Computer Science, to be held at University of Iasi, Romania, May 30 - June 1, 1996. NSF Workshop on Reinforcement Learning, Hilltop House, Harper's Ferry, MD, USA, April 12-14, 1996. IEE Colloquium on Self-learning robots, Savoy Place, London, UK, February 12, 1996. BENELEARN-95, 5th Belgian-Dutch Conference on Machine Learning, Université Libre de Bruxelles, September 15, 1995. SFI Working Group on Learning and Adaptation in Robots and Situated Agents, Santa Fe Institute, NM, USA, May 9-13, 1993.

Premio Italiano per l'Intelligenza Artifciale 1996.

Qualification for the function of university professor in France (since Feb 16, 1995)

Winner of a tenured position as assistant professor at Politecnico di Milano (December 1995). Position not accepted (in order to accept the position offered by the FNRS at the University of Brussels)

Fellow of the IEEE (Institute of Electronical Engineers), 2006.

Dr. Dorigo's Marie Curie fellowship results have been selected by the European Commission as one of the 'MARIE CURIE FELLOWSHIPS SUCCESS STORIES' (document EUR 17763 published by the European Commision in December 1997)

Coordinator of the European 'Metaheuristics Network' funded by the European Union within the Improving Human Potential program. 2000-2003(36 months). Funding: 985,000 EUR

Coordinator of the European 'Marie Curie Training Site' funded by the European Union within the Improving Human Potential program. 2000-2004 (48 months).Funding: 158,000 EUR.

FNRS research award for building a 'Beowulf' style cluster of PCs. 2000-2001. Funding 17,000 EUR.

Scientist in charge and research director for a 24 months Marie Curie postdoctoral fellowship awarded to Dr. Hussain Saleh by the EC funded Improving Human Potential programme. Funding: 152,000 EUR.

Scientist in charge and research director for a 24 months Marie Curie postdoctoral fellowship awarded to Dr. Stefka Fidanova by the EC funded Improving Human Potential programme. Funding: 152,000 EUR

Scientist in charge and research director for a 24 months Marie Curie postdoctoral fellowship awarded to Dr. Nicolas Meuleau by the EC funded Improving Human Potential programme. Funding: 152,000 EUR

''FNRS - Dr A. De Leeuw-Damry-Bourlart award in Applied Sciences'' for his fundamental contributions to the foundation of the swarm intelligence research field, 2005.

Marie Curie Excellence Award for research on Ant Colony Optimization and Ant Algorithms, 2003.

Premio Italiano per l'Intelligenza Artifciale 1996.

Fellow of the IEEE (Institute of Electronical Engineers), 2006.

Fellow of ECCAI (European Coordinating Committee for Artificial Intelligence), 2007.

Fellow of ECCAI (European Coordinating Committee for Artificial Intelligence), 2007.

Dr. Dorigo's Marie Curie fellowship results have been selected by the European Commission as one of the 'MARIE CURIE FELLOWSHIPS SUCCESS STORIES' (document EUR 17763 published by the European Commision in December 1997)

''FNRS - Dr A. De Leeuw-Damry-Bourlart award in Applied Sciences'' for his fundamental contributions to the foundation of the swarm intelligence research field, 2005.

Marie Curie Excellence Award for research on Ant Colony Optimization and Ant Algorithms, 2003.

CajAstur International Prize for Soft Computing, Spain, 2007.

CajAstur International Prize for Soft Computing, Spain, 2007

Best Video Award at the AAAI-07 AI Video Competition, Vancouver, 2007.

IEEE Transactions on Evolutionary Computation Outstanding Paper Award, 2007 .

Premio Italiano per l'Intelligenza Artifciale 1996. - Marco DORIGO

Fellow of the IEEE (Institute of Electronical Engineers), 2006. - Marco DORIGO

Fellow of ECCAI (European Coordinating Committee for Artificial Intelligence), 2007. - Marco DORIGO

''FNRS - Dr A. De Leeuw-Damry-Bourlart award in Applied Sciences'' for his fundamental contributions to the foundation of the swarm intelligence research field, 2005. - Marco DORIGO

Marie Curie Excellence Award for research on Ant Colony Optimization and Ant Algorithms, 2003. - Marco DORIGO

CajAstur International Prize for Soft Computing, Spain, 2007 - Marco DORIGO

Prix pour la meilleure vidéo au ''AAAI-07 AI Video Competition'', Vancouver, 2007.

''IEEE Transactions on Evolutionary Computation Outstanding Paper Award, 2007'', pour l'article: ''Search Bias in Ant Colony Optimization: On the Role of Competition-Balanced Systems,'' IEEE Transactions on Evolutionary Computation, 9(2):159-174, April 2005.

''Best Paper Award'' à la ''Eight Conference on Intelligent Autonomous Systems (IAS-8)'', Amsterdam, The Netherlands, pour l'article: ''Hole Avoidance: Experiments in Coordinated Motion on Rough Terrain'', 2004.

Marco Dorigo was awarded an ERC Advanced Grant for the project ''E-Swarm: Engineering Swarm Intelligence Systems''

ERC Advanced Grant for the project ''E-SWARM: Engineering Swarm Intelligence Systems'', 2010. - Marco DORIGO

ERC Advanced Grant pour le projet ''E-SWARM - Engineering Swarm Intelligence Systems'', 2010

The paper ''An Incremental Ant Colony Algorithm with Local Search for Continuous Optimization'' has received the best paper award of the ACO-SI track at GECCO 2011.

Best Video Award at the AAAI-11 AI Video Competition, San Francisco, CA, 2011.

Prix Wernaers, pour la recherche et la diffusion des connaissances. F.R.S.-FNRS, 2012

Botsker Award for the Most Innovative Technology. Robot Film Festival. New York, July 2012



disciplines et mots clés déclarés


Automatisme et régulation Cybernétique Intelligence artificielle Recherche opérationnelle Théorie des algorithmes

algorithmes basés sur le comportement collectif des fourmis algorithmes des fourmis algorithmes génétiques distributed optimization heuristiques intelligence en essaim métaheuristiques optimisation distribuée optimisation par colonies de fourmis recherche locale itérée recherche tabou recuit simulé robotique collective robotique en essaim systémes adaptatives