The design of collective decision-making mechanisms for robot swarms engaged in tasks that require consensus among the robots is a challenging problem in swarm robotics. The complexity of this design problem increases with the number of options and the number of cues that robots have to consider to make a decision. The research work presented in this thesis addresses this challenge by exploring the potential of evolutionary robotics (ER) as a design tool for synthesising neural network controllers that underpin the robots' decision-making process. The main objective is to design individual mechanisms that support the emergence of robust, scalable, and effective collective decision-making strategies while avoiding common assumptions made in previous research. These assumptions include pre-defined correlations between environmental features and robot behaviour or the use of specific opinion formation mechanisms, such as the voter or majority rule, to update opinions.

The thesis focuses on two fundamental collective decision-making scenarios: the collective perception scenario and the site selection scenario. The first scenario involves robots collectively identifying the most prevalent element in the environment, represented by the colour covering the largest portion of the arena floor. The second scenario requires the robots to collectively choose the best site among several options based on their quality.

La Faculté d'Informatique de l'UNamur vous invite à la Thèse de Doctorat de Ahmed ALMANSOORI « On the Evolution of Mechanisms for Collective Decision-making in a Swarm of Robots ». 

Dirigée par le Prof. Elio TUCI.

Devant un jury composé de :

  • Prof. Wim VANHOOF, Président, Université de Namur
  • Prof. Elio TUCI, Promoteur, Université de Namur
  • Prof. Patrick HEYMANS, Membre interne, Université de Namur
  • Prof. Muhanad HAYDER MOHAMMED MOHAMMED, Membre interne, Université de Namur
  • Prof. Yara KHALUF, Membre externe, Université de Wageningen (Pays-Bas)

Vous êtes cordialement invités à un drink, qui suivra la soutenance publique.

Pour une bonne organisation, merci de donner votre réponse pour le jeudi 10 octobre au moyen de ce lien.

Contact : Notaro Amelie - amelie.notaro@unamur.be