Title : On the evolution of adaptable and scalable mechanisms for collective decision-making in a swarm of robots

Abstract : A swarm of robots can collectively select an option among the available alternatives offered by the environment through a process known as collective decision-making. This process is characterised by the fact that once the group makes a decision, it can not be attributed to any of its group members. In swarm robotics, the individual mechanisms for collective decision-making are generally hand-designed and limited to a restricted set of solutions based on the voter or the majority model. In this talk, I demonstrate that it is possible to take an alternative approach in which the individual mechanisms are implemented using artificial neural network controllers automatically synthesised using evolutionary computation techniques. In collaboration with my colleagues, we qualitatively describe the group dynamics underlying the collective process leading to consensus, which in this work is defined as 100\% of robots holding the same opinion about the environment type. We carry out extensive comparative tests that quantitatively evaluate, on a perceptual discrimination task, the performance of the most commonly used decision-making mechanisms (voter model and majority model) with the proposed dynamic neural network model under various operating conditions and for swarms that differ in size. The results of our study clearly indicate that the performances of a swarm employing dynamical neural networks as the decision-making mechanism are more robust, more adaptable to a dynamic environment, and more scalable to a larger swarm size than the performances of the swarms employing the Voter model and the majority model. The presented results are validated using a multi-agent simulation and a swarm of physical e-puck2 robots.