Evolution of Coordinated Motion Behaviors in a Group of Self-Assembled Robots
Trianni Vito

Abstract:

In this work, we introduce a swarm robotic system, called a swarm-bot. A swarm-bot is a self-assembling and self-organizing artifact composed of a swarm of s-bots, mobile robots with the ability to connect to/disconnect from each other. In particular, we address the problem of synthesizing controllers for the swarm-bot using Artificial Evolution. We describe the motivation behind the choice of the evolutionary approach and we provide examples of its application, detailing the results obtained in different tasks, namely coordinated motion and hole avoidance. We show how evolution is able to produce simple but effective solutions, which lead to the emergence of self-organization in the swarm-bot.