No abstract

In this paper we present a coordination model for multi-robot systems based on cooperative behaviors, where the low level behaviors are obtained through artificial neural networks and evolutionary algorithms to achieve a common goal. For this purpose, we have defined two strategies of self-alignment to carry out the docking process between two robots. Both strategies share the same goal of achieving an optimal alignment between two robots. The main difference between these strategies is that: the strategy 1 consists of having one active and one inactive robot, and in the strategy 2 both robots are active. Experimental results are presented by a robotic device simulator (Player) and a multi-robot simulator 2D (Stage) for each strategy displaying differences between both strategies and benefits in time execution. The paper ends with a critical discussion of experimental results.