AutoMoDe-Chocolate: a Method for the Automatic Design of Robot Swarms that Outperforms Humans

We present two empirical studies on the design of robot swarms. In Study A, Vanilla and EvoStick, two previously published automatic methods, are compared with human designers. The comparison is performed on five new swarm robotics tasks, different from those on which Vanilla and EvoStick have been previously tested. The results show that Vanilla performs better than EvoStick but it is not able to outperform human designers. The results indicate that Vanilla’s weak element is the optimization algorithm employed to search the space of candidate designs. To improve over Vanilla and with the goal of obtaining an automatic design method that performs better that the human designer, we introduce Chocolate, which differs from Vanilla only in the fact that it adopts a more powerful optimization algorithm. In Study B, we perform an assessment of Chocolate. The results show that Chocolate outperforms both Vanilla and the human designers: Chocolate is the first automatic design method for robot swarms that is shown to outperform a human designer.