Learning Based Leadership in Swarm Navigation

Collective migration in biological species is often guided by distributed leaders that modulate their peers’ motion behaviors. Distributed leadership is important for artificial swarms, but designing the leaders’ controllers is difficult. A swarm control strategy that leverages trained leaders to influence the collective’s trajectory in spatial navigation tasks was formulated. The neuro-evolutionary learning based control method was used to train a few leaders to influence motion behaviors. The leadership control strategy is applied to a rally task with varying swarm sizes and leadership percentages. Increasing the leadership representation improved task performance. Leaders moved quickly when the swarm had a higher percentage of leaders and slowly when the percentage was small.