Graduate Thesis Or Dissertation


Artificial Swarm Control Through Learning Based Leadership Public Deposited

Downloadable Content

Download PDF


Attribute NameValues
  • Collective migration in animal groups is often guided by distributed leader agents that influence their peers by modulating their motion behaviors. Distributed leadership is a promising navigation strategy for artificial swarms, but designing the leaders’ controllers is difficult due to the swarm’s collective emergent behaviors. The presented research formulates a swarm control strategy that leverages trained leaders to influence the collective’s trajectory in spatial navigation tasks. A swarm’s decentralized architecture is advantageous for scalability and robustness, but poses challenges in motion coordination, because influence and information propagate through local interaction networks, rather than global channels. A neuro-evolutionary learning-based control method is presented in which a subset of a swarm is trained to influence motion behaviors. The leadership control strategy is applied to a rally task with varying swarm sizes and leadership percentages. Increasing the leader representation improved task performance, but the performance increase was negligible for a leader-swarm ratio of 16% or greater. The learned behaviors were different with high and low leader percentages. The leaders moved quickly when the swarm had a higher percentage of leaders and slowly when the percentage was small.
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Committee Member
Academic Affiliation
Rights Statement
Peer Reviewed



This work has no parents.

In Collection: