Control of Multi-Agent Swarms with Cooperative Particle Swarm Optimization
Abstract
This report describes a new approach for the distributed control of multi-agent systems that are performing search in uncertain environments. This approach is called Cooperative Particle Swarm Optimization (Cooperative PSO), and is derived as a modification of Particle Swarm Optimization (PSO) that accounts for uncertainty in the search environment. This research develops a Cooperative PSO technique and illustrates how it can be applied to physical search systems (such as robotic swarms) to successfully control the cooperative behavior of a small swarm of agents. Simulation experiments are performed to show the algorithms effectiveness via comparisons against conventional PSO in scenarios with uncertain search environments.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 06, 2019
- Accession Number
- AD1081002
Entities
People
- Kyle D. Demedeiros
- Thomas Wettergren