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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 06, 2019
Accession Number
AD1081002

Entities

People

  • Kyle D. Demedeiros
  • Thomas Wettergren

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Automata Theory
  • Autonomous Systems
  • Cognitive Systems Engineering
  • Computational Science
  • Control Systems
  • Cooperative Control
  • Data Mining
  • Evolutionary Algorithms
  • Information Systems
  • Motion Planning
  • Multiagent Systems
  • Particle Swarm Optimization
  • Simulations
  • Swarm Intelligence
  • Unmanned Underwater Vehicles

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Operations Research
  • Robotics and Automation.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Machine Learning Algorithms
  • Autonomy
  • Autonomy - Autonomous System Control