Increased UAV Task Assignment Performance Through Parallelized Genetic Algorithms (Preprint)

Abstract

This paper explores the parallelization of a Genetic Algorithm (GA) utilized for task assignment of a team of Unmanned Air Vehicles conducting a Suppression of Enemy Air Defense mission. The GA has been developed and implemented in the Multi-UAV simulation environment for testing. The algorithm has been parallelized with each UAV acting as an independent processor. Two different implementations are explored, one where each UAV independently runs a GA, and the best overall solution is selected at the end, and one where the UAVs exchange information several times during the evolution of generations. The results of these implementations are compared to the original, non-parallelized GA performance.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2006
Accession Number
ADA461621

Entities

People

  • Brian M. Stolarik
  • Lance E. Walp
  • Marjorie A. Darrah
  • William M. Niland

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Space
  • Weapons Technologies

DTIC Thesaurus Topics

  • Air Defense
  • Air Force
  • Air Force Research Laboratories
  • Aircrafts
  • Algorithms
  • Control Systems
  • Cooperative Control
  • Defense Systems
  • Demographic Cohorts
  • Evolutionary Algorithms
  • Genetic Algorithms
  • Linear Programming
  • Simulations
  • Systems Engineering
  • Unmanned Aerial Vehicles
  • Vehicles

Fields of Study

  • Computer science

Readers

  • Aerial Unmanned Vehicle Swarm Micro Periodontal Dentistry.
  • Materials Science and Engineering.
  • Parallel and Distributed Computing.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Machine Learning Algorithms
  • Autonomy
  • Autonomy - UAVs
  • Biotechnology