Self organized UAV swarm planning optimization for search and destroy using SWARMFARE simulation

Authors:
Dustin J. Nowak;Ian Price;Gary B. Lamont
Affiliations:
Air Force Institute of Technology, WPAFB, Dayton, OH;Air Force Institute of Technology, WPAFB, Dayton, OH;Air Force Institute of Technology, WPAFB, Dayton, OH
Venue:
Proceedings of the 39th conference on Winter simulation: 40 years! The best is yet to come
Year:
2007

Citing 6
Cited 2

Flocks, herds and schools: A distributed behavioral model

SIGGRAPH '87 Proceedings of the 14th annual conference on Computer graphics and interactive techniques
Three-layer architectures

Artificial intelligence and mobile robots
Swarm intelligence: from natural to artificial systems

Swarm intelligence: from natural to artificial systems
Self-Organization in Biological Systems

Self-Organization in Biological Systems
Image Processing in a Tree of Peano Coded Images

CAMP '97 Proceedings of the 1997 Computer Architectures for Machine Perception (CAMP '97)
GA directed self-organized search and attack UAV swarms

Proceedings of the 38th conference on Winter simulation

Emergent architecture in self organized swarm systems for military applications

Proceedings of the 10th annual conference companion on Genetic and evolutionary computation
A hybrid approach based on multi-agent geosimulation and reinforcement learning to solve a UAV patrolling problem

Proceedings of the 40th Conference on Winter Simulation

Quantified Score

Hi-index	0.01

Visualization

Abstract

As military interest continues to grow for Unmanned Aerial Vehicle (UAV) capabilities, the Air Force is exploring UAV autonomous control, mission planning and optimization techniques. The SWARMFARE simulation system allows for Evolutionary Algorithm computations of swarm based UAV Self Organization (SO). Through SWARMFARE, the capability exists to evaluate guiding behaviors that allow autonomous control via independent agent interaction with its environment. Current results show that through an implementation of ten basic rules the swarm forms and moves about a space with reasonable success. The next step is to focus on optimization of the formation, traversal of the search space and attack. In this paper we cover the capabilities, initial research results, and way ahead for this simulation. Overall the SWARMFARE tool has established a sandbox in which it is possible to optimize these and build new behaviors.