This investigation uses a self-organization (SO) approach to enable cooperative search and destruction of retaliating targets with swarms of homogeneous and heterogeneous unmanned aerial vehicles (UAVs). To facilitate specific system design, a facilitating SO algebraic framework is created that emphasizes scalability, robustness, and exibility. This framework is then used to implement a UAV behavior architecture relying upon rules governing formation and target interaction. Sets of applicable behaviors are created by weighted summation of the rules where different weights act as distinct behavior archetypes. Appropriate behavior archetypes are based upon sense information distilled from the environment and a simple perceptron mapping. Successful behaviors are evolved within this architecture using a genetic algorithm. This approach tests a swarm of UAVs, when sensor and attack abilities are both homogeneous and heterogeneous, against targets with superior engagement range. Resulting behaviors are highly cooperative, generally scaleable, and robust.
Evolving Self-Organized Behavior for Homogeneous and Heterogeneous UAV or UCAV Swarms
2006
238 pages
Report
Keine Angabe
Englisch
Aircraft , Reactor Engineering & Nuclear Power Plants , Bionics & Artificial Intelligence , Remotely piloted vehicles , Self organizing systems , Homogeneous reactors , Heterogeneous reactors , Test and evaluation , Algorithms , Skills , Interactions , Attack , Genetics , Targets , Searching , Behavior , Architecture , Swarms , Unmanned aerial vehicles , Uav(Unmanned aerial vehicles)
Online Contents | 1998
British Library Conference Proceedings | 2001
|British Library Conference Proceedings | 2007
|Online Contents | 1997
UCAV: REDESIGNING ITS MISSION - Darpa to oversee USAF-Navy UCAV development
Online Contents | 2003