SBIR-STTR Award

Development of a Concept for Swarmed mini-UAVs for Automatic Target Recognition
Award last edited on: 10/30/2018

Sponsored Program
STTR
Awarding Agency
DOD : Navy
Total Award Amount
$1,096,630
Award Phase
2
Solicitation Topic Code
N04-T005
Principal Investigator
John E Moody

Company Information

Augusta Systems Inc

3606 Collins Ferry Road Suite 202
Morgantown, WV 26505
   (304) 599-3200
   info@augustasystems.com
   www.augustasystems.com

Research Institution

West Virginia University

Phase I

Contract Number: N00014-04-M-0288
Start Date: 7/1/2004    Completed: 4/30/2005
Phase I year
2004
Phase I Amount
$99,149
Unmanned Aerial Vehicles (UAVs) have served to enhance and augment the surveillance and reconnaissance abilities of the military of the United States of America. In developing the next generation of UAVs, the application of novel methodologies to UAV control will become more important as the number and mission criticality of deployed UAVs continues to increase. One of these novel approaches, long considered to possess some ideal characteristics, is the idea of reactive agents and the associated emergent behavior. This technique possesses the potential to provide minimal user intervention, a high level of robustness, and largely autonomous operation provided that suitable algorithms and techniques can be developed. The proposed work should provide the basic mathematical framework for reactive agent based Automatic Target Recognition in which these reactive agents could be simulated and, based on this simulation, optimization strategies for simple emergent behaviors developed along with mission based parameters estimated. The proposed approach models sensing behavior from an information theory perspective and then utilizes this in generating mission based system parameters followed by optimization of those parameters. If successful, this should allow for the implementation of reactive agent based techniques for UAV control embodying the benefits as appropriate.

Benefit:
The proposed research should provide a sufficiently accurate simulation of reactive agent based automatic target recognition on unmanned aerial vehicles to allow evaluation of both the benefits and feasibility of potential future introduction of this technique into actual UAVs. Provided the research results in the eventual introduction of this technology into unmanned vehicles, this technique should provide a high level of flexibility and robustness for the selected missions. Augusta Systems would focus its commercialization activities on private and public sector clients in three key areas defense (including land and water applications), energy and environmental (including applications for geologic sequestration monitoring, watershed characterization, pipeline monitoring, etc.), and transportation (including applications for highway traffic monitoring and Coast Guard applications).

Keywords:
mission based parameters, mission based parameters, SWARM, cooperative automatic target recognition, Reactive Agents, Emergent Behavior

Phase II

Contract Number: N68335-05-C-0303
Start Date: 8/17/2005    Completed: 8/16/2007
Phase II year
2005
Phase II Amount
$997,481
The objective of this project is to develop algorithms controlling the high level flight pattern of Unmanned Aerial Vehicles (UAVs) utilizing swarming technology in a manner to maximize Automatic Target Recognition (ATR) performance for a selected algorithm through cooperative search operations involving a larger number of inexpensive UAVs. Based upon the success and results of the Phase I work, this will be accomplished through the selection of a suitable ATR algorithm and sensor, modeling of the ATR algorithm and sensor performance, development of reactive agents to support appropriate, cooperative, swarming behaviors, development and application of optimization techniques for the reactive agent parameters, and ground truth verification of overall system performance.

Benefit:
The proposed research should provide a sufficiently comprehensive test of cooperative ATR based on swarming behavior controlled flight patterns of UAVs through the use of reactive agents and pheromone maps to allow evaluation of both the benefits and feasibility of potential future introduction of this technique into actual UAVs for operational implementation. Applications of this technology could be many and varied with potential for utilization in any Intelligence, Surveillance, and Reconnaissance (ISR) operation along with any civilian/commercial application that could benefit from automated recognition of desired features both simplifying the use of and improving the effectiveness of unmanned vehicles.

Keywords:
unmanned aerial vehicle, Autonomy, SWARM, reactive agent, pheromone, Optimization, Automatic Target Recognition