|Acquisition Program: || Objective: ||Develop an adaptive desktop training device with underlying learning management system (LMS) architecture to train ISR imagery analysis for better decision making by warfighters.
|| Description: ||ISR imagery data has become paramount to military success in current operations in Iraq and Afghanistan. As more and more ISR platforms are being pushed into the operational environment it is becoming increasingly important to provide training that educates users on what they should expect to see from this imagery in the context that these assets will be deployed. Cultural, environmental, behavioral, economic, religious, and other factors play a significant role in the types of imagery users will observe in the AOR. Being aware of the context within a particular situation provides necessary information to determine if a potential target is for example: just filling in a hole as part of his/her job or covering up an IED. Additionally, understanding current and evolving tactics of insurgent operations are also an important factor in recognizing what is truly happening or about to happen in a situation and can mean the difference between life or death of troops and innocent civilians. A desktop training system is needed to train these users (Distributed Common Ground Station (DCGS) imagery analysts, Remotely Piloted Aircraft (RPA) crew members, ground troops who utilize ROVER feeds, etc) on how to interpret the actions they are seeing on the ground in order understand the significance of what is occurring and make better decisions about what actions to take. This system should provide an individually adaptive imagery training capability based on an underlying LMS architecture to bring users to a high degree of skill level to recognize events and situations on the ground using simulated Electro-Optical, Infrared, and Full Motion Video imagery. Furthermore, this system should have the ability to ingest new insurgent TTP information and other important factors (cultural, environmental, behavioral, economic, religious, etc) to adapt intelligent agent models and scenarios presented to users so that training can remain up-to-date with current operations. Finally, this system, though first developed as a standalone desktop environment, should have the capability for expansions into more complex operational simulation environments.
|| ||PHASE I: This phase will identify content for the development effort based on an assessment of operational needs. In addition, Phase I will develop a proof-of-concept desktop exemplar of the training and rehearsal concept to be fully developed in the Phase II effort.
|| ||PHASE II: Will build upon Phase I to fully develop, refine, test and evaluate the components of the system to include the underlying LMS, adaptive training course content, intelligent agent technologies and modular design for integration with an operational simulation environment. The final prototype will demonstrate these capabilities as well as the ability to ingest new or update material.
|| ||PHASE III DUAL-USE COMMERCIALIZATION:
Military Application: Imagery data for ISR is a major component of operations across all services. The developed technology would be beneficial for imagery analysts and warfighters who utilize IMINT sensors in DCGS, RPA, and ground operations.
Commercial Application: This training system would provide a beneficial tool for US Customs and Border Protection, homeland security, and natural disaster relief personnel who perform analysis on imagery data for decision making.
|| References: ||
(1) DeGregorio, E.A., Messier, R.H., Shelton, J. and Castro, K. (2006). “Adapting Commercial Video Game Technology to Military Simulation Applications,” Australian SimTecT Conference.
(2) Carolan, T., Schurig, I. and Bennett, W. Jr. (2006). “Competency-based Training Adapting to Warfighter Needs,” (Technical Report No. AFRL-HE-AZ-TR-2006-0014). Mesa, AZ: Air Force Research Laboratory, Warfighter Readiness Research Division.
(3) Flynn, M., Pottinger, M., and Batchelor, P, “Fixing Intel: A Blueprint for Making Intelligence Relevant in Afghanistan.” Center for a New American Security. January 2010. http://www.cnas.org/node/3924.
|Keywords: ||Imagery Analysis, Personalized Learning, Adaptive Training, Learning Management System, Desktop Training, Signal Detection|