C4I and Software Intensive Systems Test
Abstract
The C4T project continued development of AI technologies in multiple areas of “Big Data” rapid analytics of large structured and unstructured datasets in support of F-35 Test and Evaluation (T&E). The C4T project completed the development of near-real time automated multi-band infrared target segmentation technology using state-of-the-art neural network and deep learning based algorithms. The C4T project developed M&S technologies to support real-time assessments of complex environments such as undersea environments. These technologies provided an acoustic propagation model, both narrow and broad band, of sufficient fidelity to test torpedo performance in various maritime tactical environments. The model included a real-time simulation/emulation system for testing torpedo sonar systems in multiple bathometry, biological and threat environments. The C4T project developed technologies to provide a reliable, fast, and cost-effective approach that enables direct injection Live Virtual Constructive (LVC) testing of next generation weapon systems. These technologies will enable live assets to sense and respond to the latest threat stimulus without regard to whether the stimulus is real or synthetic. The C4T project developed a configuration optimization of test support networks. Technologies included planning expeditionary tests, managing bandwidth and spectrum contention with a networked system under test, managing battery consumption, providing Real-Time Casualty Assessment (RTCA) data during live tests and providing continuous re-planning capability. These technologies will address deficiencies in Army Operational Test (OT) for network-enabled technologies. The C4T project initiated the development of deep neutral network technologies for real-time Automated Target Recognition (ATR) using real and synthetic data. These technologies are being developed to support Unmanned Aerial Vehicle (UAV) target recognition.
Document Details
- Document Type
- Accomplishment
- Publication Date
- Oct 01, 2020
- Source ID
- 0a8b99bdb571b42dde2be106458a7d57