You are here

Application of Artificial Intelligence/ Machine Learning/Deep Learning to the Test and Evaluation of Command, Control, Communication and Intelligence (C3I) systems

Description:

TECHNOLOGY AREA(S): Info Systems, 

OBJECTIVE: Design and create a tool that automates and optimizes planning and test execution of Artificial Intelligence/ Machine Learning/Deep Learning enabled Command, Control, Communication and Intelligence (C3I) network and systems. 

DESCRIPTION: Recent advances in the areas of artificial intelligence/ machine learning/deep learning (AI/ML/DL) have provided the opportunity to automate time-consuming manual processes in C3I network Test and Evaluations (T&E). Specifically, the incorporation of such things as neural networks and training processes has elevated AI/ML/DL as key innovation areas to improve test planning and reduce validation/verification of test infrastructure prior to test execution. This effort would mature these AI/ML/DL concepts to develop a planning/execution tool to generate a location specific network (system under test) architecture recommendations (based upon number of nodes, topography, Radio Frequency propagation, number of communication hops, etc.). Node locations will ensure that testing of the performance edges are verified (e.g. number of communications hops is selectable 1 – N drives node location). Additionally, this tool will recommend an optimal data collection infrastructure, perform the data collection, analysis and presentation. Real-time performance monitoring, analysis and feedback during test operations will enable improvements to the data collection and test processes. The collected dataset(s) will provide inputs to the AI/ML/DL tool enabling learning and improvement of tool functionality over time. The tool will also provide root-cause analysis for anomalies identified during test, improving use case implementation and execution. The system would follow a Modular, Open Systems Approach (MOSA) to allow T&E of a variety of Army systems. The MOSA approach would also provide extensible AI/DL/ML functions to identify and expand upon critical characteristics of the C3I systems. This tool will enable non-deterministic approach to C3I T&E. This tool must also provide C3I T&E community results expressed in statistical terms for comparison to historical C3I systems performance. Expected uses of the tool outputs are: Descriptive analysis - data aggregation/mining provides insight into what has occurred Predictive analysis – statistical models/forecasting to understand what may occur Prescriptive analysis – optimization/simulation provides course of action recommendation Note: Model validation, learnability, algorithm efficiency and empathy are among the key features of this tool. 

PHASE I: Develop a tool design that includes artificial intelligence (AI) machine learning (ML), and deep learning (DL) algorithms and concepts, hardware and software specifications, and protocol operation (both internal and external). 

PHASE II: Develop and demonstrate a prototype artificial intelligence (AI) machine learning (ML), and deep learning (DL) tool in a realistic environment. Conduct testing to prove feasibility over extended operating conditions. 

PHASE III: End-state of this effort is transition of this tool to military Command, Control, Communication and Intelligence (C3I) programs of record and the commercial market. This tool is envisioned to optimize incorporation and application of artificial intelligence (AI) machine learning (ML), and deep learning (DL) capabilities in the decision-making process. This will provide verification and validation of AI/ML/DL algorithms and confidence in the increasing independent autonomy of Command, Control, Communication and Intelligence (C3I) systems. DUAL-USE APPLICATIONS: This system could be used in a broad range of military and civilian Command, Control, Communication and Intelligence (C3I) applications where equipment and systems must be optimally located - for example, in military exercises/operations or in enhancing critical industrial/commercial operations in congested/convoluted topographical environments. 

REFERENCES: 

1: "SUMMARY OF THE 2018 DEPARTMENT OF DEFENSE ARTIFICIAL INTELLIGENCE STRATEGY: Harnessing AI to Advance Our Security and Prosperity". February 12, 2019. Online at https://media.defense.gov/2019/Feb/12/2002088963/-1/-1/1/SUMMARY-OF-DOD-AI-STRATEGY.PDF

KEYWORDS: Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), Test And Evaluation (T&E), Command, Control, Communication And Intelligence (C3I) 

US Flag An Official Website of the United States Government