You are here

Dynamic, Risk-Based, Situational Awareness and Response

Description:

TECHNOLOGY AREA(S): Info Systems 

OBJECTIVE: Develop a system for integrated threat detection, classification, and situational awareness considering data associated with risk relative to assets, providing capability for fixed and mobile asset security leveraging all available information. 

DESCRIPTION: The USAF is tasked with securing both fixed-site facilities and mobile assets against a multiplicity of potential threats, including conventional weapons (rockets, artillery, mortars (RAM)), and shorter-range weapons (small arms, rocket-propelled grenades (RPGs)). Enemy use of vehicle-borne explosive devices and other improvised weapons are also of great concern. An emerging threat to site security is the rapid proliferation of low-cost UAS (“drones”). Weaponized drones, particularly operating in coordinated swarms, pose an immediate risk. Their low cost and commercial availability have enabled an increasingly deadly role in theater. Other threats include cyber-directed attacks against such infrastructure as the power grid or water supply. In some location, biological weapons, severe weather, wildfires, civil unrest, and many others threats can also pose significant operational hazards to secured facilities. Commanders are tasked with continually assessing these threats versus the risk associated with particular defended assets. This creates a feedback loop: assess the threat, evaluate the risk relative to affected asset(s), command the optimal response. Decision makers develop risk metrics—a product of the asset’s determined operational value, potential threats to that asset, and an assessment of its vulnerability. In reality, risk assessments continuously change, especially in light of detection and classification of threats constituting hostile intent. Presently, the nature of gathering and synthesizing data from a variety of sensor systems, each with its particular operating characteristics, requires operators to understand multiple disparate data streams from various systems. Under attack, interpreting these data streams requires an understanding of the “quirks” and characteristics inherent in each system. Decision making under such circumstances, especially if infused with incorrect and/or otherwise inaccurate information, may be suboptimal and thus prone to error. This project seeks to improve command responses by considering event detection data from multiple networks, paired with historical data, to update asset risk metrics in real time. Machine learning algorithms can be developed to aggregate these data and weigh relevant factors. In graphical terms, this can be visualized as a situational awareness display on which threat events are continually overlaid with an updating assessment of asset risk. This information can serve as an “automated playbook” on how best to respond to certain threats, and provide valuable insight to commanders and first responders faced with dispatching countermeasures in highly dynamic, and sometimes uncertain, tactical situations. This will enable faster response to attacks, and allow countermeasures to be directed more effectively. Overall, the payoff is better use of available USAF resources, and decreased logistical burden. This topic envisions utilization of emerging technologies in the realm of machine learning. Such systems are capable of improving their predictive accuracy (assessment of “truth”) as they are provided with more and more data. In the past few years, computational hardware required to utilize these tools has advanced to the point where such systems can be deployed in tactical command centers with minimal additional facilities requirements. Some of these systems utilize graphics processors (GPUs), which have been in wide circulation for about a decade. Additionally, new types of processor architectures are being developed specifically for deep learning frameworks. Coinciding with the advances in hardware, software tools are available that make development of applications readily accessible. 

PHASE I: It willdemonstrate the feasibility of an automated agent for situational awareness based on real-time determination of threat. Range and domain of threats and type of assets selected for assessment can be negotiated to pare the problem to a manageable level. Existing software systems may be utilized as needed. Final exam is a system simulation demonstrating one or more example scenarios. 

PHASE II: Deliver self-contained system capable of the objectives in a supervised setting integrated at a level suitable for demonstration. Implement algorithms based on historical and live data from three or more diverse sensors, at least one being from a mobile platform. The offeror shall attempt to quantify deviations in observed performance from that predicted in system simulations in Phase I. Deliverables shall include a functional real-time processor to be used in future testing and development. 

PHASE III: The system shall be further developed and improved based on results of earlier phases resulting in integrated tools ready for commercialization and transition to operational programs. This technology will provide a new and improved capability for First Responder centers in DoD, DHS, FAA, etc. 

REFERENCES: 

1. Girão P.S., Postolache O., Pereira J.M.D. (2009) Data Fusion, Decision-Making, and Risk Analysis: Mathematical Tools and Techniques. In: Pavese F., Forbes A. (eds) Data Modeling for Metrology and Testing in Measurement Science. Modeling and Simulation in Science, Engineering and Technology. Birkhäuser Boston.; 2. D.L. Hall and J. Llinas (Editors). Handbook of Multisensor Data Fusion. The Electrical Engineering and Applied Signal Processing Series, CRC Press LLC, Boca Raton (FL), 2001.; 3. Stampouli, D & Vincen, Daniel & Powell, Gavin. (2009). Situation assessment for a centralized intelligence fusion framework for emergency services. 2009 12th International Conference on Information Fusion, FUSION 2009. 179–186.; 4. https://developer.nvidia.com/deep-learning

KEYWORDS: Artificial Intelligence, Big Data, Data Analytics, Data Fusion, Machine Learning, Risk Analysis 

US Flag An Official Website of the United States Government