“Reverse Extrapolation of RF Threats in Electronic Warfare Settings”

Supported by the Agency for Defense Development (2013. 10 ~ 2018. 12)

 

This research focuses on the simulation of the basic components of reverse extrapolation of Radio Frequency (RF) threats.  In electronic warfare environments, the enemy’s electromagnetic radiations can be captured by our system. The radioactive data gathered are analyzed to identify RF threats and used to execute jamming against them.

   To interpret and design our system, we first model RF threats using the following parameters: radio frequency, frequency bandwidth, modulation, etc. The enemy’s radar simulated with a transponder or emitter transmits electronic signals; next, the sensors of the system intercept those signals as radioactive parameters. We will flexibly simulate the communication between the electronic emissions of RF threats and the receivers of our system in various electronic warfare scenarios. We will also utilize the data gathered through our system to reversely model RF threats. The reverse extrapolation process will be carried out by our system to identify and classify threats using profiles compiled through a series of machine learning algorithms including Bayesian classifier, decision tree, clustering techniques, etc. After reversely modeling the RF threat, the Electronic Support Measures (ESM) within the system will provide threat-specific information, which is needed for Electronic Counter-Measures (ECM) such as jamming. To evaluate whether or not the system precisely identifies and classifies terminal or non-terminal threats, we are going to analyze the effectiveness of jamming techniques.

Through a six-year team research, we will develop a comprehensive testing system that rigorously simulates the system in electronic warfare settings, identifying the opponent’s radars, missiles, etc., given the collection of parameters emanating from radioactive sources. We hope to develop a prototype of the system that is both able to reversibly extrapolate and specify the threat and able to integrate Electronic Support Measures (ESM) which are utilized for Electronic Counter-Measures (ECM), i.e., radar jamming.

“Fusion and Processing of Distributed Target Information for Cooperative Surveillance”

Supported by the Agency for Defense Development (2011. 12 ~ 2014. 5)

 

This research focuses on autonomous military robots and their ability to track targets in distributed multi-agent environments. In order to track targets, our agents model the features of threat data perceived through IR sensors. The fusion of input data using a compilation technique is critical for identifying and classifying various kinds of targets. Through the use of coordination framework and decision theory, further, our agents are enabled to make coordinated decisions for target allocation under uncertain situations. These military robots are semi-autonomously operated; that is, their actions are mostly decided by themselves, but sometimes controlled by their commanders. The main goal of our research is to design and develop a simulator that is able to assess the performance of a) the robots’ ability to coordinate the tracking of targets and b) the ability to predict the future positions of those targets. We hope to develop a simulator that can successfully create simulated, uncertain military environments in which military robots can be repeatedly tested for their coordinated decision-making, target allocation, and the continuous tracking of the subsequent movements of targets.

“Prediction of Aircraft Survivability Equipment Suite Operational Effectiveness”

Supported by the Agency for Defense Development (2011. 11 ~ 2012. 10)

 

In this research, we model the method in which aircraft survivability equipment suites successfully choose their countermeasures, and experiment with their autonomous decision-making against threats in various electronic warfare settings. We design and implement our simulators to estimate the operational effectiveness of aircraft survivability equipment suites. We formulate the operational effectiveness into the form of reduction in lethality (RL), and also propose the benchmark of RL in various methods of removing threats. Using our simulator, we hope that the autonomous decision-making of countermeasures and the analysis of survivability using the framework of RL could be available for military operators.

“Home Remote Control Providing Emotional and Visual User Interfaces”

Supported by the Gyeonggi Research Institute (2008. 12 ~ 2009. 11)

 

The goal of this research is to develop an integrated home remote control that makes it easier for people to operate audio/video, home entertainment systems, air conditioner, lighting, and security system through multimodal interfaces, such as voice recognition, pen, and touch. Multimodal input user interfaces provide people with accessibility and an easy-to-use solution. Towards this end, we will investigate the theory of mind, and design user models in typical home environments. We will also profile user preferences based on the user model, and provoke the specific data corresponding to each user from the saved profiles, which automatically enables the remote control to be set to the user’s preferences. Through this project, we are going to develop an integrated home remote control and test it in real home environments.

“Autonomous Threat Detection and Classification”

Supported by the Agency for Defense Development (2007. 12 ~ 2009. 10)

 

This research investigates the autonomous decision-making process of threat detection, classification, and the selection of alternative countermeasures against threats in electronic warfare settings. We introduce a threat model, which represents a specific threat pattern, and a methodology that compiles the threat into a set of rules using machine learning algorithms. This methodology based upon the inductive threat model could be used to classify real-time threats. Further, we calculate the expected utilities of countermeasures which are applicable given a situation, and provide an intelligent command and control agent with the best countermeasure to threats. We will present empirical results that demonstrate the agents capabilities of classifying threats and choosing countermeasures to them in simulated electronic warfare settings.

“Multi-Spectral Threat Data Integration of ASE”

Supported by the Agency for Defense Development (2006. 12 ~ 2008. 6)

 

The ability to dynamically collect and analyze threat data and to accurately report the current battlefield situation is critical in the face of emergent hostile attacks, and enables battlefield helicopters to continually function despite of potential threats. The research is to model threats to battlefield helicopters, which represents a specific threat pattern and a methodology that compiles the threat into a set of rules using machine learning algorithms. This methodology based upon the inductive threat model can be used to detect real-time threats. We will report experimental results that demonstrate the distinctive and predictive patterns of threats in simulated battlefield settings, and show the potential of compilation methods for the successful detection of threat systems.

“Robust Multiagent Decision-Making in Time-Critical Environments”

Supported by the Korea Research Foundation (2002. 12 ~ 2004. 11)

 

The proposed research concentrates on the implementation of flexible decision-making framework that can be used by an autonomous agent in real-time multi-agent settings. Real-time requirements and agent's autonomy are indispensable in the real-world: in most work on real-time systems, the agent's rational behaviors need to be made in a timely fashion. For example, real-time issues in space exploration or battlefield situations are crucial because any overhead or loss of timely response can result in catastrophic failure. Robust autonomy is an essential property for agents that perform unforeseen tasks, which are too hazardous or expensive for humans to perform.

We will design and implement ways in which the autonomous agents can be equipped with flexible decision-making procedures to be practical under time constraints. The goal of our agents is to successfully achieve their complex tasks using approximation techniques while coping with real-time pressures by computing urgency of situation at hand.