Operator Challenge Response

Today, the volume of raw data being collected is growing at an exponential rate so much so that humans cannot process and analyze the data in a quick, efficient way for operators to use. Right now, the process of collecting data to creating usable data is happening at an extreme delay as data is being collected, then sent to a headquarters office where it is then analyzed and then finally sent back to operators. We plan to devise a plug-in for the ATAK system where data is collected and analyzed in real time so that the delay in collecting data and using data is virtually eliminated. This will allow operators to be more informed about the decisions they are making and will allow them to make decisions in a timelier manner as they are no longer waiting for data to be processed and analyzed—that happens on their devices as soon as the data is collected.

Today, there are more and more sensors on the battlefield. Some are in the air, some are in orbit, some are worn by soldiers, some are positioned on the ground, and so on. As this trend continues there will soon be an overwhelming amount of data created by all these sensors, and it will become impossible for humans to effectively absorb it all and take the right action. Currently much of this kind of data is sent back to a headquarters office to be processed by people and software, and then the resulting information and recommendations are disseminated back out into the field to the people who can make a decision and act. This causes a significant delay and does not scale.

The goal of this project is to turn data from distributed sensors into usable information, send it to the right people, and do so scalably as the number of sensors and the volume of raw data grows exponentially. The ideal end state of the project is to create a plug in for the ATAK system where data sources can be inputted and analyzed right there, real-time, on the device. To accomplish this end-state, a large portion of the project will be spent researching different data sources, understanding how they are stored and how to merge the different data sources into a single, usable dataset. Once the data is in a usable format, we can talk to operators to see what type of a usable interface they would like to see employed, and we can build something that uses the dataset to create a usable interface that operators can use on the edge in real time.

As stated in the problem statement, there are many different types of sensors on the battlefield, so an unknown we have right now is determining which data is the most common and where to focus our research efforts as we could research different types of data forever, but ultimately, to get the project started, we are going to have to pick a couple data sources and use those. We want the end state of this project to be of use to operators, so we would like to know what data sources to focus on and which data sources are most commonly seen/used. Another challenge we might have is getting access to “real” data as much of the data we are going to be looking at is probably classified at some level. In addition, if we do access the classified data, we are going to have to devise a way to keep the different levels of data separate as each data source is probably a different classification level.