Army Takes on Wicked Problems With the Internet of Battlefield Things

Soldiers with the Fort Meade, Md.-based 780th Military Intelligence Brigade conduct cyberspace operations during a training rotation for the 2nd Stryker Brigade Combat Team, 2nd Infantry Division, at the National Training Center at Fort Irwin, Calif., on Jan. 24. Several cyber organizations took part in the rotation as part of an pilot program to designed to help the Army develop how it will build and employ cyber in its tactical formations. (Photo: U.S. Army)

The Army’s work on the Internet of Battlefield Things (IoBT) is more than just a way to carve out a catchy name for the proliferation of smartphones, tablets, wearable devices, cameras and embedded devices that take the field with military forces. It also underscores the most important element of having those connected devices–the data collection and automated analytics capabilities required to make good use of the information they provide.

The explosion of things connected to the Internet in everyday life and the industrial sectors has naturally led to subsets within the IoT. There are internets of Aircraft Things, Space Things, Underwater Things, and Medical Things. But like projects in other areas, the Army Research Laboratory’s $25 million IoBT project, is focused mostly on back-end processing. Being led by the University of Illinois at Urbana-Champaign, the project is a collaborative research alliance (CRA) looking to go beyond machines following orders to where they work almost as partners with soldiers in the field.

“We don’t want to micromanage the machines and things doing the work,” Tarek Abdelzaher, who’s leading the work at the University of Illinois, told the Chicago Tribune. “I want to tell [the machines] my intent, and then I want them to have the sort of intelligence, autonomy, and initiative to figure out how to meet my intent.”

That involves incorporating predictive intelligence, making use of recent advancements in artificial intelligence, machine learning, and neural networks into the process. Walid Saad, an assistant professor at Virginia Tech who is co-managing an Army grant awarded to the school to study the placement of objects in the IoBT, noted that the project “will marry notions from data analytics, information theory, game theory, and distributed learning.”

The IoBT program is part of the Army’s long-range plans for keeping up with the technological advances, and in some cases the advantages of potential adversaries, reflected in the Army’s operational outline for 2020-2040, “Winning in a Complex World.” The Department of Defense has admitted that in two decades of concentrating on comparatively low-tech wars in Iraq and Afghanistan, it has largely ignored development in techniques, such as electronic warfare (EW), that would come into play in other more contested environments. Russia, for instance, has demonstrated advanced skill at EW and cyber warfare in Ukraine. China has demonstrated similar propensities in the Pacific.

DOD wants to get in front of similar developments on the battlefield. “The Army must tackle wicked problems wherein objectives and constraints evolve in unpredictable ways,” the U.S. Army Research Laboratory said in its original solicitation for the IoBT project. The mix of disparate sensors and other sources, the scale of their deployment and the variety of their functions all contribute to the complexity, as does the speed at which conditions can change. “Events now unfold in internet time,” the notice said.

To keep pace, the Army’s systems are going to need a new level of sophistication. “In this context, future IoBTs will be significantly more complex than today’s networked systems, and novel mathematical approaches and techniques will be needed to represent them, reason about them, understand their behaviors, and to provide predictive analytics in diverse and dynamic environments,” ARL said.

ARL is focusing its research in four primary areas: discovery, composition, and adaptation of goal-driven heterogeneous IoBTs: autonomic IoBTs to enable intelligent services; and distributed asynchronous processing and analytics of things. Cyber-physical security also has included a cross-cutting factor inherent to each area.

The $25 million in grants is intended to cover the first five years of what could be a 10-year project. In addition to Illinois (which is getting $6 million of the money), other research partners are Carnegie Mellon University; University of California, Berkeley; University of California, Los Angeles; University of Massachusetts; University of Southern California; and SRI International.

Recent