U.S. Army AI Research Strengthens Certainty in Battlefield Decision-Making

U.S. Army researchers have developed a new framework for neural networks’ processing that enables artificial intelligence to better judge objects and potential threats in hostile environments By DA Staff / 27 Aug 2021

Discover Leading Defense Technology Solutions

Discover cutting-edge solutions from leading global suppliers
SUPPLIER SPOTLIGHT
U.S. Army AI Research Strengthens Certainty in Battlefield Decision-Making
Follow DA

Researchers from the U.S. Army Combat Capabilities Development Command (DEVCOM) Army Research Laboratory (ARL) and university partners from the Internet of Battlefield Things Collaborative Research Alliance (IoBT CRA) have developed a method for neural networks to be more confident in their understanding of battlefield environments.

To achieve this, researchers reviewed frameworks to represent uncertainty, categorized sources of uncertainty in military information-networks’ common operating environment, and created solutions to manage uncertainty within systems.

The researchers developed insights from the uncertainty management approaches into a workflow that maximizes effectiveness in accomplishing mission goals despite the presence of uncertainty in data inputs. Through this process, they teach neural networks when to say, “I am sure,” and be right about it.

This improved confidence in neural networks has significant implications for the battlefield, as certainty in Artificial Intelligence (AI) conclusions and behaviors is paramount to ensure ethical and effective decision-making autonomy in combat.

“Modern defense applications, like Aided Target Recognition, increasingly leverage advances in AI to enhance automation of various battlefield functions” said Dr. Maggie Wigness, Army researcher and deputy collaborative alliance manager of the IoBT CRA. 

“A key component of improving automation is to improve machine confidence in understanding its environment, so that the machine can exercise ‘good judgment.’”

“Older data fusion technologies like a green circular radar screen, resembling those often shown in older movies, would show targets as dots bleeping on the screen,” said Dr. Tarek Abdelzaher, a professor at the University of Illinois and the academic lead of the lab’s IoBT CRA. 

“Operators knew something was approaching because they could see the dots and knew what a dot meant.”

The future operating environment will be filled with smart autonomous devices and platforms that create diverse and complex information signatures.

“AI can pick up the data from these complex information signatures, but the logic that connects those signals to a conclusion such as, ‘this is a target,’ is a lot more complicated and difficult for the machine to indicate to the operator,” he said.

Because of more subtle signals that operators may not understand, it is no longer always clear why a data fusion system thinks an item is, for example, a tank versus a civilian, nor is it always clear how confident the system is in its assessment.

The researchers address this through their paper, On Uncertainty and Robustness in Large-Scale Intelligent Data Fusion Systems, and through solutions developed in the IoBT CRA, which are helping to enable unconstrained command and control of complex, intelligent, pervasive systems-of-systems in modern battlespaces.

“Uncertainty measurement and mitigation for machine learning frameworks is just one example of how the IoBT CRA is providing the resiliency needed to produce a fighting network,” Wigness said. 

“We know that the Army’s multi-domain operational environment is going to be highly dynamic and contested, which is why one of the main research focus areas of the program is on generating scientific contributions that directly address resiliency and robustness.”

This work and additional related work in the IoBT CRA, unlike other mainstream AI research, was specifically designed by the IoBT CRA to work within the battlefield setting, focusing on mitigating uncertainty in hostile environments under significant resource constraints and communication bottlenecks. 

Hostile environments create unique issues for the Army—platforms are destroyed, communication links are disrupted, sensors get infiltrated to give bad data, yet the Army relies on the AI to continue to work correctly.

The researchers said an AI-enabled common operating environment is expected to withstand failures, circumvent its inability to communicate, and reach accurate conclusions.

Posted by DA Staff Connect & Contact

Latest Articles

RAF Fields Electronic Warfare Drones to Disrupt Enemy Radar

The RAF has deployed StormShroud drones, UK-made uncrewed systems equipped with electronic warfare payloads, to jam enemy radar and protect frontline combat aircraft

May 21, 2025
Latest USV Platform Enables Versatile Operations in Contested Waters

SubSea Craft’s MARS is a rapidly developed, modular uncrewed surface vessel built to enhance maritime operations with scalable, multi-mission capability and autonomous deployment

May 20, 2025
New Line of Kinetic-Capable Unmanned Surface Vessels Introduced

Red Cat Holdings enters the maritime autonomy market with a new line of combat-proven USVs, expanding its multi-domain unmanned systems for naval operations

May 20, 2025
Rugged Military Computing Solutions Being Showcased at AFCEA 2025

Getac's latest rugged military computing technologies will be presented at AFCEA 2025, highlighting the company's technical solutions across military use-cases

May 19, 2025
Triad RF: Advancing Radio Testing with T006 & ARTS Automation

Triad RF’s T006 Rack and ARTS automate high-power radio testing, delivering faster, more consistent validation with improved isolation and performance validated through flight testing for mission-critical applications

May 19, 2025
Swedish Army Advances C2 Digitization with MilDef Technology

MilDef has been commissioned by FMV to deliver IT equipment that supports the Swedish Army’s digitization and enhanced command-and-control (C2) capabilities

May 19, 2025

Featured Content

New Line of Kinetic-Capable Unmanned Surface Vessels Introduced

Red Cat Holdings enters the maritime autonomy market with a new line of combat-proven USVs, expanding its multi-domain unmanned systems for naval operations

May 20, 2025
Next-Gen Group 2 UAS Enters Production with Extended Endurance & Upgrades

Aurora Flight Sciences upgrades the SKIRON-X Group 2 UAS with greater versatility and tactical mission endurance, as well as announcing the hydrogen-powered SKIRON-XLE variant

May 13, 2025
Discover ANELLO’s SiPhOG™ for GNSS-Denied Navigation at XPO25

CEO of ANELLO Photonics, Dr. Mario Paniccia, will present at Xponential 2025 on the company's SiPhOG-based inertial navigation technology in GPS-denied and GNSS-contested environments.

May 09, 2025
Advancing Defense Capability Through Strategic Collaboration Defense Advancement works with major OEMs to foster collaboration and increase engagement with SMEs, to accelerate innovation and drive defense capabilities forward.