Four uncrewed ground vehicles hunted for enemy targets without GPS during a Defense Advanced Research Projects Agency exercise last month at Fort Knox, Kentucky.
The demonstration formed part of the Robotic Autonomy in Complex Environments with Resiliency program. The Pentagon research arm examined how the ground robots could quickly drive, map out terrain, and gather information independently in contested environments.
Operations in Contested Environments
The uncrewed ground vehicles conducted surveillance of the surrounding area and independently searched for enemy forces. A human operator supervised the robots from a safe location away from the action.
“We’re moving sensors and effectors forward to the tactical edge while keeping the operator in safety out of harm’s way,” said Jason Gregory, technical advisor at DARPA, told Business Insider. Humans still “maintained control and custody and situational awareness at all times.”
Once launched, the robots went off on their missions. Gregory said that they could work together or independently depending on the scenario.
Operators Supervise Uncrewed Ground Vehicles and Target Engagement
The human operator supervised the uncrewed ground vehicles, assigned them tasks, checked their findings, and decided how best to engage enemy targets. During the Kentucky demonstration, the operator used satellite imagery to task the robots.
One uncrewed ground vehicle stopped in place after spotting a potential target represented by a closed box holding a drone inside. The human operator then decided to launch a simulated target rocket.
A key part of the testing program involved ensuring the robots could perform tasks without GPS. The vehicles built their maps as they moved.
DARPA Develops Software for Vehicles to Operate Without GPS
The military needs to prepare to fight through contested environments where GPS is unavailable. DARPA developed new software so that ground vehicles could use only their onboard sensors to make decisions to move as fast as possible.
Gregory said that the software was tested on four-wheel, all-terrain uncrewed ground vehicles as well as tracked vehicles to ensure deployment across different hardware. The work relied on observations from Russia’s war in Ukraine regarding the role of ground robots and operator deployment.
Autonomous ground vehicles face distinct challenges depending on the terrain, environment, and climate. Desert operations require moving through sand and rocks while extreme heat strains batteries and communications systems.
Swamplands, forests, muddy fields, and snow also complicate operations. The Robotic Autonomy in Complex Environments with Resiliency program involved five years of research to understand the scientific and technical challenges of autonomy, artificial intelligence algorithms, and ground mobility.
