Peraton has demonstrated an artificial intelligence control system that keeps robotic platforms operating safely in extreme conditions, including when damaged.
The tech, called Adaptive Control with AI (ACAI), helps machines adjust to real-time stress like mechanical failure, harsh terrain, or rough seas, while still giving human operators guidance.
It draws on computer vision, machine learning, physics modeling, and optimization tools to recognize system limits and adapt behavior without compromising safety.
Backed by the Defense Advanced Research Projects Agency (DARPA), ACAI is part of a wider push to make autonomous systems more resilient in contested or unpredictable environments
“We are proud to be at the forefront of developing cutting-edge technology that directly supports critical missions,” said Todd Borkey, Chief Technology Officer at Peraton.
“By advancing autonomous systems, we are helping government agencies seamlessly integrate AI and machine learning into their operations, architecture, and systems.”
Real-World Testing
Peraton has put ACAI through a series of trials, installing the technology on both a damaged US Army ground vehicle and a crane used in ship-to-ship replenishment.
At Sandia National Laboratories, the tech guided the crane on a moving platform to place a missile-shaped payload into a silo as the platform simulated heavy seas.
The AI reduced sway and prevented collisions, reportedly meeting performance metrics even under intensified stress conditions.
In separate tests, ACAI enabled a damaged army ground vehicle to adapt to tread failures, slippery inclines, and high winds, preventing rollovers and unsafe maneuvers.
On rocky terrain, it guided the vehicle directly through the course, while the same vehicle without ACAI went off track.
