Peraton Labs has won a Defense Advanced Research Projects Agency contract to develop real-time adaptive control technologies.
These machine learning-based technologies would allow ground vehicles, ships, drone swarms, robotic systems and other long-lived physical systems to adapt to unexpected events.
Considering military systems must operate over a wide range of environments, over long periods of time and in unexpected conditions, the burden is on the human or autonomous operator to maintain safe control of systems operating in unusual conditions (like damage, environmental extremes and other unanticipated situations).
Under DARPA’s Learning Introspective Control program, the Peraton Labs team will design the capability to update the system control algorithm in real-time and guide the system’s human operator or autonomous controller.
“Peraton Labs will research, design, implement, and test a solution called Adaptive Control with AI (ACAI) to assist operators, human or machine, in maintaining control of systems in adverse situations,” said Petros Mouchtaris, president of Peraton Labs.
Adaptive Control with AI uses data from on-board sensors and applies a combination of machine learning, constrained optimization and a robust optimal control framework to pick optimal controls based on current system state and environmental conditions. This intelligent control algorithm coordinates between performance and safety to provide high-performance controls while maintaining safety and stability.
“We are excited to develop and deliver real-time adaptive control technology that provides military platforms with substantial advantages in speed, agility, and responsiveness for operations in dynamic theater environments,” Mouchtaris said.