Summary
Control design currently aims to model the range of operating environments that are anticipated at design time. Plans can fail, however, when physical attacks, unforeseen conditions, or unanticipated use places the system outside the design envelope.
Custom tailored aftermarket remedies are not commonly available and require a skilled technician to install, and modifications to existing systems through procurement channels can take months or years. The Department of Defense (DoD) systems are particularly long-lived, so ongoing adaptation would permit continual modification as missions and theaters change, providing a strategic advantage over an adversary.
The Learning Introspective Control (LINC) program aims to develop machine learning-based introspection technologies that enable physical systems, with specific interest in ground vehicles, ships, drone swarms, and robotic systems, to respond to events not predicted at design time. LINC technologies endeavors to update control laws as required in real time while providing guidance and situational awareness to the operator, whether that operator is human or an autonomous controller.
The current approach to handling platform damage or modification places the burden of recovery and control on the operator.
LINC seeks to develop machine introspection and learning technologies that continually compare the real-time behavior of a military platform – as measured by on-board sensors – with a learned model of the platform, determine whether the observed behavior differs from that model in ways that might compromise stability and control, and implement an updated control law when required and effectively communicate those updates to the operator.
This allows the operator to maintain effective control and trust in the platform.