Adaptive Control Architecture for Unmanned Surface Vessels
Aurora Flight Sciences, a Boeing Company
Manassas, VA
703-369-3633
www.aurora.aero
Aurora Flight Sciences, a Boeing company, is developing and testing machine learning-based introspection technologies aimed to enable physical systems, in this case ships, to adapt their control laws as they encounter uncertainties or unexpected events. The work is part of a seedling program titled “Fast Adaptation and Learning for Control Online” (FALCON) to support the Defense Advanced Research Projects Agency’s (DARPA) Learning Introspective Control (LINC) program.
Aurora’s FALCON solution is a platform-agnostic, computationally lightweight online learning and adaptive control architecture that delivers fast convergence for changing nonlinear, nonparametric dynamics in cyber-physical systems. It can detect destabilization quickly and reconstitute control online for safe and continued operation.
In response to changing circumstances, FALCON recalculates safe reachable operating limits in real time while providing guidance and situational awareness to the operator, whether that operator is human or an autonomous controller.
This spring, Aurora implemented their proof-of-concept control architecture on 1.5-meter-long unmanned surface vessels (USV) and began testing in the Charles River in Cambridge, Massachusetts. The USV compensates for the currents and waves, which are large relative to the size of the vehicle. The first program demonstration examines the USV’s ability to reconstitute control after a significant reduction in control effectiveness of one thruster, similar to the disturbance induced by rudder lock in larger vessels.
The program team also includes the Massachusetts Institute of Technology (MIT) Aerospace Controls Laboratory led by Prof. Jonathan How, and the MIT Marine Autonomy Laboratory (PavLab) led by Dr. Michael Benjamin. The MIT PavLab, located in the MIT Sailing Pavilion on the Charles River, is providing the USVs, which serve as a rapidly adaptable test platform for FALCON.
Work on the FALCON program is ongoing, with future demonstrations planned to investigate additional unpredictable disturbances, such as large wind loading and fuel slosh effects.
Visit Here
Top Stories
INSIDERManufacturing & Prototyping
How Airbus is Using w-DED to 3D Print Larger Titanium Airplane Parts
INSIDERManned Systems
FAA to Replace Aging Network of Ground-Based Radars
NewsTransportation
CES 2026: Bosch is Ready to Bring AI to Your (Likely ICE-powered) Vehicle
NewsSoftware
Accelerating Down the Road to Autonomy
EditorialDesign
DarkSky One Wants to Make the World a Darker Place
INSIDERMaterials
Can This Self-Healing Composite Make Airplane and Spacecraft Components Last...
Webcasts
Defense
How Sift's Unified Observability Platform Accelerates Drone Innovation
Automotive
E/E Architecture Redefined: Building Smarter, Safer, and Scalable...
Power
Hydrogen Engines Are Heating Up for Heavy Duty
Electronics & Computers
Advantages of Smart Power Distribution Unit Design for Automotive...
Unmanned Systems
Quiet, Please: NVH Improvement Opportunities in the Early Design...



