US Air Force Seeks AI to Auto-Detect Mid-Air Refueling Errors via SBIR Solicitation
The US Air Force has issued a Small Business Innovation Research (SBIR) solicitation for AI software that uses computer vision to analyze KC-46 tanker camera footage and automatically detect operational deviations like speed and alignment errors, aiming to reduce human assessment inconsistencies. Applications are due by November 25, 2026.
According to TechRadar, the US Air Force is exploring the use of artificial intelligence to identify mistakes during aerial refueling operations and improve how crews receive performance feedback. The project falls under the Small Business Innovation Research (SBIR) program, which invites companies to develop technological solutions addressing specific military requirements. Interested developers have until November 25, 2026, to submit applications outlining how their proposed systems could satisfy the service's operational and training requirements.
The proposed system would analyze footage captured by cameras on the KC-46 Pegasus, a refueling aircraft equipped with cameras supporting remotely controlled fuel transfer operations. Its remote vision equipment allows boom operators to guide the refueling apparatus using camera feeds and 3D displays instead of direct observation. However, the aircraft's existing viewing technology has experienced persistent technical difficulties.
Using computer vision and machine learning, the technology would examine aircraft movements and determine whether crews maintained appropriate separation and alignment. It would also monitor the refueling boom, comparing its movements against aircraft trajectories to identify potentially dangerous deviations during fuel delivery. Measurements would include aircraft speed, relative positioning, approach velocity, and alignment, allowing instructors to examine specific maneuvers rather than relying on general observations.
Currently, assessments depend substantially on instructor observations, crew evaluations, and manually examining recorded footage, according to the military's research solicitation. These methods can produce inconsistent judgments, particularly when instructors interpret the same maneuver differently or overlook brief errors during complicated operations. Therefore, the software’s assessment will include graphical overlays, color-coded performance maps, and chronological displays identifying significant events during individual refueling exercises.