Source image : Boeing
The United States Air Force is experimenting with a new approach to aircraft inspection that leverages drones, AI enablement, and cloud collaboration in an effort to increase the quality and reduce the amount of time associated with aircraft inspection, according to C4ISR.net.
Traditional, human-led manual inspection of aircraft take hours and frequently miss tiny details. The Air Force, working with Boeing and Near Earth Autonomy, a company that develops drone operating systems, is testing the use of autonomous uncrewed aerial systems with mounted cameras to catalog the condition of Boeing C-17 cargo planes used to transport passengers and heavy weapons systems.
Images taken by the drones are sent to the cloud and analyzed by pattern recognition software using 3D models of the aircraft. This information is then passed on to human inspectors who can then focus their searches on areas flagged as potential problems by the AI enabled system. According to Scott Belanger, an executive with Boeing Global Services, “we’re not trying to replace the human inspection. We’re trying to inform it. We’re trying to upskill that human inspection so when they do go on the tail, they’re not guessing: They know exactly what to bring, they know exactly what to expect.”
And this technology enabled process can help dramatically reduce the time of inspections. Alli Locher, a manager with Near Earth Autonomy, told reporters on 27 June that “a preflight inspection right now can take up to four hours. We can do it in 30 minutes [with the drone, cloud, AI system].” She continued by saying that “eventually you’ll be able to just pull up a tail number, click anywhere on the 3D model of that aircraft and be able to see a history of images of that exact part you clicked on, from anywhere in the world over the life of the aircraft.”
In addition, the drone inspection process has also proven more accurate in testing, having detected “up to 76%, 78% damage”, which—while still needing improvement—is considerably better than the human-only metric of 50%.
The USAF trial effort is another on the long and growing list of how autonomous systems, machine learning, cloud computing, and other technologies (particularly mixed reality) are increasing the pace of important but frequently tedious, expensive, and time consuming process such as inspection, training, design, logistics, intelligence collection and analysis, and testing.
It also demonstrates how technology is being envisioned not as a means of replacing humans, but rather as a teammate that can vastly improve the efficiency of human activities.
This concept of human-machine teaming is most frequently cited in relation to human operators controlling uncrewed systems in operational environments, but it applies across a broad range of far more mundane tasks in which AI’s capacity to process complex data sets provide human operators with information and recommendations that help focus their actions and inform their decisions.