Avidyne’s recently revealed retrofit flat-panel program is awesome. But the bigger story might be the company’s fairly low-key announcement that it was embarking on a project to…well, do stuff with artificial intelligence. What stuff that is remains to be seen, but one of them is a no-brainer. It is, in fact, something I’ve been advocating for the last 20 years now…using cameras and AI to spot other airplanes. Early experiments that Avidyne is running on that exact capability are extremely promising, and it’s just the start of what AI could do for aviation, every segment of it, from low and slow to globe-spanning aircraft.
The outlook for Avidyne and Swiss partner company Daedalean takes a long view, but its goal is to certify initial capabilities by next year, though Schwinn admits it will take some flexibility from the FAA, as few such systems have ever been approved.
Avidyne is branding the AI initiative “PilotEye Vision System,” which underscores what Avidyne sees as an early function of AI, that is, helping pilots see and avoid other aircraft, something human eyes are woefully underpowered at.
But AI can and certainly will go far beyond traffic spotting. By using sensors, such as the cameras mounted on its research aircraft, AI can take in, analyze and interpret more data more quickly and way faster than any human can. Future capabilities might include landing assist systems, as well.
Avidyne president and CEO Dan Schwinn explained that Daedalean and Avidyne can combine their core competencies, which he described as “artificial intelligence neural network software and certification methodology” at Daedalean with “the proven hardware design, manufacturing and certification expertise here at Avidyne,” in order to make headway into certifiable aviation applications for AI, which Schwinn described as a paradigm shift for the FAA.
“Leveraging advanced AI technologies,” he said, “these solutions will initially include visual-spectrum camera-based systems for visual positioning and traffic detection, hazard avoidance, and landing guidance, as well as providing the data that pilots need for quicker and more-accurate land-anywhere decision-making assistance in the event of emergency.”
It really is a game-changer, though it’s still early in the game. That said, just based on the nature of piloting aircraft, AI will likely bring numerous safety benefits to aviators because it is better at doing what we need to do to avoid known hazards, some of which are difficult or impossible for humans to see and/or avoid.