Mike Sinnett, vice president of product development at Boeing Commercial Airplanes, recently announced that in the next two years they plan to flight-test an artificial intelligence system capable of flying a civil aircraft. Having already started simulations and ground-based experiments this year, they aim to progress to flight tests on real aircraft by 2019, with the tests proving whether or not aircraft with reduced crew or even no pilot could be operated safely for passenger and freight flights.
Since US airlines have not had a fatal accident since 2009, the safety standards for autonomous flights will need to be “as good as zero” said Sinnett. He added “There’s going to be a transition away from the requirement to have a skilled aviator operating the airplane tactically, to having a system that operates the vehicle autonomously – if we can do that at the same levels of safety, integrity and availability that we have today.”
Aviation industry trends appear to be the driving force behind these tests. Boeing forecasts sales of about 40,000 new aircraft in the next two decades and Sinnett believes that “More of those will be growth than replacement.” He added “It begs the question, where are all those experienced pilots going to come from?” Whilst historically airlines have looked towards the military to fill their pilot shortages, recently the military have implemented changes in a bid to level the playing field so that leaving for an airline career becomes a much tougher decision.
The use of autonomous systems is not a new experience for Boeing - earlier this year for example, a research project demonstrated a robotic system called ALIAS (Aircrew Labour In-Cockpit Automation System) which helped a pilot fly and land a Boeing 737.
However, while pilots already use autopilot systems and fly-by-wire controls for level flight and landings, Sinnett believes that in time automation could handle auto-takeoffs as well “The airplane is capable of doing it, but not capable of doing it at the same level of integrity as with a pilot in the loop,” he said. Ultimately, Boeing needs to develop artificial intelligence tools that can replicate the same decision-making processes that pilots use
