AI Just “Landed” a Boeing 737 for the First Time By Itself
It’s going to take us a healthy dollop of faith in technology to accept autonomous vehicles at some point on our roadways. But what about in our skies? The thought of robot-driven planes ferrying hundreds of people overhead to their destinations conjures images of metal, fire, and passengers raining down from the skies. Still, proponents of such systems believe autonomous transport of all kinds, including commercial flight, will be less prone to error when humans are removed from the equation. Once the bugs have been worked out, of course.
The U.S. military believe automated aircraft may improve mission safety and success rates, and their Defense Advanced Research Agency, or DARPA, has just announced the successful simulated flight and landing of a Boeing 737 by an AI-driven robot co-pilot named ALIAS. “ALIAS” is an acronym for “Aircrew Labor In-Cockpit Automation System.”
DARPA hopes ALIAS can eventually be trusted with the “execution of an entire mission from takeoff to landing, even in the face of contingency events such as aircraft system failures.”
ALIAS was built for DARPA by Aurora Flight Sciences, “a leader in the development and manufacturing of advanced unmanned systems and aerospace vehicles,” according to their website. It goes far beyond existing autopilot systems that are limited to assisting a human pilot in flying a plane in-between the critical takeoff and landing phases.
ALIAS has, broadly speaking, three components:
(AURORA FLIGHT SCIENCES)
ALIAS has previously been tested in a real Cessna Caravan.
(AURORA FLIGHT SCIENCES)
ALIAS has also flown a Diamond DA42 light aircraft and a Bell UH-1 helicopter.
Diamond DA42 and Bell UH-1 (DIAMOND AIRCRAFT/BELL HELICOPTER)