A robotic copilot autonomously learned how to fly and land an aircraft in a Boeing 737-800NG simulator.

This is part of Aurora Flight Sciences’ contribution to the Aircrew Labor In-Cockpit Automation System (ALIAS) program, which was created by the Defense Advanced Research Projects Agency (DARPA).

As claimed by DARPA, automated capabilities in military aircraft demand complex interfaces to efficiently respond to emergency situations. Software and avionics upgrades are a viable option, but they come at a steep cost, potentially worth tens of millions of dollars per aircraft.

"The program intends to leverage the considerable advances made in aircraft automation systems over the past 50 years, as well as similar advances in remotely piloted aircraft automation, to help reduce pilot workload, augment mission performance, and improve aircraft safety," according to DARPA.

To further these goals, Aurora has run a series of successful robotic flight tests mimicking various aviation scenarios. This builds upon Aurora’s list of promising ALIAS-related tests on a DHC-2 Beaver, UH-1 Iroquois, Cessna 208 Caravan, and Diamond DA42 aircraft.

In the event that the pilot is incapacitated, the robot used the 737’s existing auto-landing system to safely descend back to the ground. The simulation tests were conducted at the U.S. Department of Transportation’s John A. Volpe National Transportation Systems Center in Cambridge, MA.

"Having successfully demonstrated on a variety of aircraft, ALIAS has proven its versatile automated flight capabilities," says Aurora’s Vice President of Research and Development John Wissler in a press release. "As we move towards fully automated flight from take-off to landing, we can reliably say that we have developed an automation system that enables significant reduction of crew workload."

What’s next in the ALIAS program? Well, Aurora is currently developing a version of the system without robotic actuation. This variation will offer support to the aircraft’s pilot by tracking the plane’s procedural, physical, and mission states. By continually updating the pilot on its gathered data, it increases the pilot's overall situational awareness while in the air.

Other goodies include in-cockpit machine vision, advanced tabled-based user interface, robotic components for flight control operation, speech recognition and synthesis, and a knowledge procurement process that transfers an automation system to another aircraft within 30 days.  

Watch Aurora’s latest accomplishments in the video below.