The Defense Advanced Research Projects Agency (DARPA) has approved phase two of a research project to enable the automation of air traffic control.
The phase two contract, awarded to Lockheed Martin Advanced Technology Laboratories, is a 12-month, $5.2 million effort to advance an artifical intelligence system called Generalized Integrated Learning Architecture (GILA).
The decision to proceed to phase two followed a successful go, no-go test that measured GILA's performance on a variety of air operations scenarios.
If successful, GILA will provide support for new human air traffic controllers and aid in the deconfliction of congested in-theatre airspace with the generation of airspace control orders.
The increased use of unmanned air vehicles in combination with manned aircraft is expected to further complicate airspace management in future.
"Eventually [GILA] will outperform the novice human planner by 125% while giving the inexperienced user an embedded, accelerated training capability," says Lockheed. GILA was developed under a $22 million, 48-month phase one contract award.
Lockheed's project partners include the University of Maryland, Georgia Institute of Technology, Georgia Tech Research Institute, University of Illinois, Arizona State University, Stanford University, University of Massachusetts, University of Wyoming, Oregon State University, and Fujitsu Laboratories of America.