PARIS—Researchers at the Department of Artificial Intelligence of the Polytechnic University of Madrid (UPM), Spain, said they have developed an automatic air navigation and collision avoidance model using an automatic learning system.
The software solution, researchers claimed, aligns aircraft flight paths with other nearby aircrafts in a dense airspace such as an airport. If the aircraft is heading towards a building, it automatically avoids the obstacle. And, if several aircrafts are about to land on the same runway, the system prioritizes landing maneuvers without human intervention, they noted.
Scientists explained that the software solution is able to automatically navigate an aircraft and steer it to a target or consecutive targets. The aircraft automatically avoids collision with any physical obstacle, including other aircrafts, land, geographical features and buildings. It also avoids areas with adverse weather conditions, military operation areas, national airspace, etc.
The team indicated that the model implements automatic 3-D maneuvers, where the aircraft performs all sorts of turns with ascents and descents. The model controls all the maneuvers from start to finish, without any pilot or air traffic control involvement or remote steering.
So far, researchers said the model has been used in a simulator but they expect to implement it physically in real air navigation systems as an additional safety measure against human error.
The research project was led by the UPM's Facultad de Informátic, in partnership with the Escuela Superior de Ingenieros Aeronáuticos, EADS and AENA, literally Spanish Airports and Air Navigation.
This story was originally posted by EE Times.
