Researchers at Carnegie Mellon University think they have made the first AI pilot that can guide self-flying planes through crowded airspace. The artificial intelligence can track other aircraft and cooperate with their movements, safely prevent crashes, foresee the intentions of other aircraft, and interact with pilots and air traffic controllers via radio. The goal of the researchers is to create an AI whose actions are identical to those of a human pilot.
Jean Oh, an associate research professor at CMU’s Robotics Institute (RI) and a member of the AI pilot team, stated, “We believe we could someday pass the Turing Test,” alluding to the test of an AI’s capacity to demonstrate intelligent behavior comparable to a human.
The AI employs both vision and natural language to convey its intent to other aircraft, whether flown or not, to engage with them as a human pilot would. To navigate safely and in accordance with social norms, adopt this conduct. For this implicit coordination, researchers trained the AI with data from the Allegheny County Airport and the Pittsburgh-Butler Regional Airport. This data included air traffic patterns, photos of planes, and radio broadcasts.
Similar to a human pilot, the AI employs six cameras and a computer vision system to identify surrounding planes. Its automatic voice recognition feature uses NLP methods to comprehend incoming radio transmissions and speak verbally with pilots and air traffic controllers.
The development of autonomous aircraft will increase the possibilities for drones, air taxis, helicopters, and other aircraft to operate, often without a pilot at the controls, moving people and goods, inspecting infrastructure, treating fields to protect crops, and monitoring for poaching or deforestation. But the area where these planes have to fly is already full of small planes, medical helicopters, and other planes.
The FAA and NASA have suggested segmenting this urban airspace into lanes or corridors with limitations on the times, types, and numbers of aircraft that are permitted to use them. This could lead to air traffic bottlenecks that would prohibit essential aircraft, such as medical evacuation helicopters, from reaching their destination and would fundamentally alter how this airspace is now used and generally operated.
The aerospace industry has faced challenges in developing an AI to handle the air traffic and pilot-controlled lower-altitude traffic operating under visual flight rules (VFR), even though autopilot controls are common among commercial airliners and other aircraft operating at higher altitudes under instrument flight rules (IFR). The AI used by the team is built to interact with airplanes in VFR airspace with ease.
Sebastian Scherer, an associate research professor at the RI and a member of the team, said that this is the first AI pilot to successfully operate in the current airspace. “That airspace won’t change for UAVs, in my opinion. The airspace will require the UAVs to adapt. ”
The AI pilot has done well in-flight simulators, but the company has not yet tested it on actual planes. The team set up two flight simulators to evaluate the AI. The AI controls one, while a person is in charge of the other. They both use the same airspace. Even if the pilot at the controls lacks experience, the AI can safely maneuver around the controlled air traffic.
Commercially, AI could assist autonomous aircraft in carrying passengers and delivering products air traffic. Ideally, delivery drones and air taxis wouldn’t have pilots on board. This would make them lighter and protect them from a lack of pilots.
The project’s lead researcher, Jay Patrikar, a Ph.D. candidate at the RI, stated, “We need more pilots, and AI can help.”
The U.S. Army Research Office and the Artificial Intelligence Integration Center of the Army Futures Command provided funding for this study (AI2C).
