The first AI pilot allows autonomous aircraft to traverse crowded skies.

Artificial intelligence can safely avoid crashes, forecast other aircraft's intentions, track and coordinate with their actions, and communicate with pilots and air traffic controllers via radio. The researchers from Carnegie Mellon University hope to develop the AI to the point where its actions are indistinguishable from those of a human pilot. To engage with other aircraft as a human pilot would, the AI communicates its intent with other aircraft, whether flown or not, using both vision and natural language. This conduct results in safe and socially acceptable navigation. The researchers achieved this implicit cooperation by training the AI on data collected at Allegheny County Airport and Pittsburgh-Butler Regional Airport, which included air traffic patterns, aircraft photographs, and radio broadcasts. Six cameras and a computer vision system are used by the AI to detect neighboring planes in a way comparable to that of a human pilot. Its automatic voice recognition component employs natural language processing techniques to comprehend incoming radio signals as well as converse with pilots and air traffic controllers via speech.

Drones, air taxis, helicopters, and other aircraft will have more opportunities to operate – transferring people and cargo, checking infrastructure, treating fields to protect crops and monitoring for poaching or deforestation – frequently without a pilot at the controls. However, these aircraft will have to fly in an area already packed with small planes, medical helicopters, and other aircraft. While autopilot controls are prevalent on commercial airliners and other aircraft flying at higher altitudes under instrument flight rules (IFR), building an AI to handle the often congested and pilot-controlled lower-altitude traffic flying under visual flight rules (VFR) has proven difficult. The AI developed by the team is intended to communicate with aircraft in VFR airspace. The AI pilot has yet to be tested on actual aircraft, but it has done well in flight simulations. The team sets up two flight simulators to test the AI. The AI controls one, while a person controls the other. Both fly in the same airspace. Even if the person at the controls is inexperienced, the AI can safely navigate around the piloted aircraft.

Source : https://www.sciencedaily.com/