According to the team, the artificial intelligence can safely avoid collisions, predict other aircraft’s intent, track aircraft and coordinate with their actions, and communicate over the radio with pilots and air traffic controllers. The researchers aim to develop the AI so the system’s behaviours will be indistinguishable from those of a human pilot.
“We believe we could eventually pass the Turing Test,” said Jean Oh, an associate research professor at CMU’s Robotics Institute (RI) and a member of the AI pilot team, referring to the test of an AI's ability to exhibit intelligent behaviour equivalent to a human.
To interact with other aircraft as a human pilot would, the AI uses both vision and natural language to communicate its intent, whether piloted or not. This behaviour leads to safe and socially compliant navigation. Researchers said they achieved this implicit coordination by training the AI on data collected at the Allegheny County Airport and the Pittsburgh-Butler Regional Airport that included air traffic patterns, images of aircraft and radio transmissions.
The AI uses six cameras and a computer vision system to detect nearby aircraft similarly to a human pilot. Its automatic speech recognition function uses natural language processing techniques to understand incoming radio messages and communicate with pilots and air traffic controllers using speech.
Advancement in autonomous aircraft will broaden opportunities for drones, air taxis, helicopters and other aircraft to operate — moving people and goods, inspecting infrastructure, treating fields to protect crops, and monitoring for poaching or deforestation — often without a pilot. These aircraft will have to fly, however, in an airspace already crowded with small airplanes, medical helicopters and more.
MORE IN AEROSPACE
The FAA and NASA have proposed dividing this urban airspace into lanes or corridors with restrictions on when, what kind and how many aircraft can use them. This would significantly alter current use and standard practices and could create air traffic jams, preventing critical aircraft, like medivac helicopters, from reaching their destination.
While autopilot controls are common among commercial airliners and other aircraft operating in higher altitudes under instrument flight rules (IFR), developing AI to handle the often crowded and pilot-controlled lower-altitude traffic operating under visual flight rules (VFR) has challenged the industry. The team's AI is designed to seamlessly interact with aircraft in the VFR airspace.
Researchers have yet to test the AI pilot on actual aircraft, but it has reportedly performed well on flight simulators. To test it, the team set up two flight simulators. One is controlled by the AI, the other by a human. Both operate in the same airspace. The AI can safely navigate around the piloted aircraft even if the person behind the controls is not an experienced pilot, researchers confirmed.
Commercially, the AI could help autonomous aircraft deliver packages and ferry passengers, helping to reduce weight and insulate delivery drones and air taxis from pilot shortages.
The research was supported by the U.S. Army Research Office and the Army Futures Command’s Artificial Intelligence Integration Center (AI2C).
Project to investigate hybrid approach to titanium manufacturing
What is this a hybrid of? Superplastic forming tends to be performed slowly as otherwise the behaviour is the hot creep that typifies hot...