Researchers Develop Algorithm To Warn Of Midair Plane Collisions
MIT researchers have developed a new algorithm that could prevent the midair collisions of up to 10 to 12 small aircraft every year.
The Federal Aviation Administration (FAA) mandated that by 2020, all commercial aircraft must be equipped with a new tracking system that broadcasts GPS data, providing more accurate location information than ground-based radar.
The FAA has asked MIT researchers to lead the investigation of the system’s limits and capacities in anticipation of the deadline.
The researchers’ new algorithm uses data from the tracking system to predict and prevent collisions between small aircraft. There have been 112 small planes that have been involved in midair collision in the last 10 years.
Maxime Gariel, a postdoc in MIT’s International Center for Air Transportation and lead author on the new paper, said the challenge in designing a collision-detection algorithm is limiting false alarms.
“If half the time it’s a false alert,” Gariel said in a statement, “[people] are not going to listen to it, or they’ll turn it off.”
The team adopted a two-tiered system of alerts: A moderate alert would warn pilots that their trajectories are converging, and a high alert would indicate a severe risk of collision.
Gariel says the volume of space around each plane is a “hockey puck” that describes the plane’s probable position given a certain GPS reading.
The hockey puck that corresponds to the high alert is smaller and of fixed size, while the one that corresponds to the moderate alert is larger and fluctuates according to the planes’ trajectories.
To calculate the optimal size of the hockey puck, the researchers used six months’ worth of plane data from airports in the San Francisco area. The team had the advantage of a very accurate computer model of air traffic created by researchers at MIT’s Lincoln Laboratory. The Lincoln Lab model generates random trajectories for hypothetical aircraft that accord very well with real-world statistics.
The team tested their algorithm against the Lincoln Lab model and found that it had a low-false-alarm rate.
David Gray, the FAA’s lead on the project, said he has not yet had the opportunity to review the MIT researchers’ results in detail, but that “from the limited data I’ve seen, it seems that the algorithms that they’re looking at are performing better than the algorithms that are in existing systems that can be bought today.”
However, he said the Lincoln Lab air-traffic model is based on radar data, and that small planes often fly below the radar.
“They’re using the model for the scenarios that it’s applicable for,” Gray said in a MIT press release, “and I think that’s going to be great. But for the scenarios that it’s not applicable for, they’re going to have to develop other scenarios for us to assess.”
The team will present their findings in October at the 30th Digital Avionics Systems Conference in Seattle.
On the Net: