With the increased prevalence of commercial drones, researchers at Stanford University are working with NASA to develop a drone traffic-management system in which drones will have a greater awareness of their surroundings and will communicate with other drones in order to avoid collisions.
Stanford Intelligent Systems Laboratory is one of the over 130 labs working with NASA to manage drone traffic through an unmanned aerial system traffic management system, or UTM. This system will be able to manage a large number of drone operations without individual human control operators. With Amazon generating 130,000 drone deliveries per normal shopping day, an automated system without human contact is essential.
“You’re not going to hire another 30,000 people just to handle the traffic from drones,” said Hao Yi Ong, a grad student working in the lab, to the Stanford News Service. “It’s just not feasible.”
Also included is automated conflict avoidance, where drones will alert other drones when a collision is possible and will make necessary changes to avoid it.
“UTM is meant to fulfill a lot of the functions of air traffic control, but it will be in the cloud and largely automated,” said Mykel Kochenderfer, an assistant professor of aeronautics and astronautics and director of the lab, to Technologyreview.
Kochenderfer and Ong recently co-published a paper detailing an algorithm that would reduce drone collisions. The lab ran more than a million conflict simulations and determined the drones’ response times and how often a collision would occur. Drones were able to make the quickest decisions when paired with the closest other drone. Once more drones entered the simulation, response decreased, but the system was still able to reroute a drone within 50 milliseconds.
Kochenderfer and his researchers have only tested their work in simulations and still recognize that there is still much work to be done, such as how to account for breakdowns in communication, deliberately disruptive drones and sudden weather anomalies. NASA will be rolling out the UTM solution in a series of four builds with the first one being released last August, and Kochenderfer expects that their technology will be implemented in the final UTM build, estimated for completion in 2019.
“It’s gratifying to work on a problem that people are coming together and knocking heads and figuring out the best solution, even though there actually isn’t a single profitable flight yet,” Ong said.
“This is one of the most exciting areas of aerospace right now — the use of drones,” Kochenderfer said. “Many of the applications they enable can lead to new economic models, but the potential for saving lives and improving efficiency, I think that’s really quite interesting.”
Contact Jeremy Quach at jquach ‘at’ stanford.edu.