Communications of the ACM
Helping Drone Swarms Avoid Obstacles Without Hitting Each Other
Engineers at the Swiss Federal Institute of Technology Lausanne developed a predictive control model that allows swarms of drones to fly in cluttered environments quickly and safely.
Credit: Alain Herzog/EPFL
A predictive control model developed by engineers at the Swiss Federal Institute of Technology Lausanne (EPFL) allows individual drones to predict their own behavior and that of neighboring drones in a swarm, to keep them from bumping into each other.
EPFL's Enrica Soria said, "Our model gives drones the ability to determine when a neighbor is about to slow down, meaning the slowdown has less of an effect on their own flight."
In the new model, Soria explained, "Drones are commanded using local information and can modify their trajectories autonomously."
Tests conducted in the university’s Laboratory of Intelligent Systems found that in areas with multiple obstacles, the model improves a drone swarm's speed, order, and safety.
From EPFL News (Switzerland)
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found