Decentralized traffic management of autonomous drones

SwarmInt2024

Balázs, B., Vicsek, T., Somorjai, G., Nepusz, T., & Vásárhelyi, G. (2023). Decentralized traffic management of autonomous drones. Submitted to Swarm Intelligence, arXiv preprint arXiv:2312.11207.

Background

Flocking and traffic are the two basic orthogonal building blocks of swarm motion. In flocking, agents have the same goal and synchronize their motion to go together. In traffic, agents have individual goals and coordinate their motion to avoid conflicts smoothly. This article focuses on the latter case. We developed a traffic algorithm and flew the largest ever autonomous swarm of 100 drones with it. (Note that limits are purely financial, not technical as we demonstrate also in the article with 2500 drones in simulation).

To achieve these goals, we use the same mindset and concept as with our previous flocking algorithms, and combine momentary flocking terms – optimized for traffic – with self-organized path planning. The results substantially outperforms what could ever be done with human pilots.

Video abstract

Will be available upon publication…

Abstract (preprint, first submitted version)

Coordination of local and global aerial traffic has become a legal and technological bottleneck as the number of unmanned vehicles in the common airspace continues to grow. To meet this challenge, automation and decentralization of control is an unavoidable requirement. In this paper, we present a solution that enables self-organization of cooperating autonomous agents into an effective traffic flow state in which the common aerial coordination task - filled with conflicts - is resolved. Using realistic simulations, we show that our algorithm is safe, efficient, and scalable regarding the number of drones and their speed range, while it can also handle heterogeneous agents and even pairwise priorities between them. The algorithm works in any sparse or dense traffic scenario in two dimensions and can be made increasingly efficient by a layered flight space structure in three dimensions. To support the feasibility of our solution, we experimentally demonstrate coordinated aerial traffic of 100 autonomous drones within a circular area with a radius of 125 meters.

Funding

Special thanks to CollMot Robotics for using their intelligent drone swarm and their swarm-level ground control station, Skybrush.

Media Coverage

Be the first to write about this article!