Coordinated dense aerial traffic with self-driving drones
Balázs, B., & Vásárhelyi, G. (2018, May). Coordinated dense aerial traffic with self-driving drones. In 2018 IEEE International Conference on Robotics and Automation (ICRA) (pp. 6365-6372). doi:10.1109/ICRA.2018.8461073
Interestingly, our articles around autonomous drone traffic received much less attention than ones around flocking, even though performing smooth autonomous traffic is much more complicated than flying in synchrony and potentially also has much more practical applications. During flocking, the goal is to synchronize motion and move together towards a common goal, where conflicts appear only if there are walls or obstacles around. Meanwhile, during traffic every single agent has an individual goal which is for sure in conflict with the goals of all the other agents. They have to coordinate themselves in a common (very dense, in our case) airspace and resolve all trajectory conflicts in real time in a self-organized manner to maximize traffic flow.
To tackle this challenge, we used our flocking models as a base and extended it with traffic-specific interaction and self-propelling terms. The results speak for themselves, we can’t wait to (receive much more citations and) see our algorithms in action in practical applications of drone delivery or any general multi-drone scenario!
In this paper we present a general, decentralized air traffic control solution using autonomous drones. We challenge some of the most difficult dense traffic situations, namely, crosswalk and package-delivery scenarios, where intelligent collective collision avoidance and motion planning is essential for a jam-free optimal traffic flow. We build up a force based distributed multi-robot control model using a tunable selection of interaction terms: anisotropic repulsion, behaviour driven velocity alignment, self-organized queueing and conflict avoiding self-driving. We optimize the model with evolution in a realistic simulation framework and demonstrate its applicability with 30 autonomous drones in a coordinated outdoor flight within a densely packed virtual arena.
- USAF Grant No: FA9550-17-1-0037;
- K_16 Research Grant of the Hungarian National Research, Development and Innovation Office (K 119467);
- János Bolyai Research Scholarship of the Hungarian Academy of Sciences (BO/00219/15/6).