A single human can oversee a “swarm” of more than 100 autonomous ground and aerial robots without taking on an excessive amount of labor, according to research from Oregon State University.
The results are a significant step toward the efficient and cost-effective use of swarms in a variety of applications, including package delivery, urban disaster response, and wildland firefighting.
We don’t see a lot of delivery drones yet in the United States, but there are companies that have been deploying them in other countries. It makes business sense to deploy delivery drones at a scale, but it will require a single person be responsible for very large numbers of these drones. I’m not saying our work is a final solution that shows everything is OK, but it is the first step toward getting additional data that would facilitate that kind of a system.
Julie A. Adams, Professor, College of Engineering, Oregon State University
The findings from the Defense Advanced Research Project Agency’s OFFSET program—short for Offensive Swarm-Enabled Tactics—were published in Field Robotics. In 2017, Adams was a member of a team that was awarded an OFFSET grant.
Over the four-year study, researchers deployed swarms of up to 250 autonomous vehicles, including multirotor airborne drones and ground rovers, to gather data in urban areas known as “concrete canyons,” where buildings obstruct line-of-sight satellite-based communication. The data that the swarms gather on their missions at military urban training areas might contribute to increased safety for American citizens and soldiers.
Adams served as a co-principal investigator on one of two swarm system integrator teams that created the framework for the system and combined the efforts of other groups that were primarily concerned with virtual environments, swarm tactics, swarm autonomy, human-swarm collaboration, and physical experimentation.
Adams added, “The project required taking off-the-shelf technologies and building the autonomy needed for them to be deployed by a single human called the swarm commander. That work also required developing not just the needed systems and the software, but also the user interface for that swarm commander to allow a single human to deploy these ground and aerial systems.”
A virtual reality interface known as I3, created in collaboration with Smart Information Flow Technologies, allows the commander to direct the swarm from a high altitude.
“The commanders weren’t physically driving each individual vehicle, because if you are deploying that many vehicles, they can't – a single human can’t do that. The idea is that the swarm commander can select a play to be executed and can make minor adjustments to it, like a quarterback would in the NFL. The objective data from the trained swarm commanders demonstrated that a single human can deploy these systems in built environments, which has very broad implications beyond this project,” Adam further stated.
Several Combined Armed Collective Training Facilities operated by the Department of Defense hosted testing. Additional vehicles were introduced throughout each multiday field exercise, and swarm commanders reported on their workload and level of stress or exhaustion every ten minutes.
The commanders’ workload levels were also measured during the last field exercise, which included over 100 vehicles, using physiological sensors. The data from these sensors was entered into an algorithm that calculates an individual’s total workload as well as the workload levels in their sensory channels.
Adams concluded, “The swarm commanders’ workload estimate did cross the overload threshold frequently, but just for a few minutes at a time, and the commander was able to successfully complete the missions, often under challenging temperature and wind conditions.”
Straub, C., et. al. (2024). Predicting the stability of star clusters in general relativity. Classical and Quantum Gravity. doi:10.1088/1361-6382/ad228a