Is it possible for one person to supervise a swarm of more than 100 autonomous ground and aerial robots? Absolutely, according to research conducted by Julie A. Adams, professor of computer science at Oregon State University.
“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,” said Adams, who is co-principal investigator and associate director for deployed systems and policy at the university’s Collaborative Robotics and Intelligent Systems Institute. “It makes business sense to deploy delivery drones at scale, but it will require a single person to be responsible for very large numbers of these drones.”
About the Research
Her research, supported by a Defense Advanced Research Project Agency program known as OFFSET or Offensive Swarm-Enabled Tactics, represents a big step toward efficiently and economically using drone swarms beyond package delivery, such as wildland firefighting and disaster response in urban areas.
How the Drones are Deployed
During the project, Adams and colleagues deployed up to 250 autonomous vehicles simultaneously, including multirotor aerial drones and ground rovers capable of gathering information in congested urban environments, where buildings can impair communications. A swarm commander was tasked with single-handedly deploying and controlling each group.
“The commanders weren’t physically driving each individual vehicle, because if you're deploying that many vehicles, they can’t — a single human can’t do that,” Adams said. “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.”
Results of the Field Tests
The tests were conducted in mock urban environments at multiple Department of Defense training facilities. Each multiday field exercise introduced additional vehicles. Every 10 minutes, each swarm commander provided information about their workload and how stressed or fatigued they felt.
During the final field exercise, featuring more than 100 vehicles, the commanders’ workload levels were also assessed through physiological sensors that fed information into an algorithm to estimate their sensory channel workload levels and overall workload.
“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,” Adams said.
