Tech News

OSU research finds that a single person can oversee a “swarm” of 100 unmanned autonomous vehicles.


CORVALLIS, Ore. – Research involving Oregon State University has shown that a “swarm” of more than 100 autonomous ground and aerial robots can be supervised by a single person without subjecting them to excessive workload .

The results represent a big step toward efficient and economical use of swarms in a range of roles from fighting wildfires to delivering packages to responding to disasters in urban environments.

“We don’t see many delivery drones in the United States yet, but some companies are deploying them in other countries,” said Julie A. Adams of the OSU College of Engineering. “It makes business sense to deploy delivery drones at scale, but it will require a single person to be responsible for a very large number of these drones. I’m not saying that our work is a final solution that shows everything is fine, but it is the first step toward obtaining additional data that would facilitate this type of system.

The results, published in Field Robotics, come from the Defense Advanced Research Project Agency’s program known as OFFSET, short for Offensive Swarm-Enabled Tactics. Adams was part of a group that received an OFFSET grant in 2017.

During the four-year project, researchers deployed swarms of up to 250 autonomous vehicles – multi-rotor aerial drones and ground vehicles – capable of gathering information in a “concrete canyon” urban environment where visibility direct, satellite-based communication is impaired by buildings. Information collected by Swarms during their missions to urban military training sites has the potential to help ensure better security for U.S. troops and civilians.

Adams was co-principal investigator on one of two swarm systems integrator teams that developed the system infrastructure and integrated the work of other teams focused on swarm tactics, swarm autonomy, the human-swarm team, physical experimentation and virtual environments.

“The project required taking commercially available technologies and building the autonomy so that they could be deployed by a single human called the swarm commander,” said Adams, associate director for systems and policy. deployed at OSU’s Collaborative Robotics and Intelligent Systems Institute. . “This work also required developing not only the necessary systems and software, but also the user interface for this swarm commander to allow a single human to deploy these ground and air systems.”

Collaborators at Smart Information Flow Technologies developed a virtual reality interface called I3 that allows the commander to control the swarm with high-level instructions.

“Commanders weren’t physically driving each individual vehicle, because if you deploy that many vehicles, they can’t — a single human can’t do it,” Adams said. “The idea is that the swarm commander can select a play to run and make minor adjustments to it, just like a quarterback would in the NFL. Objective data provided by trained swarm commanders demonstrated that a single human can deploy these systems in built environments, which has very broad implications beyond this project. »

Testing took place at several Department of Defense joint collective training facilities. Each multi-day field exercise introduced additional vehicles, and every 10 minutes, swarm commanders provided feedback on their workload and their level of stress or fatigue.

During the latest field exercise, involving more than 100 vehicles, commanders’ workload levels were also assessed using physiological sensors which fed information into an algorithm that estimates channel workload levels a person’s sensory and overall workload.

“The swarm commanders’ workload estimate frequently exceeded the overload threshold, but only for a few minutes at a time, and the commander was able to successfully complete missions, often in temperature and temperature conditions. wind conditions,” Adams said.


Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button