12/12/2018
Written by
Flying drones is a little like parenting toddlers – when more than one is involved, it’s difficult to predict what they will do next, and there’s a chance one could go rogue at any time.
Illinois Computer Science Research Assistant Professor Sibin Mohan is working with The Boeing Company on a new project intended to provide a better understanding of the behavior of groups of unmanned aerial vehicles (UAVs), alerting operators if any are behaving irregularly or have been hacked.Mohan’s project with Boeing, “Characterizing Behavior and Anomaly Detection in Distributed Unmanned Vehicles,” will outline what constitutes normal behavior for these types of systems.
The ability to control a UAV swarm is crucial. With applications ranging from search and rescue to agriculture, the use of groups of unmanned vehicles is only expected to increase.
“If we can detect that the system, or parts of a system, is not functioning correctly, then we can fix it,” said Mohan, who also is part of the Information Trust Institute. “If you can’t detect an error, then the operator may not know that an action has to be taken, much less what actions to take.”
In instances where only one UAV is used, the controller largely knows what the vehicle is supposed to do. However, when many UAVs interact with one another, then such interactions can change their behavior.
“If multiple vehicles are communicating with each other and something looks odd, it could be for a number of reasons,” Mohan explained. “Maybe they are too far apart, the environment is causing abnormal behavior, someone has hacked one or more of them, or some unexpected group behavior has emerged. You have to know what the correct or expected behavior is to know something is odd.”
UAV and ground-rover swarms are particularly vulnerable to attacks in part because they rely on wireless communication. This system is unreliable and easy to jam, which makes it even more important to know how groups of vehicles should operate.
Mohan’s collaboration with Boeing is set to run for three years.
Mohan, along with graduate and undergraduate students, will be building test platforms to study and characterize normal vehicle behavior using machine learning techniques.
“We haven’t begun building the platforms yet,” said Mohan. “As part of the collaboration we will demonstrate our results on a realistic platform so it’s not purely theoretical research.”