The US Army is working on a technique that will allow teams of robots on the battlefield to work together effectively, even when communications become spotty. Called α-shape, the approach helps groups of autonomous robots achieve their mission goals without conflict or duplication of efforts, despite not being able to consult with one another.
If robots are to be any use on the battlefield, then they must be able to operate under all the frustrations of the battlefield – not the least of which is that communications are often not available due to equipment failures, enemy countermeasures, or the need for stealth. This is especially true for teams of robots that have enough intelligence to adapt to conditions to accomplish their goals, but don't have ideal communication links to sort out who does what.
"Robots working in teams need a method to ensure that they do not duplicate effort," says Army researcher Dr. Bradley Woosley. "When all robots can communicate, there are many techniques that can be used; however, in environments where the robots cannot communicate widely due to needing to stay covert, clutter leading to radios not working for long distance communications, or to preserve battery or bandwidth for more important messages, the robots will need a method to coordinate with as few communications as possible."
Developed by the US Army Combat Capabilities Development Command (DEVCOM), Army Research Laboratory, and the University of Nebraska, Omaha Computer Science Department α-shape works by assigning a task to one of the team robots, then providing this information to other select robots who remember that fact. This will allow the other robots to ask who is doing this task without having to communicate directly with the robot in question, which could be in communicado at the moment.
Which robot remembers each task assigned is based on how the team's communications network is configured, and the geometry of how the robots are deployed. Each robot has an area in which they are required to remember what the goals are, and who has been assigned to the task needed to achieve those goals.
This means that the robots can quickly find the robot with the needed information, like contacting the supervisor of a department to learn what's going on. An intelligent search algorithm is also used to identify conflicts and store them for later resolution when communications are re-established. In this way, the robot team is resilient, uses less bandwidth, and each robot is better able to work independently.
"This research enables coordination between robots when each robot is empowered to make decisions about its next tasks without requiring it to check in with the rest of the team first," says Woosley. "Allowing the robots to make progress towards what the robots feel is the most important next step, while handling any conflicts between two robots as they are discovered when robots move in and out of communications range with each other."
The research was published in Robotics and Autonomous Systems.
α-shape is outlined in the following video:
Source: US Army