“Teams of humans are exceptionally good at coordination. Teams of robots, however, are clumsy at coordination, requiring extensive communication and computation.” – Nora Ayanian
There’s no denying it, robots are incomparably skilled when carrying out a specific given task, even if that task requires some light improvisation. The same can’t be said, however, when robots are forced to worked together; the overlap in work either results in extra work on the programming side or redundant/ineffective task management on the robot side. But what if robots could coordinate themselves autonomously depending on what the other robots are currently doing? It may sound like something out of Westworld, but this is exactly the question that Nora Ayanian is working to answer.
Nora Ayanian, assistant professor and Director of the ACT (Automatic Coordination of Teams) Lab at USC, endeavors to make robots and robotics a very real part of everyday life. “I want to make robots easy to use and have them everywhere,” said Ayanian, “they should be accessible, user-friendly and interactive so you can have them in your house and in your car. Right now, robots are really difficult for novices to use.”
Despite her passion for the robotic, her goal to achieve robotic automation would require researching a much less predictable source: people. By developing an online multiplayer game with funding from the National Science Foundation CAREER award, Ayanian was able to study the ways that humans can coordinate together when presented with very little information or communication tools. This research would prove invaluable in defining an automated coordination system for robots and allow to them to “think” of solutions for problems based on the activities of the greater robotic team.
Though automated coordination could certainly be applied to groups of identical robots with identical programming, Nora Ayanian believes that diversity, both in terms of team and of the robots themselves, is the key to solving complex tasks.
“The way we solve multi-robot problems right now is to uniformly apply one control policy to all of the identical robots in the team. For example, imagine we’re trying to monitor air quality with a team of physically identical aerial robots. If we considered all the factors that could affect the problem, the robots, and their capabilities, we might have too many factors to consider and our problem would be intractable,” wrote Ayanian in a blog post for Justmeans.com. “Imagine that same team of aerial robots assisted by robots on the ground. The robots on the ground could provide additional information such as temperature, position, topography, and satellite communications via hardware the aerial robots might not be able to carry. They could also perform computation, telling the aerial robots where to go and mapping the air quality, allowing the aerial robots to use more of their on-board energy for sensing.”
The contributions Nora Ayanian has made to the field of robotics don’t just end with the vast potential of her research, they are also every present in the new generation of roboticists she inspires and works alongside in her role as Director of USC’s ACT lab. We are incredibly excited to see what Ayanian’s work means for the future of robotics and dub her our “Featured Innovator of the Month.”
Note: Nora Ayanian does not work for Willamette Valley Company nor is she affiliated with our company.