There’s no shortage of warnings about robots taking over our jobs, but often overlooked is the potential for how robots and humans can work together.
That’s the focus of new research out of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), which has come up with a new model for how humans can communicate with robots more effectively.
Essentially, it all boils down to protecting humans from information overload, because robots can be programmed to gather huge amounts of information—way more than any human could process comfortably.
Say there’s an emergency like an earthquake and robots are working together to collect information at the scene. They can send each other continual updates along the lines of, “I’ve passed through a door and am turning 90 degrees right” or “After advancing four feet, I’ve encountered a wall.”
It’s important information for rescuers trying to understand what’s happening on the ground, but it can also be too much for humans to process on the fly. That’s where MIT’s new model for communications comes in. It’s an algorithm that helps determine the information that needs to be shared, and the researchers say it can reduce the need for communication by 60 percent.
Ultimately, that could make it easier to design systems that enable humans and robots to work together, such as on emergency-response teams. It could have also have implications for multirobot collaborations that don’t involve humans by minimizing the power spent on communication.
The researchers tested their system on more than 300 computer simulations of rescue tasks in unfamiliar environments. Next will be tests involving humans.
“What I’d be willing to bet is that the human-robot team will fail miserably if the system is just telling the person all sorts of spurious information all the time,” said Julie Shah, an associate professor of aeronautics and astronautics and one of the paper’s two authors. “For human-robot teams, I think that this algorithm is going to make the difference between a team that can function effectively versus a team that just plain can’t.