Boston Dynamics Atlas robot

Atlas robot by Boston Dynamics for the DARPA Robotics Challenge. Photo courtesy of DARPA.

On a conference call yesterday, DARPA Robotics Challenge (DRC) program manager Gill Pratt updated reporters on the ins and outs of the event later this month.

The DRC is set to take place December 20-21 at the Homestead Speedway outside of Miami. There will be 17 teams and their robots there to complete disaster response tasks with minimal human supervision. This so-called task-level autonomy is a DARPA-hard problem in the field of robotics. Said Pratt on the call:

“Robots right now, for the most part, are either working on a stationary basis in factories, doing very clearly defined repetitive tasks, or they are in laboratories in schools where they are in very controlled environments. Or, if they’re in the outdoors, they’re typically run through something called tele-operation, where a human being is dictating every move that they’re doing every tenth of a second or even faster. What we’re trying to do is to advance that technology and move things from tele-operation to something known as task-level autonomy, where you tell the robot—rather than move forward a tenth of an inch, move left a tenth of an inch—you tell it, “Open that door.” And the robot perceives the handle on the door, reaches out, turns the handle, and opens the door.”

Pratt said the upcoming event will serve as a kind of calibration point for the current state of the art in robotics. He expects the machines to be moving rather slowly. The bots will each have 30 minutes to complete, for example, the door-opening task. The other required tasks will include driving a vehicle, walking moving obstacles blocking a door, climbing a ladder, and using a power tool to cut through a wall. Pratt expects the next DRC event to push the state of the art to more more useful speeds. But for now, he cautioned people not to expect Terminator, despite appearances to the contrary.

“Part of the good that can come out of the trials is that we actually help calibrate the public to what reality is in this field. part of the difficulty with science fiction is that if there’s no counter example—science fact—people…can get the idea that these things aren’t actually very hard to build. So, besides calibrating ourselves to what the state of the art is, I think a lot of the good that we can do here is to calibrate the public.”

There’s a new website with more details: Interesting that DARPA has dropped its own name from the site’s name, perhaps opening the door to handing the competition off to another organization in the future. The event is open to the public.