The July 2022 issue of IEEE Spectrum is here!

Close bar

DARPA Robotics Challenge Trials: Final Results

It's the end of Day 2 of the DRC Trials, and here's how it all ended up

2 min read
DARPA Robotics Challenge Trials: Final Results

It's Saturday evening, and mere moments ago, the DARPA Robotics Challenge Trials officially ended. We'll have more DRC coverage for you over the next few days, and lots more video, but we wanted to bring you the results of the Trials just as soon as they were announced, which should be any moment now.

Have a look at our earlier post on events and scoring for a sense of what these numbers mean, but the important bits are that each task was worth a maximum of four points, and time is only a factor if there's a tie. Otherwise, robots were free to use the entire 30 minutes for each task, and they were also free to end a task at any point (or not compete at all). And here are the final scores, just posted by DARPA:

Now, here's why the scores matter, as far as the teams (and DARPA) are concerned: 

Up to eight teams will move forward with DARPA funding to compete in the DRC Finals in 2014, while other teams will also be welcome to compete using independent sources of funding.

So the the top eight teams that will get funded through to the finals in 2014 are:

1. SCHAFT

2. IHMC Robotics

3. Tartan Rescue

4. MIT

5. RoboSimian

6. Team TRACLabs

7. WRECS

8. Team TROOPER

DARPA says each team may get up to 1 million dollars, but contract negotiations will happen first. We'll get you more details on the funding when they're available. We'll also get you detailed scoring breakdowns as soon as DARPA posts them. For now, here are some awards DARPA announced:

Best in Task Awards:

Vehicle: WRECS

Terrain: SCHAFT

Ladder: SCHAFT

Debris: SCHAFT

Door: IHMC Robotics

Wall: IHMC Robotics

Valve: THOR

Hose: SCHAFT

Gill Pratt just got a standing ovation from everyone, and said, 

"I've been telling the media over the past couple of months that I would be thrilled if even one of the teams scored even half of the points in the DRC trials. It runs out that four of the teams scored more than half. This has been an incredible event that has exceeded my expectations multiple, multiple times."

Heck yeah.

The official post-event press conference is scheduled to start at 7 pm, and we'll update this post with additional info (including, we hope, the plan for 2014) as soon as we get it.

[ DARPA Robotics Challenge ]

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman
LightGreen

“I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

This article is part of our special report on AI, “The Great AI Reckoning.”

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓Show less