Robotic Software Competition Features Disaster-Response Scenarios

The Defense Advanced Research Projects Agency (DARPA) awarded funds and an Atlas robot to more than half a dozen teams who competed in a software challenge called the Virtual Robotics Challenge (VRC).

As a precursor to the Robotics Challenge, teams competing in the VRC developed software to power robots capable of responding more effectively to natural and human-derived disasters.

Out of a total of 26 teams from eight countries, nine will move forward through the surprise help of NASA's Jet Propulsion Laboratory.

"Jet Propulsion Laboratory, which also has a DARPA-funded Track A effort with its own robot, decided to merge its two efforts and offer the bulk of the resources it earned in the VRC to other teams," DARPA said in a statement.

In all, seven teams will be able to use the Atlas robots in the DRC Trials this coming December while the JPL donated its robot and a portion of its winnings to the Lockheed Martin Trooper team, leaving the newly-combined Team K and Case Western team to use an Atlas robot donated by Hong Kong University and the remaining JPL funds.

Each team was evaluated based on task completion and effective operator control of robots in five simulated runs for three different tasks addressing robot perception, manipulation and locomotion.

These tasks included: entering, driving and exiting a utility vehicle; walking across muddy and uneven terrain; and attaching a hose connector to a spigot, then turning a valve.

To simulate communications limitations in a disaster zone, the challenge imposed a round trip of latency of 500 milliseconds on data transmission and varied the total number of communications bits available in each run from a high of 900 megabits to a low of 60 megabits.

"The VRC and the DARPA Simulator allowed us to open the field for the DARPA Robotics Challenge beyond hardware to include experts in robotic software," Gill Pratt, DRC program manager, said of the competition, adding that "integrating both skill sets is vital to the long-term feasibility of robots for disaster response."