October 25, 2012
Robotics Challenge Teams Announced By DARPA
redOrbit Staff & Wire Reports - Your Universe Online
The Defense Advanced Research Projects Agency (DARPA) announced on Wednesday some of the top teams that will compete in its $2 million contest to create robots that can be used to assist in natural disasters and other emergencies.
The DRC was inspired by the “Fukushima 50,” a group of 50 men who risked their lives to prevent a nuclear meltdown at Japan´s Fukushima Dai-ichi power plant during the aftermath of the 2011 Tsunami. The program is seeking robotic substitutes that could someday take the place of humans in such dangerous situations.
Over the next two years, teams will compete to develop and put to the test hardware and software designed to enable robots to assist humans in various emergency response scenarios.
Dr. Gill Pratt, the DRC´s program manager, said the program´s focus on humanitarian assistance in disaster response is tied in with one of the ten Department of Defense primary missions that were outlined by the White House and the Secretary of Defense in January.
DARPA had previously announced the contest, but Wednesday´s news provided additional details, including the selection of two teams that will compete in separate “tracks.”
Track A teams will create the robots themselves, along with the software, while Track B teams will be provided with the Boston Dynamics-designed Atlas robot, the successor to the Pet-Proto, for which it will create software.
“Over the next two years, teams will compete to develop and put to the test hardware and software designed to enable robots to assist humans in emergency response when a disaster strikes,” DARPA said in its announcement.
“Based on proposals submitted in response to a Broad Agency Announcement, DARPA has selected and will provide funding for seven teams in Track A of the DRC to develop new robotic systems containing both hardware and software and 11 teams in Track B to develop software only.”
The teams will all receive DARPA funding for their projects, and will have until the end of next year to complete them, the agency said.
The selected Track A teams include those from Carnegie Mellon University, Drexel University, Raytheon, SCHAFT, Virginia Tech, the NASA Johnson Space Center and the NASA Jet Propulsion Laboratory. The Track B teams are from Lockheed Martin's Advanced Technology Laboratories, RE2, the University of Kansas, Carnegie Mellon University, the Massachusetts Institute of Technology, TRAC Labs, University of Washington, the Florida Institute for Human and Machine Cognition, Ben-Gurion University, the NASA Jet Propulsion Laboratory and TORC Robotics.
“Track C of the Challenge provides an opportunity for individuals and teams from around the world to compete without the need for hardware,” DARPA said.
“Anyone with the skills to develop the software needed to advance core robotic software capabilities can register and participate using the open-source DRC Simulator.”
The DRC Simulator is currently available in beta version, and will be improved in the coming months, DARPA said.
“Over time, it will be increasingly populated with models of robots, perception sensors and field environments, and function as a cloud-based, real-time, operator-interactive virtual test bed that uses physics-based models of inertia, actuation, contact and environment dynamics.”
Registration for Tracks C and D, which is just beginning, can be completed here.
“Expertise in software for robotic perception, planning, control and human-robot interface, and experience in physics-based games, models and simulation, as well as open-source code, will all be useful,” the agency said.
Participants in Track C will not receive DARPA funding up front. However, if they perform better than the Track A and B teams, they may be eligible to receive one of six Atlas robots to work with, along with funding to progress further in the challenge.
Track D is for those who do not want to take any DARPA funding, but still want to compete in the contest.
The robots will be required to drive a vehicle, under the supervision of a remote operator, open a door, climb a stairway and connect a cable or a fire hose.
They will also be tasked with figuring out tools.
"Disasters often occur in environments that have plentiful numbers of tools that are meant for human beings," Pratt told PCMag.
"And by tools, I mean things from screwdrivers to vehicles and everything in between. And often those tools are around both for construction and repair and maintenance. And, again, during the first few days after a disaster, there is no time to bring in specialized tools and, so, can we build robots that can reuse tools that were originally meant for human beings?"
Human-robot interaction is another vital component of the DRC.
"Often in a disaster, the experts who know how to handle the disaster are not robotics experts," Pratt said.
"And so we want to shorten the amount of time and the amount of work that needs to be done to allow those people to be able to directly use the robots in the disaster.”
Pratt pointed to the Fukushima tragedy, where robots from Japan and the U.S. were rapidly brought in to assist, but the plant operators needed to spend several days training to use them.
The $2M prize for the team that best meets DARPA's requirements will be awarded sometime around December 2014.
Beyond the creation of task-driven robots that can assist in emergencies, DARPA said the DRC has higher-level goals that apply to the field as a whole.
For instance, Pratt said the agency is also funding the Open Source Robotics Foundation, which seeks to create an open-source simulation package that uses cloud computing for quick and easy scalability.
“The DRC Simulator is going to be one of DARPA´s legacies to the robotics community,” said Pratt.
“One of DARPA´s goals for the Challenge is to catalyze robotics development across all fields so that we as a community end up with more capable, more affordable robots that are easier to operate. The value of a cloud-based simulator is that it gives talent from any location a common space to train, design, test and collaborate on ideas without the need for expensive hardware and prototyping.”
“In particular, we want to have these tools outlast the program and be the foundation for catalyzing the field of robotics, particularly helping to make the design of robots move from an art to a science.”
Track A´s robot designs can be viewed here.