Electronic Design

DARPA Chooses Urban Challenge Semifinalists

We're down to the semifinals, and the robots are ready. The Defense Advanced Research Projects Agency (DARPA) has selected the 36 teams that will move on to the next round of the 2007 Urban Challenge, scheduled for October 26-31 at the former George Air Force Base in Victorville, Calif. The top 20 teams from this national qualifying event (NQE) will then participate in the finals on November 3.

The program challenges teams to develop fully robotic vehicles that operate completely autonomously, obey California traffic laws while performing maneuvers such as merging into traffic and avoiding moving obstacles, and complete a 60-mile course in less than six hours. Such vehicles are key to the military's future, as a 2001 Congressional mandate requires a third of all combat ground vehicles to be unmanned by 2015.

"The depth and quality of this year's field of vehicles is a testimony to how far the technology has advanced since the first Grand Challenge in 2004," said Tony Tether, director of DARPA. While previous competitions put the robots through their paces in a desert environment, this year's Grand Challenge will have the robots go head to head on city streets.

"The vehicles must perform as well as someone with a California driver's license," Tether said. And more than safety is on the line, as the competition will award $2 million to the winning team, $1 million for second place, and $500,000 for third.

Place your bets
Stanford University's Racing Team is an early favorite, as its modified Volkswagen Touareg successfully navigated 132 miles of Nevada desert to win the 2005 Grand Challenge. Nicknamed Junior, the team's modified Volkswagen Passat will be called to duty this year (see the figure). Don't let the name fool you, though. Junior is far more advanced than its predecessor.

"In the last Grand Challenge, it didn't really matter whether an obstacle was a rock or a bush because either way you'd just drive around it," said Sebastian Thrun, a Stanford associate professor of computer science and electrical engineering. "The current challenge is to move from just sensing the environment to understanding the environment." Junior's range-finding laser array spins to provide a 360° 3D view of the surrounding environment in real time. It's joined by a device with six video cameras that "see" all around the car. Junior also sports bumper-mounted lasers, radar, GPS receivers, and internal navigation hardware. Using Intel Core 2 Duo processors, its hardware and software process all of this data to navigate safely.

Bigger and badder
Not all of the competitors hail from academic backgrounds - and not all of the cars will come from the showroom floor. Team Oshkosh will represent Oshkosh Truck Corp. with TerraMax, based on the company's four-by-four Medium Tactical Vehicle Replacement defense truck platform. It features rear steer, a 21-ft turning radius, and a 425-hp Cat C-12 engine for plenty of power in any environment.

TerraMax's autonomous vehicle control system was developed in kit form. That means this modular setup can be adapted and integrated onto most vehicles, particularly military vehicles. It includes a customized light detection and ranging (LIDAR) system and a GPS/IMU navigation system. Also, its Command Zone multiplexed electronics system operates and diagnoses all by-wire vehicle systems.

"Events such as this provide an excellent framework for the advancement of unmanned vehicle technology," said Don Verhoff, executive vice president of corporate engineering and technology with Oshkosh Truck Corp., "a technology that we are passionate about to help save soldiers' lives."

For more about the contest and the competitors, go to www.darpa.mil/grandchallenge. Richard Gawel

TAGS: Intel
Hide comments


  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.