Stanford team wins $2m. Way to go!
Three driverless robotic vehicles led by Stanford University on Saturday crossed the finish line of a $2 million Pentagon-sponsored robot race across the rugged Mojave Desert.
The race announcer did not immediately declare a winner because 22 out of the 23 robots left the starting line at staggered times at dawn, racing against the clock rather than each other.
As Stanford’s Volkswagen robot dubbed Stanley crossed the finish line, a group of Stanford students erupted into cheers and carried their team leader, Sebastian Thrun, on their shoulders.
“The impossible has been achieved,” said Thrun, throwing his cap into the crowd.
Three robots remained on the course.
Stanley started in second, but passed the pole position vehicle, a converted red Hummer named H1ghlander, at the 102-mile mark of the race. H1ghlander and a customized Humvee named Sandstorm, both by Carnegie Mellon University, also finished the race.
“I’m on top of the world,” said Carnegie Mellon robotics professor William “Red” Whittaker. “It’s the greatest day ever for these machines that pound through the desert.”
Whittaker said it appeared H1ghlander suffered a technical glitch that allowed Stanford’s robot to overtake it.
Last year’s much-hyped inaugural robot race ended without a winner when all the self-navigating vehicles broke down shortly after leaving the starting gate. Sandstorm chugged the farthest last year at 7 1/2 miles.
Of the 23 robots that competed Saturday, 15 vehicles failed to navigate the entire 132-mile course, but most still managed to beat Sandstorm’s mileage last year.
The Pentagon’s Defense Advanced Research Projects Agency, or DARPA, plans to award the prize to the first vehicle to cover the race in less than 10 hours. The taxpayer-funded race was intended to spur innovation and development of remote control-free robots that could be used in the battlefield.
Stanley finished the course in less than 7 1/2 hours.
The unmanned vehicles must use their computer brains and sensing devices to follow a programmed route and avoid hitting obstacles that may doom their chances.
Early Saturday, teams were given a CD-ROM with GPS coordinates that chart the exact route. The all-day race, which starts and ends in the casino town of Primm, spans the Mojave Desert on the Nevada side.
Vehicles have to drive on rough, winding desert roads and dry lake beds filled with overhanging brush and man-made obstacles. The machines also must traverse a narrow 1.3-mile mountain pass with a steep drop-off and go through three tunnels designed to knock out their GPS signals.
To qualify, vehicles competed in a weeklong trial at the California Speedway outside of Los Angeles where they had to zip through a 2.5-mile bumpy track littered with hay bales, traffic cones and junk cars. All 23 finalists completed the course at least once.
This year’s field was more competitive. Even before Saturday’s race, many teams tested their vehicles in parts of the Southwest desert under race-like conditions including some that practiced on last year’s course from Barstow, Calif., to Primm.
The vehicles were tricked out with the latest sensors, lasers, cameras and radar that feed information to several onboard computers. This, in turn, helps vehicles make intelligent decisions such as distinguishing a dangerous boulder from a tumbleweed and calculating whether a chasm is too deep to cross.
Cornell University’s military light strike vehicle traveled about 20 miles when it failed to across a bridge. Team members were trying to figure out what went wrong.
“We’re at a loss,” said Ephrahim Garcia, a Cornell mechanical engineer. “It’s a disappointment.”
Each contestant was followed by a chase vehicle. To ensure safety, a judge in the chase vehicle could pause a robot during the race, stopping the 10-hour clock without penalty. The judge also could press a kill switch if the robot was headed toward danger, ending its chances of winning.
The so-called Grand Challenge race is part of the Pentagon’s effort to cut the risk of casualties by fulfilling a congressional mandate to have a third of all military ground vehicles unmanned by 2015.
The military currently has a small fleet of autonomous ground vehicles stationed in Iraq and Afghanistan, but the machines are remotely controlled by a soldier who usually rides in the same convoy. The Pentagon wants to eliminate the human factor and use self-thinking robotic vehicles to ferry supplies in war zones.
On the Net:
www.darpa.mil/grandchallenge
URL: http://sfgate.com/cgi-bin/article.cgi?file=/n/a/2005/10/08/state/n144441D60.DTL