• E-mail
• Print
• Comment
• Font Size
• Digg
• del.icio.us
• Discuss article

Stanford Unmanned Car Wins US Robot Vehicle Race

Posted on: Monday, 10 October 2005, 09:00 CDT

Stanford unmanned car wins US robot vehicle race

LOS ANGELES, Oct. 9 (Xinhua) -- An unmanned Volkswagen car refitted by the Stanford University Sunday won a robot vehicle race backed by the US Defense Ministry.

The Grand Challenge 2005 was held by the Defense Advanced Research Projects Agency (DARPA) to help design the unmanned battle vehicle in the future. As the final champion, the Stanford team will get a cash prize of 2 million US dollars.

The prize-winner car, dubbed Stanley, is a diesel-powered Volkswagen Touareg. Equipped with six Pentium M computers, a GPS system, and a drive-by-wire control set, the car was able to drive 200 km through the Mojave Desert between California and Nevada by itself in nearly seven hours.

Twenty-three automatic vehicles took part in the Saturday race, but 18 failed to complete the course because of mechanical failures or sensor problems. In second place was a red Humvee called Standstorm designed by Carnegie Mellon University.

The race is part of the military's effort to fulfill a congressional mandate to cut casualties by having a third of the military's ground vehicles unmanned in 20 years. A small fleet of automatic ground vehicles currently operate in Iraq and Afghanistan, but the machines must be remotely controlled by a soldier who usually rides in the same convoy.

The organizers and team members said improved technology and familiarity with the race allowed multiple robots to sprint across the finish line. In last year's Grand Challenge 2004, no robot vehicle finished the route under the rigorous desert environment.

Before Saturday's race, teams practiced their vehicles in various parts of the desert and even went back to the drawing board to improve their vehicles' artificial intelligence and sensing systems.

The vehicles were equipped with the latest sensors, lasers, cameras and radar that feed data to onboard computers, which helped them distinguish dangerous boulders from tumbleweeds and decide whether chasms were too deep to cross. The robot vehicles had to navigate a course designed to mimic driving conditions in Iraq and Afghanistan.

The course consisted of winding dirt trails and dry lake beds filled with overhanging brush. Parts of the route forced the robots to zip through three tunnels designed to knock out their GPS signals.

Source: Xinhua News Agency - CEIS

More News in this Category