In a race that began and ended in a casino parking lot and traversed 132 miles of desert southwest of Las Vegas on Oct. 8, the Stanford Racing Team's autonomous robotic car, Stanley, won big. The artificially intelligent car traversed the off-road course in a little less than seven hours, yielding both a $2 million payout and a lofty place in the history of robotics and technology.
“The impossible has been achieved,” said team leader Sebastian Thrun, an associate professor of computer science and director of the Stanford Artificial Intelligence Laboratory. Simply by finishing the course, Stanley and four other cars showed that machines can be made to drive safely and speedily over rugged terrain without any human help.
Stanley earned the prize and the glory in a contest sponsored by the Defense Advanced Research Projects Agency (DARPA) because the modified Volkswagen Touareg completed the rugged, off-road course with the quickest time, 6:53:58. Only four other cars of the 23 in contention managed to finish. Two cars from Carnegie Mellon University followed Stanley with times of 7:04:50 and 7:14:00. In a poignant victory, a team hailing from Metairie, La., finished in 7:30:16. Some team members had lost their homes to Hurricane Katrina and the entire team lost precious practice time because of the storm.
The last vehicle to finish—a yellow behemoth of a military truck named Terramax—did not do so until the morning of Oct. 9. DARPA officials forced it to pause repeatedly during its run, and eventually overnight, in part because of the breakdown of its human-driven “chase” vehicle. Because of the overnight delay, DARPA ultimately could not provide official times for all participants and declare Stanley the winner until almost 24 hours after it crossed the finish line.
Thrilled with Stanley's performance, the Stanford team members didn't seem glum about having to wait. In addition to dozens of Stanford faculty, students and staff from the School of Engineering, the team included a large contingent of engineers from supporter Volkswagen of America's Electronics Research Lab. Other key supporters included the Palo Alto venture capital firm MDV—Mohr Davidow Ventures, energy drink maker Red Bull and tech startup Android.
The thrill of the race
Without knowing whether it was the overall winner, the Stanford team Saturday still had the unique joy of being the first to celebrate finishing the course, and the group took full advantage. Stanley cruised across the finish line early in the afternoon. As DARPA Director Tony Tether waved the checkered flag, the team and the packed grandstand roared. Team members poured two enormous Red Bull cans containing ice water over Thrun's head and shortly after, Thrun and postdoctoral researcher Mike Montemerlo were hoisted aloft in a sleep-deprived frenzy of jubilance and relief and riding on the shoulders of their teammates.
“We had a good day,” Thrun said playfully after a throng of media perched on a nearby platform pressed him to say something. In short order he was bobbing in a sea of interviewers, with fuzzy boom microphones floating over his head like a swarm of flying squirrels.
Stanley was the second vehicle to leave the starting line, five minutes after Carnegie Mellon University's H1ghlander Hummer and five minutes before that university's second entry, Sandstorm. Sandstorm was the most successful robot during the first Grand Challenge last year, when it traversed less than 8 miles of a 170-mile course.
For most of the race Stanley trailed CMU's hulking red H1ghlander until just past the 100-mile mark, when Stanley overtook the lagging Hummer. By erasing CMU's head start, Stanley vaulted into front-runner status.
It was not much later that Stanley wowed the crowd again when it headed into Beer Bottle Pass, a treacherous and windy mountain pass with sharp turns and sharper cliffs along one side of the road. Via a DARPA live video feed from the entrance to the pass, spectators could see Stanley drive into view, rounding the corner smoothly, as if the robot had not only artificial intelligence but real confidence.
Smart brain, strong body
Stanley got that smart by learning during countless hours of desert testing in the months leading up to the race. Equipped with a wide variety of sensors and a heap of custom-written software including machine learning algorithms, Stanley grew smarter with practice. Eventually it became a master of finding the path, detecting obstacles and avoiding them while staying on course.
Applications of the technology could range from the development of unmanned ground vehicles for dangerous military missions to driver assistance systems that keep civilian drivers, passengers and pedestrians safe.
Those applications, however, will have to wait. After a grueling 18 months of development, culminating in a 4 a.m. wake-up call to start Saturday's race, Thrun said, “The next challenge is to get some sleep.”
Cite This Page: