Autonomy: The Quest to Build the Driverless Car - And How It Will Reshape Our World. Lawrence Burns
autonomously complete a DARPA Grand Challenge. Tether himself waved the checkered flag as Stanley passed the finish line.
Sandstorm launched at about 6:50 A.M. The robot rumbled out of its chute with its characteristic diesel knock. It made it through underpass one, two and three even though a software bug prevented the LIDAR from detecting the walls. In fact, it performed flawlessly until 6 hours and 30 minutes into the race, when it just scraped a canyon wall in the narrowest section of the route. Sandstorm drove over the finish line 7 hours and 4 minutes after it left the start chute—a variation of only about 1 percent from what the engineers had asked of the robot. It had done exactly what it was assigned to do in remarkable fashion, placing second, by time. And in third, limping into the finish, was H1ghlander, with an elapsed time of 7 hours and 14 minutes, or 55 minutes longer than the time the Red Team had set for it. All told, five robots finished the course.
Thrun was elated, of course. Later that day he and his team gathered onstage to receive a check for $2 million. But what was just as gratifying was the way the victory felt like a validation of the whole robotics field. More than a decade later, public attitudes toward roboticists have markedly changed. Back in 2005, robotics was associated in the public imagination with projects like Thrun’s 1998 Minerva museum tour guide—as novelties, curiosities that had little effect on anyone’s day-to-day lives. A self-driving car was different. Sure, the second DARPA Grand Challenge was a controlled scenario separate from the actual world because nothing else on the course was allowed to move. But it nevertheless represented a step toward actual robot cars, which everyone realized would, if they ever became a reality, transform lives. Standing up before reporters frantically scribbling down their words, photographers and videographers capturing their images and a crowd of people cheering their accomplishment, Thrun and his teammates relished the attention as validation that the world might finally recognize the potential of their chosen field.
Thrun was magnanimous in his victory. “It’s really been us as a field that were able to develop these five vehicles that finished the race,” Thrun said. “It’s really been a victory for all of us.”
Few on Red Team felt that way. It stung that they had devoted months to test Sandstorm and H1ghlander on some of the toughest roads on the planet—and then discovered on race day that the course was easier even than the well-graded roads that had marked the first Grand Challenge. It stung, too, that based on its performance in the qualifying events, a fully functioning H1ghlander would have taken the race. And it stung that, had Red Team’s leadership allowed Sandstorm to perform to its abilities, rather than playing it safe and limiting its speed, the older Red Team robot also might have beaten Stanley. Thrun acknowledged both facts. “It was a complete act of randomness that Stanley actually won,” he said later. “It was really a failure of Carnegie Mellon’s engine that made us win, no more and no less than that.”
“It was very much a winner-take-all event,” Urmson recalls, more than a decade later. “It sucked. There was no prize for second. This had been three years of people’s lives at this point. It was brutal. I remember seeing Red afterward, and that was the most distraught I’d ever seen him.”
“It’s right up there with the worst shortcomings of one’s life,” Red says, assuming full responsibility for what he still regards as a defeat. “I let a team down. I let a lot of people down. And in a lot of ways, in a bigger way, I let down a community and a world that didn’t see the best of the technology and the movement and the vision of what things could be.”
“It was a strange feeling,” Urmson says. “It was a day that five vehicles did something believed to be impossible. Our team had pulled together and achieved the impossible. We’d done the impossible—and yet we’d lost.”
HISTORY HAPPENS IN VICTORVILLE
An introverted engineer looks at his shoes when he talks to you. An extroverted engineer looks at your shoes.
—UNKNOWN
The second DARPA Grand Challenge was successful on numerous fronts. The $2 million prize was perceived as a cost-effective way to spur progress in the field of mobile robotics. The large number of entrants, the public enthusiasm and media attention for the challenge event, and the fact that the race resulted in five vehicles that could travel 132 miles through a difficult desert landscape all contributed to a perception throughout the military of money well spent.
But inside DARPA, there remained a sense that the mission hadn’t yet been accomplished. No team had constructed a robot that could navigate the chaotic urban environments of Iraq or Afghanistan. Could a similar event spur the robotics field to make more progress?
Thus came the idea of the DARPA Urban Challenge, which would be staged in a city landscape, rather than a desert. Tether announced the event in April 2006, setting the date for November 3, 2007, and soon saw a globally diverse field of eighty-nine teams registered to compete, less than half the number of the previous contest, perhaps because this version of the challenge was perceived to be much more difficult.
Some of the format changes seemed designed to stifle the approach that Red Whittaker’s team had pioneered in the first and second races—the one that had used a group of human map techs to essentially pre-drive the race route for the robots. DARPA planned to sprinkle the course with moving obstacles, namely, other automobiles driven by Hollywood stuntmen and professional drivers. As well, many different teams would be navigating the urban environment simultaneously.
The key to this event was satisfying the objectives DARPA wanted the robots to execute throughout the course—and DARPA wouldn’t disclose that information until five minutes before start time. In fact, DARPA was so secretive in the lead-up that for a time they even declined to disclose which state would host the competition. “We knew it was going to be cold outside, so they’d probably do it somewhere that had warm weather,” recalls one participant. “But that was the only thing we knew … They didn’t want anyone pre-programming the system. They wanted some element of intelligence and route planning and control in the robot.”
The rules required the robots to drive sixty miles in six hours through an urban environment while obeying the rules of the California Driver Handbook. The challenge would require that the robot navigate a standard North American parking lot well enough to be able to maneuver into an available space. While neither pedestrians nor cyclists would be allowed on the course, the robots would have to navigate one of the most difficult elements of driving for human operators—deciding how to proceed through an all-way-stop intersection where other drivers have arrived at about the same time.
“The Urban Challenge was much harder, in terms of what the vehicle needed to do,” recalls Urmson. “The algorithmic steps we’d taken for the first two challenges were predicated on the world not moving. Once other things start moving, it’s nowhere near as easy.”
The inspiration here was to automate the operation of battlefield convoys. A military truck in Afghanistan or Iraq is transporting food to a distant village. An IED explodes somewhere ahead, and the automated convoy would have to navigate around the disturbance without running into any medics, civilians or other members of the convoy. That’s about as dynamic an environment as is possible.
There was no question that Carnegie Mellon would enter the race. There was some question whether Red would lead it. Previously, Whittaker’s Red Team had been a take-all-comers effort populated by undergraduates, volunteers, grad students or the odd full-time employee of Whittaker’s Field Robotics Center. But this time around, DARPA was pledging a million dollars of research funding to a selection of the best-run teams. Carnegie Mellon was one of the recipients. As well, the stakes felt higher this time. There was the $2 million prize. In addition, Carnegie Mellon was competing for its reputation as the nation’s top robotics center. It needed to win. “That’s a lot of money and so [the university administration] wanted to make sure we could win it,” Urmson recalls. Ultimately,