Racing team was Bryan Salesky, who ran the software team. Salesky had been working at a Carnegie Mellon Robotics Institute spin-off called the National Robotics Engineering Center. Whittaker cofounded it in 1994 with $2.5 million in funding from NASA, to commercialize the technology created at CMU’s robotics department. The place is located in a nineteenth-century former iron foundry in the Lawrenceville area of Pittsburgh, on the shores of the Alleghany River. Its job was to partner with such companies as John Deere and Caterpillar to develop commercial projects like a self-driving harvester or an autonomous excavator. Shortly before work began on the Urban Challenge, Salesky was working on an autonomous navigation system for the U.S. Army. But the project wasn’t going anywhere, and Salesky was becoming frustrated with the slow rate of progress that he thought endemic to working directly with the government.
Just twenty-six years old, Salesky was, on the surface, a bit of a strange fit for such a senior position in Whittaker’s crew. Guys like Spencer Spiker, Kevin Peterson and Chris Urmson are equally at ease with welding torches and air impact wrenches as LIDAR sensors. Salesky is more at home in a computer lab than a mechanic’s shop. But he hit it off with Whittaker’s guys, particularly Urmson, likely because the two men shared a Midwestern distaste for pretense.
In 2006, as teams across the country geared up for the Urban Challenge, other figures who would become main characters in the mobility disruption began bumping up against one another. For example, Dave Hall and Anthony Levandowski. Hall, then fifty-five, was an inveterate tinkerer and self-trained inventor. He first gained notoriety in the world of high-end audio, having famously built his first amplifier at the age of four. Living then in Connecticut in a family with lots of technical heritage—Hall’s father designed atomic power plants, and his grandfather was a physicist—he already knew how to read electronics schematics when he went to college for mechanical engineering. While there he invented a version of a tachometer, a device that measured the rotational speed of things like wheels and propellers. Licensing the patent from that invention gave him enough income that, out of college, rather than getting a job, Hall moved to Boston to set up his own little technical shop. For a time, he lived by monitoring the world of government research contracts and building prototypes for the big defense firms. In the seventies, Hall invented a subwoofer, a type of speaker that provided clearer bass tones in stereo systems. With $250,000 lent to him by his grandfather, Hall moved to California and set up a company with his brother-in-law to manufacture the subwoofer.
That was in 1979. By the turn of the millennium Hall’s company had sixty employees and a few million dollars in annual sales. Hall made a good living, but he was bored. Building remote-controlled robots that competed to “kill” other machines on BattleBots, the television show, occupied him for a time. (One of his constructions, Drillzilla, relied on the blade from a circular saw as a weapon.) He competed in the first DARPA Grand Challenge with a Toyota Tundra entry notable for its use of a stereoscopic camera setup, rather than LIDAR, to sense the road. In the interim between the first and second races, Hall became fascinated with LIDAR’s potential. Tinkering as he was wont to do, Hall determined a way to cram sixty-four lasers on a single device, more than anyone ever had before. But the big innovation was that Hall’s LIDAR spun. Previous laser range finders had stayed static, shooting lasers to get a limited field of view, a little like the way a human sees the world only in front of his or her eyes. By mounting the device atop the vehicle and engineering the LIDAR so that it revolved ten times a second and 360 degrees around, Hall’s mechanism provided a complete portrait of the area around the vehicle. The new technology in effect created a three-dimensional scan of the world. It helped Hall’s robot progress along the second Grand Challenge route faster than most of its competitors, although a mechanical failure prevented it from finishing the race.
Once DARPA announced the Urban Challenge, Hall saw that his LIDAR would be even more valuable, because the 360-degree field of view that his device provided would help the robot detect oncoming vehicles in all directions. So he set up a manufacturing operation within his subwoofer company, Velodyne, and hired as a salesman one of the brightest minds from the first two races. The person he hired was Anthony Levandowski, the thin, six-foot-seven-inch UC Berkeley grad student behind the first challenge’s Ghost Rider motorcycle.
Which is how Levandowski came to be in Pittsburgh at the old Coke Works test facility—now referred to by most as Robot City—one day in late 2006, about a year before the race. Tartan Racing had bought one of Velodyne’s LIDARs—a significant investment at about $75,000 a pop—and Levandowski flew out to Pennsylvania to help Urmson and team install it. He set it alongside the other sensors that sat on the metal latticework on the roof of Boss, the Chevy Tahoe. Levandowski anchored down the sensor, activated it, and the numerous computer scientists and engineers who had gathered to witness this moment watched as the device generated the rotational momentum it required to work properly. On a nearby computer screen appeared the ghostly dot matrix that formed the device’s output. It was impressive—a million data points that could recognize up to 120 yards away everything from parking curbs to people’s faces.
Then something came loose on the LIDAR, and the rotational momentum flung a counterweight across the room—hard. Only luck prevented the wayward schrapnel from injuring someone. There was a shocked silence, and then came Levandowski’s voice.
“We’ll fix that,” said the gangly engineer.
Levandowski would become well known years later as the central figure in an important lawsuit between Waymo and Uber. Brilliant and ambitious, Levandowski demonstrated a tendency to get himself into situations others would characterize as conflicts of interest. He was often in demand at the smartest, highest-performing groups working on the most intriguing projects. Velodyne would ultimately sell its LIDAR to at least seven of the Urban Challenge competitors, including two each to the Carnegie Mellon and Stanford teams. Around the same time Levandowski was selling this integral piece of technology to as many teams as he could, however, he also was advising the Stanford team for the Urban Challenge. There’s no indication he did anything unethical at this point; Stanford apparently knew about his role with Velodyne, but it is easy to see how this activity could be perceived as a conflict of interest. And just to make all this even more incestuous, Google’s Street View played a key role in how it all went down.
By 2006, Thrun was itching to do a start-up. The atmosphere of Silicon Valley played a role, as did the Stanford AI prof’s developing relationship with Google cofounders Larry Page and Sergey Brin. But what should the start-up do?
Thrun was fascinated with the data that he and Montemerlo had collected while testing Stanley for the second Grand Challenge. Teaching Stanley to drive, motoring in the Touareg around the Mojave Desert, Thrun and his teammates had struck on the idea of fixing cameras, pointed in several different directions, on the roof of the vehicle. Not as sensors—rather, the imagery helped them re-create the circumstances that triggered bugs in Stanley’s programming. Over time, Thrun realized how interesting it was to just go through the imagery collected by the multidirectional rooftop cameras.
That year, Thrun happened to be teaching a class at Stanford about computer vision. He assigned the class’s most brilliant student, Joakim Arfvidsson, the task of creating a program that could easily stitch together the camera footage in such a manner that it provided the illusion of an unlimited field of vision, which, Thrun figured, would provide the impression of actually being at the original location. “Joakim recorded a street in San Francisco,” says Thrun. The resulting computer program gave the feeling of actually standing on the street. “You could look up, look down—it was completely amazing.”
Thrun gave Arfvidsson an A-plus in the class. During the summer of 2006, alongside his oversight of Stanford’s Urban Challenge team, Thrun assigned a second team the task of building a version of the street-visualization software that could
