Shelley, the fully autonomous Audi TTS developed by Volkswagen and Stanford, has completed her Pikes Peak hill climb in a fairly respectable 27 minutes. An aggressive and skilled human driving the same car could have made it to the top 10 minutes sooner, but for a robot, this is certainly a notable performance. The course is a bit over 14 miles long, and climbs nearly 5,000 feet along the way. It’s a mix of asphalt, gravel, and dirt, and Shelley had to adapt to these different surfaces on the fly while driving as fast as possible.

Yeah, that doesn’t look as fast as possible… But you have to start somewhere, and seeing as Shelley is a robot, it’s fairly straightforward to just turn things up a few notches as you learn more about the potential (and limits) of the system.

Remember, Shelley is Volkswagen’s testbed to develop autonomous driving technologies that’ll be able to take over in the event of an emergency and pull some crazy stunt to keep you safe. The Stanford team is trying to figure out how close to the edge of performance Shelley can go without losing control, and the hill climb is only the first demonstration of that. Next, Shelley will robotically tackle some traditional paved tracks at high speeds.

[ Press Release ]

BotJunkie got invited to the official dedication of the Volkswagen Automotive Innovation Laboratory at Stanford yesterday. You remember VAIL, right? They’re the people who taught this car to park itself.

Anyway, this was our first invitation to an event involving a major head of state, so after we got through the Secret Service checkpoints and the camera sniffing dogs, we got to see the dedication ceremony and ribbon cutting by Angela Merkel, the Chancellor of Germany:

And here’s what was behind the ribbon:

As you can see, Shelley got a sexy new paint job for the occasion. At this point, she’s more or less all ready to take on the Pike’s Peak course autonomously… Next up are some high speed just-for-fun-and-breaking-the-robotic-speed-record runs out in the desert, and the duplication of a portion of the course on some flat ground without any cliffs to see how she does in the turns at full speed. The only major hardware concern is that Shelley currently does not have any obstacle avoidance sensors. So, if some hapless hiker decides to trek up Pike’s Peak at the same time as the robot does, there’s the risk of some hiker bits getting stuck to the front grille and ruining the aerodynamics of the car. One option is some form of telemonitoring, but they’re still working through ideas.

After the VIPs and their armored SUV convoy left, we had a chance to play around a little bit, and snagged ourselves a ride in Junior 3, VAIL’s self-parking Volkswagen Passat:

While we were sitting in the car for this demo, the way it’s ultimately designed to work is that you get out of the car, and tell it to go park itself using the iPhone app. When you want it back, hit the return button on your phone, and it comes back to you. It’s that easy. For more on the technology behind this, check out our post from last year on Junior 3′s autonomous parking capability.

Back when we broke the news of Stanford’s new robotic Audi TTS, Shelley, we didn’t get to see much in the way of video of the car in action besides a few brief teasers. Wired got a chance to ride along for a couple 40mph laps around a dirt track (::JEALOUS::) and brought back some video:

Shelley is on track to race up Pike’s Peak all by herself this September, but Stanford’s goal isn’t to create a robotic racer. Well, I mean, it is. But in general, they’re trying to figure out how to program a car to save your butt when something bad happens. By figuring out how to get a car to drive itself on the very edge of performance, eventually, your car will be smart enough to take over for you in an emergency and pull some crazy and nearly impossible stunt to keep you safe. As long as it’s a Volkswagen, of course.

VIA [ Wired ]

At the official public introduction to the Volkswagen Automotive Innovation Laboratory and Stanford’s new robotic car on Saturday, the VAIL showed off their latest foray into intelligent vehicle technology: an autonomous valet parking system. The system does exactly what you’re probably hoping it does: you get out if the car, tell it to park itself, and off it goes to do just that:

And of course, when you’re ready to go home, you just call the car back and it’ll be waiting for you. VAIL researchers are envisioning something like an iPhone app to control all this, but it doesn’t need to be any more complicated than a “park” button and a “return” button. The car does the rest, all by itself.

The most awesome part of all this is that the Volkswagen Passat used in this demo, Junior 3, is almost (almost) entirely stock, as far as the hardware goes. There are three different primary sensors in use: a front radar (which is available as part of Volkswagen’s adaptive cruise control system), a camera mounted in front of the rear view mirror (also available for night driving assistance), and a couple little off the shelf LIDAR units mounted on the sides. The LIDAR isn’t currently part of any option package, of course, but Volkswagen does offer other side looking sensors, like lane assist and blind spot detection. The only other major difference is the giant rack of computers in the trunk, but it turns out that the computer system is a standard package for Stanford’s autonomous vehicles, and the computer that comes with the car is actually capable of running everything. Bottom line is, we’re technologically more or less ready for autonomous parking already, with in production vehicles.

So what’s the hold-up? Well, the car currently can’t detect obstacles. Like, you know, people. There’s no reason it couldn’t do that with the current hardware, and that’s in fact the next step, but it’s still a huge liability issue that Volkswagen doesn’t want to tackle. The car also needs a detailed map of the parking lot, so you wouldn’t be able to just drop it off anywhere (yet). So when we first see this technology, VAIL envisions parking garages that are specifically designed for self parking vehicles. There would be a drop off area, and no pedestrians would be allowed in the garage, which wouldn’t need elevators, stairs, walkways, or even lights. This infrastructure isn’t ready yet, but the vehicle technology is here now.

It’s a little bit frustrating to robotics proponents like myself that in cases like these, it seems as if technology is advancing faster than society is prepared for. This is part of what VAIL is here for, though… To figure out not just the technology, but also tackle all of the related issues. There are a bunch of really smart people working on this stuff, and I have to say, if they continue making strides like this, we’re all gonna be worrying a lot less about driving in the near future.

BotJunkie was invited to Stanford on Thursday for a sneak peak at their latest robot car, from the family that includes Stanley and Junior. It’s an Audi TTS that’s been modified with sensors, GPS guidance, and a trunkfull of computers, but it’s not intended to drive you to work in the morning… It’s actually a race car, designed to push the limits of driving performance. Already, this TTS holds the unofficial world speed record for an autonomous car at 130 kph (edit- they meant to say 130 mph, which is a lot more impressive), but it’s capable of a whole lot more. Basically, Stanford is figuring out how close to the edge of control a car can be driven, and then they’re going to program their Audi to drive on that edge. They’ve set themselves a challenge of racing to the top of Pikes Peak sometime next year:

So what’s the point of all this besides being totally awesome? Simple: knowing how to drive a car to the limit gives you more options when it comes to things like accident avoidance. Most human drivers aren’t experienced enough (or have a fast enough reaction time) to take advantage of all of the potential escape routes that may be available when an accident is imminent, and research like this has the potential to teach intelligent cars how to save some of the 40,000 lives that are lost due to auto accidents every year.

We’ll have more for you early next week, after a demonstration of Stanford’s new car this weekend.

UPDATE: The car’s name is Shelley, after Mich├¿le Mouton, the most successful female rally driver ever and the first woman to win the Pikes Peak Hillclimb. She did it in an Audi, of course.

Stanford University has one of the most experienced, and successful, automotive research labs in the world. You may remember Stanley, the autonomous Volkswagen Touareg that won the DARPA Grand Challenge in 2005, as well as Junior, the autonomous Volkswagen Passat that was a runner up in the 2007 DARPA Urban Challenge. Apparently, Volkswagen Group is as impressed as everyone else has been, and, optimistic about the future of intelligence and autonomous vehicles, they’ve donated $2 million (plus research grants of $750k for 5 years) towards the construction and operation of a dedicated automotive innovation laboratory, VAIL (that would be, the Volkswagen Automotive Innovation Laboratory).

On Thursday, I met with Dr. Sven Beiker, the executive director of Stanford’s CarLab, and Dr. Burkhard Huhnke, the director of Volkswagen’s Electronics Research Lab in Palo Alto, to discuss some of the objectives of the new partnership. I asked them a few questions, starting with this one: if cars now have adaptive cruise control that keeps them from running into the car in front of them, as well as lane departure sensors that keep them from leaving their lane, how come I still have to pay attention when driving on the highway? The short answer is that the technologies aren’t quite refined enough yet, but the long answer isn’t a technical one, it’s a legal one: liability. Nobody has any idea what happens if something goes wrong and an autonomous vehicle gets in an accident, but companies are scared of it, which is why Panasonic, for example, isn’t producing its robot bed.

It’s issues like this that really define VAIL and make it different from other automotive research labs: at VAIL, they’re not just working on the cars themselves, they’re also working on everything that comes along with the development of intelligent cars: legal issues, social issues, business issues, even cultural issues… Not to mention more specific things like driver psychology. There’s a lot to consider, and that’s what they’re working on at VAIL. You know, besides all the car stuff. And there’s a lot of car stuff, too.

I also asked how Stanford was directing their research into autonomous vehicles now that there aren’t any more challenges from DARPA to provide a goal. The answer? More challenges! VAIL has identified three important areas of research, each of which has its own challenge:

Urban Environments
Challenge: drive from SF to LA, autonomously

User Interfaces
Challenge: design a one button interface that operates the entire vehicle

Up To The Limit
Challenge: race to the top of Pike’s Peak, autonomously

Sounds awfully exciting, and we’ll have more on that last one in a few hours… Stay tuned.

[Update: GetRobo has an interview with Stanford's Sebastian Thrun, where he provides some additional details on Urban Environments challenge to drive from downtown SF to downtown LA autonomously. Read it here.]

[ VAIL @ Stanford Press Release ]