Stanford's Stanley wins DARPA Grand Challenge

tonyquan writes "DARPA has just announced that Stanford's "Stanley" autonomous ground vehicle has won the Grand Challenge, a $2 million contest for driverless vehicles over a 132 mile course in California's Mohave Desert. Stanley's winning time over the course was 6 hours, 53 minutes and 58 seconds, for an average speed of 19.1 mph. Second was Carnegie Mellon's Sandstorm (7:04:50), third went to another CMU vehicle "H1ghlander" (7:14:00) and fourth to the Gray Team's KAT-5 (7:30:16) More info from DARPA."

so wait..

[molo]

Last year they had NO vehicles even make it out of the obstacle course.. and this year they had several vehicles actually complete the desert course?? What gives?

-molo

Good news

[Data Link Layer]

I honestly didn't think this contest would ever be won. Maybe in 20 years we can have auto driving cars that can make it so there is next to 0 car accidents.

Patriotism... sigh

[Anonymous Coward]

DARPA Grand Challange - Harnessing American Ingenuity [grandchallenge.org] ... as it turns out, the leader of the winning Stanford car team is a German [stanford.edu].

19.1?

[Donniedarkness]

19.1 mph? I mean, congradulations to the winners, and I'm sure there's a reason for the speed to be so low...but can anyone explain what that is to me?

I mean, I can understand the fastest solar-powered vehicle going just over 100..... but what is the reason for these driverless vehicles? I understand that they navigate these things by themselves, but is there any other reason? Is the track pretty much nothing but ridiculous curves or something?

Re:so wait..

[dohzer]

I don't think it shows a great advance in robotics and A.I. (although that is partly responsible), more just an advance in how they handled the DARPA Grand Challenge. If DARPA gave them a different challenge of similar difficulty, it might take them a few years to finish again.

Re:Good news

[freg]

I'm fully confident in our ability to make good software to meet ever increasing challenges, even to the point that we can have smart cars who take over driving if the driver is incapacitated. But to have a car drive me around on its own free will is a level of trust I wouldn't leave with Microsoft or any car manufacturer around today.

Re:19.1?

[Yvanhoe]

In fact, one member of the team explained in a conference that they aimed to finish the race. Which was already a great achievement. DARPA has put a time limit on the race and Stanford chose a speed which was the lowest possible (to lower risks of accidents) while still providing a secure margin for unexpected events. (From what I remember, they planed to have an average of 30 mph so they race must have been thougher than they thought)

If there is a Grand Challenge in 2006, it will probably look more like a race, now that everyone knows it is possible.

Re:so wait..

[Zathrus]

There are several factors here. First and formost, the vehicles are more capable. The software is vastly better and the hardware is somewhat improved. Did you think that they've been sitting around doing nothing for the past 17 months? They've been working on improvements since the last challenge, and they've spent a lot more time actually testing their vehicles in desert terrain.

There are some people who say that this year's course is far easier than last year's. I don't know myself -- I'm not involved with any of the teams and I don't have detailed knowledge of the courses. But there has been some commentary by those involved to this effect, as well as from bystanders. One huge difference is that the most difficult part of the course (Beer Bottle Pass, a narrow road with a steep drop off on one side) was at the end of the course this year, while the equivalent part was near the start last year. Stanford's leader is quoted as saying something to the effect that if they'd inverted last year's course then a lot of cars would've gone much further, even if none of them finished. The complete lack of media attention last year may have been one reason why DARPA swapped the course around -- it's rather anti-climactic to write about a race where the best racer hardly even got off the finish line and leads to the kind of stories DARPA really doesn't want to see (waste of taxpayer money, will never work, etc.).

In any case, given that less than 25% of the vehicles finished, I'd hardly say that it was a trivial thing to do. It's still amazing. Congrats to those who did, and to all of those who participated for that matter -- it's quite an accomplishment, even if there's a long way to go still before this is really usable in a real world environment.

Re:Good news

[October_30th]

But to have a car drive me around on its own free will is a level of trust I wouldn't leave with Microsoft or any car manufacturer around today.

I would certainly let a computer drive me around in a car -- whenever I fly somewhere I'm already trusting my life to a computer.

Modern commercial passanger airplanes come with fly-by-wire flight control system. That means that the onboard computers essentially decide whether or not to adjust the flight surfaces according to the pilot's wishes -- if the computer system gets fuxored, there's no way to fly the plane manually. Doesn't seem to be that big a problem.

Re:How few remain

[knix]

I believe that team, Team ENSCO just blew a tire. They were doing very well and on pace to win I think until they had a mechanical malfunction, not a computer malfunction.

Gray Team?

[mikeee]

Anybody know anything about the Gray Team and their bot? Their 4th-place finish seems to be far the best of any of the 'low budget' teams; about all I can find is that it was sponsored by The Gray Insurance Co., that their IT department (and founders who were bored of spending money on yachts?) worked on it, as well as some Tulane students, and that it was a Ford Escape (small SUV) hybrid.

They don't seem to have a webpage for the team...

Re:Patriotism... sigh

[Anonymous Coward]

"The only reason the VW vehicle finished, and finished first, is because the team from Stanford is made of briliant people. I'm sure they would have won with a Jeep, Hummer, Ford or whatever."

Well, probably, but it sure made it a lot easier that they were given plenty of VW's to work with, along with VW engineer's to boot. While other folks had to design exterior actuators for throttle / brake / steering along with feedback sensors and the like, Stanford could simply tie into the built in vehicle computer and harness the drive-by-wire features. And unlike others who had vehicle computers on board, they didn't have to reverse engineer the vehicle computer. Now again, those guys were smart and they still had a ton of things to tackle (like the rest of us), but they got half of the equation handed to them. And don't think that VW just donated a single vehicle. Like Red Team (AM General and GM in their case) they were sporting multiple vehicles. In fact they had another robot identical to Stanley (except for smaller computers on board) that they just used for spare parts. Must be nice.

I give props (oh yes I said it) to grey team. They probably dumped money into their vehicle, but I am willing to bet it is a small fraction compared to CMU and Stanford.

As with anything, knowledge is behind everything, but money sure makes it easier.

Re:Stanford + Volkswagen

[Anonymous Coward]

It actually did say "Drivers not required" around Stanley's wheel wells, along with the VW logo.

Sensors

[maximthemagnificent]

That makes sense. I used to do some work with mobile robots at Brown University's AI lab, and I found that the difficulties were all about sensors. Once you could turn the physical obstacles into data abstractions and once you knew where the robot was in relation to them, the algorithms were pretty darned easy. I used to walk around pretending that I only had the information available to the robot and see how I did, with human intelligence, at avoiding obstacles. Our vision system was very slow and took 3 seconds per frame, so I'd close my eyes and blink them open for an instant every three seconds. It was very hard. Moving slow helped a lot, of course. Of course we were running on a 486 back then...

Re:Good news

[lowrydr310]

Is your dune buggy street legal?

It's funny how our laws are written. I know a guy who built a Lamborghini Countach kit car out of some steel tubing, a pre-made fiberglass body, and an engine that isn't even close to passing federal emission laws. He had no problems getting it inspected, registered, and getting a license plate for it. Custom choppers are the same: It's easy to weld some tubing together and slap on wheels, an engine, and a transmission and you're out on the streets in no time!

I want to import a new Toyota Hilux diesel pickup because a compact diesel pickup truck isn't available in the USA. Unfortunately I'm not allowed to do this because it hasn't been tested against US crash standards and the engine isn't EPA certified (despite being less polluting than just about any diesel engine currently offered in the USA).

Team Grey is the Real Winner

[humankind]

When you look at the results, and you see two colleges with virtually unlimited resources and millions of dollars spent on their vehicles, huge corporate sponsors and engineers at their beck and call from Boeing to Catepillar, who finished, and then this dinky little Team Grey from a suburb of New Orleans, with a splintered development team as a result of the Hurricane Katrina disaster, and they FINISHED just behind the big guys, leaving other heavily-funded vehicles in the dust.

Relatively speaking, a small indy group, even if their time was a tad slower than CMU or Stanford, essentially put those three teams to shame when you compare the resources they had available to them.

The real story here is who is behind the Grey team's car. It must be a far superior design than either CMU or Stanford's considering the limited resources and experience they had in addressing the challenge.

Re:cmu won all three

[epgandalf]

I haven't heard too much about bad blood between Robotics Faculty at CMU. I do know that Red Wittaker is a real slave driver. Someone I know quit working on Sandstorm because he didn't like Red. Another person I knew kept working even though he knew that he wouldn't be sleeping at all for about 2 years.
I also know that there's some bad blood between Illah Nourbakhsh and Howie Choset. Illah's a great guy and Howie is a real asshole. Anyone who's taken robotics classes at CMU knows what I'm talking about.