Inside DARPA's Robot Race

Used to be a lot slower. by rob_squared · 2006-03-29 05:31 · Score: 2, Interesting

I remember an old nova special about self-navigating robots, and at first it took about a day to cross a room.

But mostly these robots depend on the assumption that everything remains still.

--
I don't get it.

Re:Used to be a lot slower. by +InvaderSkoodge · 2006-03-29 06:07 · Score: 1

"But mostly these robots depend on the assumption that everything remains still."

But "Stanley" did pass whoever had been in first place while that vehicle was moving.
Re:Used to be a lot slower. by slcdb · 2006-03-29 07:29 · Score: 1

Yep. That was a big question mark in my mind as I watched the show last night. As soon as the first vehicle left the gate, I had to wonder, "What's going to happen if one of them catches up to the vehicle in front of them?" Passing a moving object is not like avoiding stationary objects -- which is all the qualifying course contained.

Surprisingly, Stanley seemed to have no trouble at all passing Highlander, but I wonder how much of that was just pure luck (and the fact that it happened during a stretch where the trail was much wider than in many other spots).

--
Despite what EULAs say, most software is sold, not licensed.
Re:Used to be a lot slower. by +InvaderSkoodge · 2006-03-29 07:42 · Score: 1

"I wonder how much of that was just pure luck (and the fact that it happened during a stretch where the trail was much wider than in many other spots)."

Yeah, it would have been interesting to see what would happen if Stanley had caught up to Highlander at a spot where there wasn't room to pass. Would it believe that Highlander was a stationary object and stop moving, thinking there was no way to proceed, or would it just have followed behind Highlander?

I understand that it is not within the spirit of this competition, but I also have to wonder if it would have been possible to program in a little "offensive" driving where Highlander could have somehow prevented Stanley from ever passing.

Seen it by Moby+Cock · 2006-03-29 05:31 · Score: 5, Informative

PBS broadcast that show last night. While I realise that is is a little 2001 to actually watch a program when it is braodcast, I did. And I really enjoyed it. I am hardly current on the status of autonomous robotics and I was pleasantly surprised by how far along the technology is. 130 miles through the dessert using only GPS and local sensors is a pretty amazing feat, and that course was tough. It features mountain switchbacks, tunnels and other hazards. If you even have a passing interest in robotics I recommend watching the show.

Re:Seen it by Random+Utinni · 2006-03-29 06:25 · Score: 2, Insightful

It was a good show. One nifty bit of engineering from the Stanford team was to overlay a video camera image over laser-generated map, use a color-matching system to determine what colors of the video were level and safe to drive on, and then extrapolate what areas of the video image were safe.

The main difficulty that I see, going forward, is that the laser-rangefinder systems that these robots all relied on all function by looking for obstacles and attempting to avoid them. They can spot vertical anomalies, such as hay bales, other cars, poles, etc., but that's about it. None of these systems can actually determine road conditions. A rangefinder can't tell if the smooth road up ahead is actually a ginormous pothole filled with water, or if the road ahead is covered with a thick layer of ice. All it knows is that the area ahead is flat and clear... accelerate at will. Under such circumstances, any of these robots would run into serious difficulty, even if the course were relatively flat and straight.

As impressive as driving a windy road autonomously is, there's a long way to go before these things see commercial, or even military, use.
Re:Seen it by Manchot · 2006-03-29 07:05 · Score: 1

I agree. It was a very good program, made even better by the fact that it's narrated by John Lithgow. (I'm surprised that no one has mentioned this yet.)
Re:Seen it by dw604 · 2006-03-29 07:13 · Score: 1

Since you said "windy" I read it as "windy" (ie. gusts of wind). I wonder how well these things can compensate for THAT. I bet they have a long way to go as far as "feeling" the grip on the road and drag/body roll of the chassis like a human does.
Re:Seen it by jandrese · 2006-03-29 09:30 · Score: 1

Worse, the MITRE team was killed by the wind, or more accurately by dust devils. they kept having dust devils blow in front of the sensors, causing the vehicle to make an emergency avoidance manuver (oh no! Something jumped in front of me!). One of these manuvers left the vehicle in a bush, unable to move because it couldn't find a clear way out of the bush.

--

I read the internet for the articles.
Re:Seen it by vistic · 2006-03-29 09:35 · Score: 2, Interesting

I caught the show yesterday also.

I was really happy Stanford won the competition. The "red" team with two entries (from Carnegie Mellon?) also finished but were behind on time... the thing is though not only was Stanford's win absolute, they also did it much "smarter".

Stanford took an approach of focusing on software, to make their vehicle more smart. They gave it the course, but left it up to the vehicle to decide how fast to go and the specifics of how soon to turn, etc.

Meanwhile Carnegie Mellon took the approach of focusing on hardware, and it took them something like 2 hours to go over the course and specifically map out a path for the vehicle to follow and the speed it should take (as opposed to I think they said 27 minutes to just give the course details to the Stanford vehicle). Carnegie Mellon had a team of at least a dozen grad students figuring it all out.

So I was much happier with Stanford's win, it seemed like more of an accomplishment.

Stanford 0wn3d Carnegie by Anonymous Coward · 2006-03-29 05:31 · Score: 2, Interesting

Unlike Carnegie's "H1ghlander" and "Sandstorm", Stanford's "Stanley" VW Touareg had no fancy motion compensated sensors and the team didn't flesh out the race course with more GPS data and tell the vehicle how fast it could drive in certain areas. Stanley's software did all that on the fly.

Also, the SuperDAD Toyota pickup looked like it had a tenth of the tech of Stanley but it was doing almost as well. If only the laser sensor hadn't detached itself from the roof.

Re:Stanford 0wn3d Carnegie by lo0ol · 2006-03-29 06:10 · Score: 1

Yes, since one race really says a lot about which one is better. Let's look at the situation a few years from now and then make judgements. After all, CMU beat everyone the previous year. Plus, Stanford's team was basically a CMU team if you look at the composition of the team. Plus, using "0wn3d" at all was so 1997.

Who cares though. Look at the improvement from two years ago to this past race. Now we have (forgive me if I forget the details) 5-6 vehicles that finished the race? That says great things about the development of robotics in general.

--
Good-Tutorials
Re:Stanford 0wn3d Carnegie by Anonymous Coward · 2006-03-29 06:25 · Score: 0

>>Yes, since one race really says a lot about which one is better.

Stanley walked (drove?) away with a $2 million check. No one else did. Guess they were better.

>>Stanford's team was basically a CMU team if you look at the composition of the team.

But it was obvious that the strategies used were completely different: micromanagement of massive amounts of data vs improved interpreting of a smaller set of data.

>>Plus, using "0wn3d" at all was so 1997.

I'm guessing this is some sort of subtle (yet lame) insult. Using "so 19xx" is something high schoolers say. Go back to study hall.
Re:Stanford 0wn3d Carnegie by Anonymous Coward · 2006-03-29 06:54 · Score: 2, Funny

Plus, using "0wn3d" at all was so 1997
1997? Hell, that term has been in use since 1337!
Re:Stanford 0wn3d Carnegie by Anonymous Coward · 2006-03-29 08:38 · Score: 0

You obviously weren't paying attention when Stanley passed Highlander *at speed*.

I'd call that pretty much "owned" in a race. The cherry on the top is that Stanley was the only robot that didn't contact a single obstacle during the trials. Owned? Yes.
Re:Stanford 0wn3d Carnegie by Quixote · 2006-03-29 17:18 · Score: 2, Insightful

True. There was so much hype surroung "Red Storm" and how it would p0wn the rest of the field before GC-1. Then during the trials, their Hummer tipped over because it took a curve too fast (d'oh!! where's the linkage between the wheel turning system and the speed system?). And in the race, it almost caught fire because 1 wheel got stuck and the other spun freely; the system controlling the engine just kept increasing the RPM, with the eventual result that the tires melted and flew off, and the controllers had to hit the emergency stop.
It was clear then that the CMU team was loaded with tech, but lacked smarts. They were trying to bruteforce the course (they sent teams to navigate every possible path in the race area with a GPS, so they could map out obstacles beforehand. Geez! talk aboout spare no expense!).
The most impressive, of course, was DAD. With almost nothing but a pair of cameras for stereo vision, they were able to achieve so much in their garage.

Great show but... by SeeMyNuts! · 2006-03-29 05:35 · Score: 5, Insightful

it is interesting just how involved the contestants are. This contest is their life. They mentioned several times in the show how many months of long workdays they spent to build and program these cars. And, then, who owns the work? Do they at least get patent recognition on some of the innovations? Some of the software they talked about was truly seriously cool stuff.

Sidenote: One hour of Nova or Frontline is like watching 5 days worth of "learning" and "discovery" shows elsewhere. It's amazing how good some of these shows are.

Re:Great show but... by Machina+Fortuno · 2006-03-29 05:53 · Score: 2, Interesting

I love PBS documentaries man. You can learn sooo much from them in a nice little narrated package.

Maybe all these guys are geniuses and get grants to work on the stuff. Maybe university supported or something like that. Or! They make their money in half a year, and build robot cars the rest of the time.

--
...
Re:Great show but... by CXI · 2006-03-29 05:55 · Score: 2, Informative

They'll get patent recognition if they, you know, filed any patents. These teams can do whatever they want with any innovations they make. Many of them, especially the school based teams, operate under grants from other agencies which might have limitations on who owns or can patent what. However, each team makes the choice about where their funding comes from and what strings are attached to it.
Re:Great show but... by sentanta · 2006-03-29 05:56 · Score: 1

I think most of the contestants are sponsored by the big automakers - so Stanford's team got funding/parts from Volkswagen. As to who owns the patents? Wouldn't Stanford?

--
The Big Yuan - tracking mainland China
Re:Great show but... by Moby+Cock · 2006-03-29 06:05 · Score: 0

Sidenote: One hour of Nova or Frontline is like watching 5 days worth of "learning" and "discovery" shows elsewhere. It's amazing how good some of these shows are.

Hear hear!
Re:Great show but... by Machina+Fortuno · 2006-03-29 06:10 · Score: 1

I would figure that any patent disputes would be settled in the contract though. Like...

"Because you are sponsored by VW, all respective research and technologies are ours, muahahah"

or vice versa, or... something like that. There would have to be a pretty clear relationship between the sponsor and the grunt, whether it be royalties or whatever

--
...
Re:Great show but... by Darth_brooks · 2006-03-29 06:37 · Score: 1

Most (or many) universities make you sign away your rights to a patent for something you created on "university" time with university funds and equipment. It's one of the many political battlegrounds on campus in higher education these days. "How do you define what was done on whose time?" "Just because I work for the university doesn't mean that everything I do belongs to the uni", etc. etc.

I would wager that Stanford would be on the high ground if it came down to a legal battle.

--
There are some people that if they don't know, you can't tell 'em.
Re:Great show but... by Anonymous Coward · 2006-03-29 06:42 · Score: 0

Hear hear!
I'm deaf you insensitive clod!
Re:Great show but... by Anonymous Coward · 2006-03-29 07:25 · Score: 2, Interesting

To answer your question regarding who owns what. I can't speak for the large University teams because they are just in a different universe as the rest of us were. Most teams didn't bother filling out patents because we were all just too damn busy. What we do rely on is our IP though. I was on a finalist team and we did write some pretty cool software that we are trying to do some stuff with on another project now. We own all the code (we wrote it). CMU and Stanford are a different beast altogether. I assume the university owns much of the code that they wrote. But really that's not a big loss for them, if it wasn't for the threat of DARPA taking contracts somewhere else that Stanford and CMU already had ( before the race was ever announced ) they wouldn't have even competed. They were competing to save their contracts, not for the money or to do something *neat*. Of course I am a little biased. I was on a small team with the only funding coming from our own pockets. We worked our day jobs and spent all night working on the vehicle. Even during the qualifying we were soldering boards in the motel that night. I'll admit, I wish I had a team of VW engineers working on a vehicle they designed and giving us all the I/O info needed to use the onboard vehicle computer directly.

Hmm by ackthpt · 2006-03-29 05:35 · Score: 3, Insightful

After watching Why We Fight, I'm not so keen on something like this anymore.

--

A feeling of having made the same mistake before: Deja Foobar

Re:Hmm by CallFinalClass · 2006-03-29 05:45 · Score: 1

Please elaborate.
Re:Hmm by ackthpt · 2006-03-29 07:45 · Score: 1

Please elaborate.
DARPA competitions encourage innovation in technology. Technology which may well end up on the battlefield some day. Not necessarily a bad thing if it prevents the loss of life, but after viewing the aforementioned film, I've got to thinking about how improved technology may be encouraging to those who would start wars. Why We Fight goes a ways toward exploring the military-industrial complex, congress' complicity (i.e. parts of a bomber are made in all 50 states, any representative proposing cutting the project sacrifices jobs in their state and 'doesn't bring home the bacon') and think-tanks which effectively are geared towards finding more ways for the private sector to invade government.
It's an excellent movie, far better and quite a bit more fair than Farhenheit 9/11. It really should be put on prime-time television, but as one reviewer noted, not a chance.

--

A feeling of having made the same mistake before: Deja Foobar
Re:Hmm by Anonymous Coward · 2006-03-29 08:30 · Score: 0

"Technology which may well end up on the battlefield some day. Not necessarily a bad thing if it prevents the loss of life"

The goal of war isn't to prevent the loss of life. The goal of war is to resolve conflict by killing. It's not always the best way to resolve disagreements, but, if you kill enough people, is highly effective. I think one of our problems is we're not mean enough. The Germans were highly effective at warfare in the early years of WWII because they weren't afraid to kill whole heaps of people. Their mistake was pissing off too many people at the same time. If they would have taking on one country at a time, we'd probably be discussing this in German. Also, the US probably saved lives (both Japanese and American) in its struggle with Japan by killing lots of people at once (A-Bomb). If we would have done it "conventionally" it would have taken a lot longer and ended up costing more lives and maybe even the freedom of Japan (the Ruskies were about to invade when Japan surrendered to the US).

Nice to see CMU... by Darth+Maul · 2006-03-29 05:36 · Score: 1

As an alumnus of Carnegie Mellon, it was great to see the coverage. I did not realize that a lot of the Stanford team came from CMU; certainly says a lot about our robotics dept. Red is certainly a powerhouse there, and congrats that the two vehicles came in second and third.

I'm such a Nova junkie, and this was an excellent episode.

--
--- witty signature

Re:Nice to see CMU... by brilinux · 2006-03-29 06:12 · Score: 1

Well, according to readme, CMU ended up on top anyway... (pdf warning, blah blah blah))

I'm a geek, so I watched this twice last night. by hackstraw · 2006-03-29 05:37 · Score: 5, Interesting

I will say, I was impressed, and surprised that I did not see an article on it at /.. I believe there was one last year.

I will say, that aside from "Stanley" winning the race on completion and time, I also believe that Stanley was the best technology. The H1lander and friend were micromanaged, and there were two vehicles that had different strategies (the tortoise and the hair) and it took almost the whole 2 hours of a team of people to map out the course and program the robots. They then added the fudge factor for human error with the fast and slow strategies.

Stanley was programmed in minutes of receiving the map, and it calculated its speed dynamically on its own. Stanley had "adaptive vision" which overlaid laser, video, and other sensory data to create a dynamic field of view of what was safe to drive through.

Now, what shocked me, was that so many teams finished this year. Nobody got past 7 or 9 miles last year, and many vehicles passed the entire 132 mile trip this year. Watching the vehicles drive was impressive. Most of the time, they appeared to be manned.

The course was not easy, by any stretch of the imagination. With the success of Stanley, I believe that this will increase the adaptive and learning capabilities in current software controlled systems. Currently, software is brute forced into trying to accommodate all possible logical conditions, which is impossible, and often just wrong.

Re:I'm a geek, so I watched this twice last night. by Zocalo · 2006-03-29 05:47 · Score: 4, Funny

There were two vehicles that had different strategies (the tortoise and the hair)
Let me guess; in the end it was a close shave and the tortoise only won by a whisker? ;)

--
UNIX? They're not even circumcised! Savages!
Re:I'm a geek, so I watched this twice last night. by Stalyn · 2006-03-29 05:59 · Score: 2, Insightful

The Red team (CMU) basically preprogrammed their robots before the race by looking at satellite maps of the race course. I thought in essence this was cheating but I suppose it was not against the rules. The Blue Team (Stanford) had a better software solution where their robot would essentialy drive and learn on the fly. I'm glad to see Stanley won because this is the technology needed for automated driving, imagine using the Red team's solution and have to preprogram you car? What's the point?

--
The best education consists in immunizing people against systematic attempts at education. - Paul Feyerabend
Re:I'm a geek, so I watched this twice last night. by hackstraw · 2006-03-29 06:10 · Score: 1

I'm glad to see Stanley won because this is the technology needed for automated driving, imagine using the Red team's solution and have to preprogram you car? What's the point?

Exactly. I believe that the Stanley approach was more "real life" for what we do now, and what will be done in the future. When I go on a trip, or even go to somewhere locally where I don't know the exact location of where I go, I at least get the address and correlate it to something I do know. With the ease and availability of Google maps, I usually get a map. This is what the Stanley team did.

The Red team had something like 15 or more people parallel processing and micromanaging the whole trip with arbitrary 5m/s or 6m/s speeds, and again, its worth noting that the red team had 2 vehicles one with a more aggressive and one with a more conservative speed input.

Stanley was able to drive 132 miles at an average of about 20m/h across rugged terrain up and down mountains, through tunnels, hairpin turns, and _pass_ the red team truck to win. Plus, its worthwhile to point out that the Red team had H1s whereas the Stanley team had a more modest and fuel efficient VW.

The Stanford Stanley team kicked ass. I'm very impressed.
Re:I'm a geek, so I watched this twice last night. by thequux · 2006-03-29 10:12 · Score: 2, Informative

Sorry to break up the party, but the second race was MUCH easier then the first. For the first 7 or 8 miles, each vehicle was in a dry lakebed. Comapre this to the ravines and washes that were in the first 7 or 8 miles of the last course.

Why did they make it easier? My personal theory is the act of congress that calls for 2/3 of the armed forces to be autonomous vehicles by 2008 (or something of the sort; I'm probably wrong about the date).

By making people win (not to denigrate their achievement... debugging an autonomous vehicle is no mean feat!), DARPA has robbed the rest of the teams of a fair shot.

TerraHawk, in particular, was designed for a much mure brutal course. It was not the fastest vehicle, but in the terrain that we expected, it wouldn't need to be. (actually, the 5 m/s speed cap was in software... we limited it for safety reasons, as well as the trash can we murdered at the Site visit when we tried to raise the speed a bit :-)

We had problems because, In an effort to deal with that kind of course, we were replacing components right up until the end. (and we did our first test of the new vehicle the day before we went up to Fontana. The old vehicle was well tested, but it had issues with the pneumatics, and we were willing to risk failure in order to get a better chance of success.)

Now that I'm partially off topic, I might as well go the rest of the way.

I am most probably the only person in the world who has worked on no less than THREE teams (PVRW, Team Tormenta, and Terra Engineering). But, I also noticed that is was the big money teams that got through the NQE and on to the main race. Interestingly enough, after the race, when DARPA refused to announce the winner immediately, conspiracy theorists were arguing (with reason) that DARPA was trying to find some technicality to let the Red team win; 8 hours later, they realized that there was no such technicality, and their favored team lost.

Now, before that's marked as flaimbait, keep in mind that this is coming from someone who hasd been involved with this for 2 years, and who noticed the beaurocracy involved.

As a final illustration of this beaurocracy, at the gate to the team garages, ther was a seperate entrance fro people. For about 25 feet on the public side of the gate, there was a portable barrier set up so separate the footpath and the path for vehicles. On the other side, however, there was absolutely nothing. Now the guard was rather strict about the "humans on the human path, and 'bots on the 'bot path" rule, een when someone was coming out the the team area to go to something right next to the gate.

Comaring this to the creativity shown by the teams, you really had to wonder: who was really more organized?

Seen it-One eyed. by Anonymous Coward · 2006-03-29 05:38 · Score: 2, Interesting

The interesting thing for me is that the method we use (our eyes) was too difficult for machines. That's why all those robots used lasers, and other techniques. We've come far, but we still have a long way to go.

Re:Seen it-One eyed. by morgan_greywolf · 2006-03-29 06:05 · Score: 2, Insightful

The human eye and visual cortex are an amazingly complex and complicated system. Interestingly enough, I remember about reading about the a while back in December. According to the wired article, IIRC, Stanley used a combination of lasers (short range) and cameras (long range). It then took what it learned about the short range view of the landscape and it applied that knowledge against what it was seeing on the long range from the cameras.

This is actually not too far different from how human vision works -- we sort of guess about the landscape in front of us based on knowledge of other landscapes and the current landscape around us that we can see close-up. We just don't have lasers. ;)

--
My blog

You almost never see the words by gurutc · 2006-03-29 05:41 · Score: 2, Insightful

'Coverage' and 'Darpa' in the same paragraph.

Another interesting point is that it seems to me that this is the development arena for the military's new autonomously roving gun platform.

--
Moderation in All Things... Especially Moderation - gurutc

Re:You almost never see the words by Jett · 2006-03-29 05:54 · Score: 5, Interesting

I hadn't heard about it being for an autonomous gun platform. I watched the show last night and they presented it as purely for supply transports. They specifically mentioned Jessica Lynch and how she was just a truck driver who should never of been exposed to combat. They also mentioned that the DOD want's 1/3rd of their transport trucks to be autonomous within 10 years.
Re:You almost never see the words by kosanovich · 2006-03-29 06:00 · Score: 1

"Another interesting point is that it seems to me that this is the development arena for the military's new autonomously roving gun platform."

At some point this may be true, but more immediately this is the development arena for the military's new autonomous supply delivery system. If you look at the people that are most often getting attacked it's the supply caravans. If we didn't have to have people in those vehicles then the loss when a caravan is attacked is much less. Just because we can make a robot that can get from point A to point B doesn't mean it can easily identify and lock onto an enemy then fire... think of going to the taxpayers to pay for that.
Re:You almost never see the words by hackstraw · 2006-03-29 06:17 · Score: 0, Offtopic

They specifically mentioned Jessica Lynch and how she was just a truck driver who should never of been exposed to combat.

She should have not volunteered for such a dangerous job.

I have a pet peeve with sob stories about how people enter known dangerous jobs, especially the military, where their existence is to be disposable to help the poor people of Iraq and ensure the economic welfare of the people back home.

Now, the initial invasion of Iraq is at best controversial. The continued occupation with no plans of leaving are another story. Every time I see one of those cute bumper stickers that say, "I support our troops" which is the most noncommittal version of "Its OK to be at war", I say to myself, "Then bring our troops home where they are safe".
Re:You almost never see the words by Moby+Cock · 2006-03-29 06:18 · Score: 1

What struck me about that comment regarding Jessica Lynch is that she was resupplying the frontline. That means she was driving an armoured truck to where guys (and girls) are actively engaged in firefights but her exposure to danger was the concern. Of course, anyway that we can have fewer people in harm's way in a positive but I found it unsettling that the battle line soldiers were mentioned as a throw-away in order to frame their argument.

Overall though, a good show. Go watch it.
Re:You almost never see the words by Anonymous Coward · 2006-03-29 07:07 · Score: 0

"Another interesting point is that it seems to me that this is the development arena for the military's new autonomously roving gun platform."

Well, as others have said, its because they're currently in development for supply convoys. But, for the sake of debate and also I'm bored, lets say they are being developed as autonomously roving gun platforms. How is that a bad thing? The reason armies exist is to resolve disagreements between two or more groups of people by killing enough of the "other guys" that the ones that are left give up. As bad as it sounds, its not really good or bad... it's just the way things are and always will be. If we can create robots to do this job more efficiently, then why shouldn't we?
Re:You almost never see the words by DG · 2006-03-29 08:24 · Score: 1

I came into the show - in glorious HD, no less (PBS has great HD content!) - a little late, so I missed the Jessica Lynch reference.

But I do understand the desire to attempt to make resupply trucks autonomous. I'm not entirely sure it's really possible... but I do understand the desire.

Modern militaries consume enourmous amounts of supplies, and those supplies are big, bulky, and heavy - and more often than not, highly explosive.

The main gun round for an M1A1 tank is around 200mm in diameter, weighs ~23kg, and is almost a metre long. A single Abrams will carry 40 of them, so a complete battle reload for a troop of 4 tanks is 3680kg (not counting packing material and dunnage; add 15% more weight to account for that and you're up to ~4250kg. The Abrams also uses a combustable cartridge case in its main gun ammo (the round is not encased in brass, only the base plate is metal - the rest of the powder case is burned up when the ammo is fired) which reduces the weight per round, but makes the ammo *V*E*R*Y* flammable.

The tank also carries 500 gallons of fuel, which is good for about 150 miles of cruising/fighting, or about 8 hours of operation. (The Abrams has a turbine engine which is very fuel efficiant and light at full power, but also burns almost as much fuel at idle as it does at full throttle) A typical tanker truck carries about 4000 gallons, so a single tanker truck will get 4 tanks 300 miles, or 16 hours of operation.

Because this stuff is so bulky and heavy, the trucks that carry it are all about payload. There just isn't any room in the weight budget to provide any real armour. You can sometimes help protect the crew, but there's no way in hell you can armour the cargo - and the cargo is basically a big ol' bomb. Until such time as the fuel and ammo are transferred inside the tanks (where they are safe - well, safe-ish) the supply trucks are enormously vulnerable.

During the "Thunder Run" that seized Bagdad, the armoured column that grabbed and held the centre of the city came within a whisker of running out of fuel, and the resupply column that saved them took fire and lost a number of vehicles.

Autonomous supply trucks could have driven supplies forward without submitting the crews to the terror of a charge through enemy-occupied territory while riding a bomb. And unlike an autonomous weapon system, you aren't handing a human life over to a machine.

It's an interesting idea. I don't think it'll fly... but it is interesting.

DG

--
Want to learn about race cars? Read my Book
Re:You almost never see the words by gurutc · 2006-03-29 09:22 · Score: 1

Here's a link to 'non-convoy' uses: http://news.bbc.co.uk/2/hi/americas/4199935.stm Also, Carnegie Melon's TUGV: http://www.post-gazette.com/pg/05217/548931.stm

--
Moderation in All Things... Especially Moderation - gurutc
Re:You almost never see the words by Anonymous Coward · 2006-03-29 09:35 · Score: 0

I have a pet peeve with sob stories about how people enter known dangerous jobs,

So you don't have a problem with Mexicans dying while crossing the desert into the U.S.?

Because it's, you know, dangerous.
Re:You almost never see the words by darkwing_bmf · 2006-03-29 17:18 · Score: 1

LOL, Those pictures remind me of Johnny 5... "Be a Pepper Too!"

torrent by Anonymous Coward · 2006-03-29 05:43 · Score: 5, Informative

http://www.mininova.org/tor/266446

My Robot by Anonymous Coward · 2006-03-29 05:43 · Score: 2, Funny

I would have entered a giant mechanical penis shaped robot car with "Kill all humans" written on the sides.

Too bad I've been so busy slacking this year.

Great show but...Patents bad. by Anonymous Coward · 2006-03-29 05:45 · Score: 0, Funny

"And, then, who owns the work? Do they at least get patent recognition on some of the innovations? Some of the software they talked about was truly seriously cool stuff."

But, but. Software patents are bad. Now I'm confused.

Haven't I seen this before...? by TriZz · 2006-03-29 05:47 · Score: 1, Funny

...the Knight Rider prophacy is coming true!

Note to David Hasselhoff: Now's the time to re-invest into your (American) acting career!!

--
No matter how hot a girl is - some guy somewhere is sick of her shit.

Re:Haven't I seen this before...? by Machina+Fortuno · 2006-03-29 05:59 · Score: 1

I really hope that that note doesn't reach David.

Hell yeah! Now instead of having friends or parents drive us everywhere, our cars can! And secondly... if I talk to my car, it just keeps bitching about low oil pressure. I told it to stop whining and go complain to the auto-shop. But the automated system at the shop accidently ate my car. Poor thing...

--
...

Needs Serious funding by thePig · 2006-03-29 05:48 · Score: 1

Shouldnt we be all seeing fully functional independent robots by now?
The robotics is taking a long time to mature.
*very very* long time
I believe the problem is that only small set of individual professors and small group of students cannot achieve huge breakthroughs in engineering.

Creating an Atom Bomb was just engineering (since sustained reaction was experimentally proved in 1933 itself).
But how many people could do it?
It took a huge set of scientists (*read - not engineers) and a huge set of engineers working together to achieve it.
And they did it in what 3 years ??

Similarly one big government funded project, and we can see real robots around.
Otherwise, in 50 years from now, we would still have similar news coming out.

--
rajmohan_h@yahoo.com

Re:Needs Serious funding by Machina+Fortuno · 2006-03-29 06:03 · Score: 1

You sound like you are really ready for the planet to be overtaken by robots.

While the fact that so "few" (I am not sure of the validity of that statement)are working on improving robotics, you have to realize the massive task that it is to translate reality into a machine. And then... for that machine to independently make a decision based on the generalizations of their enviroment.

And about the A-bomb... they had Einstein, they cheated.

--
...
Re:Needs Serious funding by TigerNut · 2006-03-29 06:31 · Score: 1

What would a fully functional independent robot do? How would it improve your lifestyle? What is that worth to you, as a consumer? When you can make a valid business case based on good answers to those questions, the robots will come out of the woodwork.
In some arenas, the technology already exists. Roomba vacuums are fully functional independent robots. You can get (for a price, and with limited capability) robot lawn mowers. Some subway systems use automated trains; they're fully functional and independent within the constraints of their designed task. Fully automated aircraft landing systems have been demonstrated, but they require infrastructure investment and some psychological buy-in by the travelling public. Autopilots (especially as implemented in cruise missiles) are essentially independent survival machines with a dedicated goal.
You can see that the main issue with robotic systems is to get them to have some consideration for human existence, if the mechanical system that they operate is large enough to injure or kill them. Remove that constraint, and it's a lot easier.
Klaatu! Borada! Nikto! AAAAAAAAAIIIGHGH

--
Less is more.

Saw this show last night by Ponga · 2006-03-29 05:57 · Score: 1

Really good documentary! Seriously, you know you are a TRUE nerd when you witness an autonomous vehicle actually complete a race like this... and a tear comes to your eye! Really, I got misty-eyed watching this!!

Re:Saw this show last night by TriZz · 2006-03-29 05:59 · Score: 0

HAHAHA! I could imagine you playing "Eye of the Tiger" on your stereo with the video muted.

~*tear*~

--
No matter how hot a girl is - some guy somewhere is sick of her shit.

Agressive Robot Drivers by digitaldc · 2006-03-29 06:09 · Score: 4, Funny

What do you do in the future when one of these is mass-produced and forgets its turn signal and cuts you off?
Do you scream and give it the finger?
Throw rocks at it?
Run it off the road?
Launch a homing missile at it?
Any way around it, driverless vehicles will have no rights in our future society!
Who will speak up for the robots?

--
He who knows best knows how little he knows. - Thomas Jefferson

Re:Agressive Robot Drivers by Woogiemonger · 2006-03-29 06:59 · Score: 1

What do you do in the future when one of these is mass-produced and forgets its turn signal and cuts you off?
...
driverless vehicles will have no rights in our future society!

If your fears are realized, hopefully they'll have no lefts either.
Re:Agressive Robot Drivers by evilviper · 2006-03-29 10:02 · Score: 1

What do you do in the future when one of these is mass-produced and forgets its turn signal and cuts you off?

Finally, all my knowledge aquired over the years becomes extremely useful!

I know this one... What you do is get way out in front of it, and get out of your car. Walk over and grab the yellow-line in the middle of the road. Rip it so that you have an end, and carry your end to the nearest wall, then set it down. The robotic vehicle will follow the curved line at full speed, straight into the brick wall, where it will be flattened...

The only thing I'm not sure about, is if it will see stars or birds flying around it's head...

--
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant

video is worth a thousand words by 80+85+83+83+89+33 · 2006-03-29 06:10 · Score: 1

i do keep up with robotics and ai, religiously following the progress of the field for almost twenty years. and i have read every article i could find on the DARPA race, and kept track of the race on the (awful) Flash/shockwave site. after the race was won, i've almost become burnt out on it, almost not caring to watch the NOVA footage. well, i'm glad i did, because it showed the best inside info on how Stanford's AI and sensor fusion worked. and it compared and contrasted Stanley's AI techniques with Carnigie Mellon's. of course, watching multi-ton driverless vehicles veer off course and plow full steam ahead straight towards the spectators was exciting (some of the concrete barriers were knocked farther than when hit by NASCAR stock cars!). and H1ghlander sure had a taste for chewing up haybales! props to the geniuses at all the teams!

--
i disable sigs

Tell PBS Thanks! by IanDanforth · 2006-03-29 06:13 · Score: 3, Informative

I really enjoyed this, especially the fact that it was the full show online for free.

Let PBS know what you thought about the format, show, or anything else.

-Ian

Re:Tell PBS Thanks! by Anonymous Coward · 2006-03-29 07:36 · Score: 0

Actually it would be even better if you gave them some cash .....

Fascinating program by amightywind · 2006-03-29 06:16 · Score: 1

This was a fascinating program. It would have been nice if the Stanford team divulged more of their ideas, what software languages and designs they used etc. It looked like they were doing a Bayesian classification on combined laser ranging and video on the terrain ahead. Doing that for 1 image is complicated enough. Doing 10+/sec is mindblowing. The control system moderated the vehicle's need to follow a prescribed path with how safe the path was. Amazing stuff, very elegant. Pretty much done with a stock Volkwagon SUV. Next time they should conduct this race without GPS. I have no doubt someone will figure it out.

--
an ill wind that blows no good

Re:Fascinating program by Moby+Cock · 2006-03-29 06:21 · Score: 1

I agree that more detail would have been preferable. However, I expect the producers have to contend with trying to make this show appeal to a broader viewership than the typical /. geeks like you or I.

Does anyone have any links that contain more gory details about the Stanford effort?
Re:Fascinating program by SpyPlane · 2006-03-29 07:13 · Score: 4, Informative

Do a google search on Sabastian Thrun, he was the team lead for Stanford, and formally at CMU (what a non-coincidence). Most of the software they used on Stanly (Stanford's bot) was either written by Sebastian in his former research or taken from experience gained on CMU's team the previous year. The ladar mapping he used, I know I saw on some former page of his that had all the gory algorithm details. It might just take a little bit of searching. He also has a c library out there somewhere that does a lot of this stuff, but I can't seem to find it now.

One paper that's of interest might be here: http://www.cs.cmu.edu/afs/cs.cmu.edu/user/thrun/pu blic_html/papers/thrun.ces-tr.html (sorry, no linky, writing in a hurry)

And that paper is mentioned in the readme of the BFL (Bayesian Filtering Library) found here:
http://people.mech.kuleuven.be/~kgadeyne/software/ bfl-trunk/

Lastly, at one point all of us competitors were required to give our design documents to DARPA, and they put them up on their webpage here:
http://www.darpa.mil/grandchallenge05/techpapers.h tml

BTW, I wasn't on Stanford's team, but I was on another finalist team.

--
"We need a fourth law of Robotics: Stop Fingering My Wife"
Re:Fascinating program by Yokaze · 2006-03-29 07:31 · Score: 1

> Most of the software they used on Stanly (Stanford's bot) was either written by Sebastian in his former research or taken from experience gained on CMU's team the previous year.
[...]
> BTW, I wasn't on Stanford's team, but I was on another finalist team.

Those claims combined, it is fairly easy

--
"Between strong and weak, between rich and poor [...], it is freedom which oppresses and the law which sets free"
Re:Fascinating program by SpyPlane · 2006-03-29 07:52 · Score: 1

Nice try, I wasn't on CMU either. No I was on a team that actually had to work for every dime they spent on the vehicle.

I'm not stating anything false. Read his research and when it took place. The core stuff all came from CMU or Sebastian in previous efforts (like I stated). Now once at Stanford they changed how they did things entirely and wrote a ton of code to make everything play much nicer than CMU's platform. Stanly was much smarter than either of the two CMU bots.

--
"We need a fourth law of Robotics: Stop Fingering My Wife"
Re:Fascinating program by Yokaze · 2006-03-29 09:13 · Score: 2, Interesting

> Now once at Stanford they changed how they did things entirely and wrote a ton of code to make everything play much nicer than CMU's platform.

This sounds a little bit more like that, what I have heard. I've read, that they throw away most of the code and rewrote a large deal. E.g the classification of driveable terrain by the laser scanner was rewritten and learned. AFAIK, most of what has been published (and to what you pointed) is fairly generic stuff.

To the best of my knowledge, it has not been published how they learned the far range vision based on the near range laser scanner, which, to my eyes, is the most interesting part of the project.

> Nice try, I wasn't on CMU either.

Well, the comment on Sebastian Thruns previous affiliation and the code development sounds like something Mr. Whittaker could have said. But from what I've heard, he followed a fully stochastically approach and less reliance on the physical stability of the sensors and GPS, which AFAIK was quite different to the Red Teams approach and resulted in a much smaller code base.

--
"Between strong and weak, between rich and poor [...], it is freedom which oppresses and the law which sets free"
Re:Fascinating program by SpyPlane · 2006-03-29 10:00 · Score: 1

"To the best of my knowledge, it has not been published how they learned the far range vision based on the near range laser scanner, which, to my eyes, is the most interesting part of the project."

They didn't use the near range laser scanner for the far range vision. They had a color camera they used. That was what was used to get those Red/Green video's/pictures you see on Nova's site. None of the competitors used the SICK Lasers for anything more than 25 meters, because they simply didn't work past that. A couple of teams had a different laser, but I can't remember the name, I know it was around $30-35k a pop, vs the $7500 a pop for the SICK. A little far out of our price range. Stanford also had RADAR, but AFAIK that was only for range calculations and suplimental drivability map data.

Camera whether stereo or not was the big "if" in the competition. It seemed like it was a surefire way to doom your team. We tried video, but in the end we ended up relying on LADAR like everyone else. To my knowledge even Standford only slighly used their camera system, compared to their LADAR/RADAR use. It was just too hard to get working reliably. Given another year, we could have had ours trained to drive you to work, but like everyone else, there simply wasnt the time available to train a vision system.

--
"We need a fourth law of Robotics: Stop Fingering My Wife"
Re:Fascinating program by Anonymous Coward · 2006-03-29 10:06 · Score: 0

I watched the program, and I applaud the participants.

I wonder though, Instead of taking an existing car and equipping it with an intelligent robot, wouldnt it be better to come up with an intelligent robot capable of transporting people?
Re:Fascinating program by crazyharry · 2006-03-29 18:05 · Score: 1

>SpyPlane: >No I was on a team that actually had to work for every dime they spent on the vehicle. That sounds a Rockwell-Collins Employee from government systems on Team Terramax!

Sensors by Rac3r5 · 2006-03-29 06:16 · Score: 1

A lot of things seems trivial to implement in theory, but in actuality physical and environmental constraints seem to introduce a whole different ball game. A big congrats to all the teams who entered.

One thing that I noticed from the article is that one of the teams has problems with dust accumulating on the sensors. How would one get rid of this dust, so that you don't recieve incorrect readings?

Re:Sensors by Anonymous Coward · 2006-03-29 06:58 · Score: 0

There is a sophisticated device for removing accumulated dust and grime with which you are probably not familiar.

Its called "the shower"
Re:Sensors by SpyPlane · 2006-03-29 07:30 · Score: 1

Many of the teams (including us, small team, but still finalist) had little water spray nozzles. The LADAR would actually have a very specific error code when it was being disrupted, so we triggered on that. We also disregarded all "obstacles" within 1 cm of the sensor (ie: the lense!).

Although software was a big focus, having good mechanical engineers was the key. Keeping stuff cool and free from vibration type failures was a BIG deal.

--
"We need a fourth law of Robotics: Stop Fingering My Wife"
Re:Sensors by Rac3r5 · 2006-03-29 07:40 · Score: 1

my first reaction to the dust issue was why not use water. But then I was thinking, won't spraying water on the sensors just cause you to have big clogs of dust on the sensor due to water droplets?
Re:Sensors by SpyPlane · 2006-03-29 07:49 · Score: 2, Informative

Honestly, not really. It was so damn dry out there that they water would spray the dust off and dry off in no time. I'd say rarely though did we ever see the water system turn on. Really, only in our mud testing did we ever get major buildup. Those LADAR's were pretty resilient sensors. The sun shining in them was much worse than any dust buildup.

--
"We need a fourth law of Robotics: Stop Fingering My Wife"

Interview with Director and Team Leader by Anonymous Coward · 2006-03-29 06:19 · Score: 2, Interesting

Last Saturday, Digital Village Radio did an interview with Jason Spingarn-Koff, the filmaker of The Great Robot Race, and Sebastian Thrun, the leader of the winning Team Stanford. Here's a link to the mp3.

Thanks! by Anonymous Coward · 2006-03-29 06:19 · Score: 0

v nice

but would it work? by lardlad · 2006-03-29 06:25 · Score: 3, Interesting

So DARPA funds this to create autonomous supply vehicles, which might work in a traditional battle with clearly drawn front lines and relatively secure transport routes behind the lines.

It seems to me like 21st century warfare is a whole different animal - how hard would it be for a motivated, talented individual to figure out some simple attacks for the navigation systems on these vehicles, and get loads of sweet US munitions delivered to their doorstep? How effective would one of these vehicles be in an urban setting? How easy would it be to create a series of obstacles that would paralyze one of these vehicles?

It's amazing technology, for sure, and the Stanford and CMU teams deserve kudos. I'm just concerned that with the current rush to technological solutions and shift away from "boots on the ground", this technology will be in battle zones far too quickly.

Re:but would it work? by timeOday · 2006-03-29 07:41 · Score: 1

On the other hand, with driver drones you can try all new tactics. Perhaps instead of a single well-established supply line, you can "swarm" the supplies into place with more, smaller vehicles. As for captured munitions, with no driver onboard, a remote destruct function becomes a possibility. Or maybe highly sensitive shipments like munitions will simply be trucked conventionally (by a person). That still leaves a lot of other stuff to move around.
Anyways, I wonder what percentage of military trucking worldwide is really conducted in a combat environment? At first maybe the robots will just drive from the port in friendly nation X to the rear lines of the battle. Just as civilian applications might initially be limited to driving between warehouses on the outskirts of cities, rather than in confined city streets.
I think reducing the number of boots on the ground is a good thing. Would it solve our present "Iraq problem"? No. But I would argue that's a problem with the mission. Nation building is inherently messy and, as Bush used to say before he was elected, should be avoided.
Re:but would it work? by SpyPlane · 2006-03-29 07:45 · Score: 1

how hard would it be for a motivated, talented individual to figure out some simple attacks for the navigation systems on these vehicles, and get loads of sweet US munitions delivered to their doorstep?

How hard? I would say next to impossible. Tricking the GPS system on board is impossible, while staying alive. You'd have to emulate enough GPS sats to give the vehicle improper coordinates (not only would these Satellite emulators have to work, but they would have to be synchronized properly, don't forget to emulate Doppler effects!). Even if you do trick the vehicle, you'll have to jam the other GPS satellites to make sure you are the signal it goes for. If you try jamming GPS, you'll get a HARM sent your way (bad news). If you are talking attacking the ACTUAL navigation system on board, that means you have physical access to the vehicle, which means there's no point for it to navigate to your house, you can just offload the goods. In that case, I bet they'd either let you have the goods (if it's water or something) or drop a bomb on you while you are unloading it (if it's something more sensitive).

Your next two questions are much more valid. Urban setting will be tough. The only benefit is at least there will be some form of road boundry to work off of. The open desert is much tougher in that regard, everything looks the damn same. I assume these systems will begin to be used in the more long haul type scenarios. Open highway with no buildings, but are really dangerous to drive because of ambushes and IED's.

--
"We need a fourth law of Robotics: Stop Fingering My Wife"
Re:but would it work? by odyaws · 2006-03-29 07:45 · Score: 1

How effective would one of these vehicles be in an urban setting?
The word in the robotics community is that there will be another DARPA Grand Challenge, this time focused on urban driving. This should be a significantly harder problem, as if the first one wasn't hard enough!

--
Still trying to think of a clever sig...
Re:but would it work? by c41rn · 2006-03-29 08:59 · Score: 2, Interesting

If I remember correctly, the object sensors on these 'bots can not distinguish between a solid, impassable obstacle and a harmless bunch of scrub that could be driven through. Assuming this is true, couldn't you create a 'wall' out of bedsheets or some other cheap material and box one of these vehicles in very quickly. Once disabled (confused), you could unload the supplies or damage the vehicle.
This is just conjecture based on a half-recollection but I don't thik it would be too difficult to attack a relativly slow moving, unarmed autonomous vehicle such as demonstarated by the Grand Challenge vehicles which are at the state of the art.

I can see it now by Vapon · 2006-03-29 06:26 · Score: 1

Breaking News!!!

Virus outbreak causes cars to crash, responsible for thousands of deaths.

Re:I can see it now by Anonymous Coward · 2006-03-29 06:50 · Score: 0

News Flash^2

Legislation enacted prohibiting the use of MS Windows in automobiles
Re:I can see it now by kadathseeker · 2006-03-29 08:25 · Score: 1

Nothing could be worse than human drivers, especially the young and the elderly.

--
The 'Net is a waste of time, and that's exactly what's right about it. - William Gibson

Sebastien Thrun's book by jdduke · 2006-03-29 06:27 · Score: 3, Informative

If anyone is really interested in the technical and mathematical side of this stuff, I definitely recommend Probabilistic Robotics by (among others) Sebastian Thrun, director of the Stanford Artificial Intelligence Lab and leader of the winning team in this race.

Der Steppenwolf by BodhiCat · 2006-03-29 06:29 · Score: 1

Does anyone at DARPA, the Defense Department or any of the universities involved watch movies? Have they not seen the Terminator series? Haven't they read Harlan Ellison? Herman Hesse's Steppenwolf? Is this the start of the war between humans and machines? I think they need to require more reading and humanities credits for scientists and engineers. I can see myself in twenty years running from human hunting humvees in the national forest. What are we starting?

Re:Der Steppenwolf by slcdb · 2006-03-29 06:39 · Score: 1

What are we starting?
Don't you see? This is the beginnings of a grand scheme to unite all of mankind by creating a common enemy which will attempt to destroy us all. East and West, Communist and Capitalist, Arab and Israeli, Muslim and Christian -- all will have to unite against the evil that will be machines. And after the dust settles, we'll all live happily together. Or something.

--
Despite what EULAs say, most software is sold, not licensed.
Re:Der Steppenwolf by thePig · 2006-03-29 06:57 · Score: 1

Why would they hunt us?
What is the issue with the m/c becoming self-aware?

For humans, it is essential to fight with others (human or otherwise) to have enough space for survival.
So, this is implanted in our genes, that we fight.. or hunt or whatever.

But in robots, unless we specifically code to attack humans, they do *not* have any reason to do that. It is not in their genes*, anyhow.

Even replicating - even that is not in their genes..
So there is no isse of them becoming self-aware.

We shouldnt try to see in them, an image of us.

--
rajmohan_h@yahoo.com
Re:Der Steppenwolf by BodhiCat · 2006-03-30 02:18 · Score: 1

We shouldnt try to see in them, an image of us.
Yes, that's what scares me.
All that aside, it was a good show, I fianlly watched it last night on tape. WTG Stanly. Software uber Alles.

Seminar about Stanley by Anonymous Coward · 2006-03-29 06:38 · Score: 1, Informative

Anything you gleaned from the NOVA documentary is bullshit compared to watching the guy explain it himself

Airs on PBS Tuesday, March 28 by demonbug · 2006-03-29 06:40 · Score: 1

Something that could have been brought to my attention yesterday!

Seriously though, I'd been hoping someone would be putting together something like this (though I'd been expecting it form Discovery or TLC - yay for public television). Fortunately, it is available online for those of us who missed it.

Re:Airs on PBS Tuesday, March 28 by aikon29 · 2006-03-29 07:07 · Score: 1

It would have been nice if this were mentioned yesterday, but luckily I was flipping through the channels right before this came on and caught it. In HD no less!
Re:Airs on PBS Tuesday, March 28 by Anonymous Coward · 2006-03-29 08:08 · Score: 0

Check your PBS schedule here: http://www.pbs.org/tvschedules/

I'm sure they will replay it. Dear god man, do you know how many times I've seen "Jewel of the Earth"?

Mostly paid employees and purchased parts by Animats · 2006-03-29 06:41 · Score: 2, Informative

Most of the successful teams had significant numbers of paid employees. Stanford had about sixty people back at Volkswagen working on the hardware. CMU had a huge headcount; they had more than fifty people on site at the Speedway, including people on the payrolls of Lockheed, Caterpillar, and other vendors. Oshkosh Truck was all paid employees. Didn't talk to the Grey Team much, but they were paid by some Insurance company.

The big breakthrough was Stanford's texture vision system. I was very impressed with that. Computer vision in unstructured environments has a terrible track record, yet they made it work. Everything else was basically integration of off the shelf gear.

One accomplishment not oftened mentioned is that, by year two, many of the components that weren't available in year one were available off the shelf. In year one, getting an integrated GPS/INS/compass/odometer system was very tough. Applanix had one that cost $70K, took up a 4U rack, and required air conditioning. (CMU used it.) By year two, you could get something comparable from any of three vendors for about $20-$30K, ruggedized and able to run on 12VDC. All the successful teams had one, usually from Trimble or Novatel. Once you have one of those, just staying on course is straightforward. Then it's all about obstacle avoidance.

Re:Mostly paid employees and purchased parts by mmde · 2006-03-29 07:12 · Score: 2, Informative

A minor correction... Stanford actually had 60 people total on the team. There were 9 people from VW working on the vehicle. You can see a list of all of the team members at our website.
Re:Mostly paid employees and purchased parts by Animats · 2006-03-29 20:05 · Score: 1

My point on this is that some key components went from being expensive one-offs to commercial products in a year, because Grand Challenge entrants pushed on the vendors. That, for DARPA, was a big win. In a few years, the hardware side of automatic driving will be a total non-problem. That's a big help for researchers; you spend too much time on necessary but mundane stuff.

of course by argStyopa · 2006-03-29 06:50 · Score: 1

Obligatory Simpsons Quote:
"The wars of the future will not be fought on the battlefield or at sea. They will be fought in space, or possibly on top of a very tall mountain. In either case, most of the actual fighting will be done by small robots. And as you go forth today remember always your duty is clear: To build and maintain those robots. Thank you."
-- Military school Commandant's graduation address, "The Secret War of
Lisa Simpson"

--
-Styopa

I work at Oshkosh Truck Corporation (TerraMax) by Anonymous Coward · 2006-03-29 06:57 · Score: 0

It was interesting to see. They didn't however show that TerraMax was paused by officals many times, because of other robots broke down or in the way of the TerraMax Truck. No saying we would have won, but we did have to stop until the next day, because of the pauses. Great job Stanley and all others for completing the race.

I saw this last night too by Anonymous Coward · 2006-03-29 07:06 · Score: 0

It was a pretty interesting show but I was kind of disappointed with the concentration on the Stanford and Carnegie Mellon teams. The team I was most interested in was Team ENSCO - their car Dexter was leading at the half way point but unfortunately it hit something after 81 miles, bending the frame and causing a flat tire. I'm still a little disappointed they didn't win - the academic teams were very clearly the favorites going in to the race and even though ENSCO itself is a (somewhat) defence related company, everyone loves an underdog.

Re:I saw this last night too by SlayerDave · 2006-03-29 10:13 · Score: 1

They didn't finish the race! Out of 23 competitors, 5 finished the race. If anything, they should've focused a bit more on Team Gray and TerraMax, who did finish the race (though TerraMax was disqualified due to time).

Very good NOVA documentary by heroine · 2006-03-29 07:10 · Score: 1

This was a very good NOVA documentary. It moved quickly and covered a lot of new ground in a short time, like the algorithms the robots used and the kinds of problems they solved, unlike most documentaries which repackage the same science anecdotes over and over or only discuss philosophy.

It wasn't as much the fact that Stanley won the race as how Stanley won the race and the differing approaches of the builders that made it interesting.

Unfortunately, it was not in HD. It was widescreen low definition. They can get robots to drive 120 miles but they still can't get HD.

Robot Wars by s31523 · 2006-03-29 07:12 · Score: 3, Funny

At what point do the robots turn on each other and try to smash one another with saws, hammers and spikes? Wait, I think that is a different show...

More details... by Anonymous Coward · 2006-03-29 07:14 · Score: 0

Follow the link in this comment

Re:More details... by hendrik42 · 2006-03-29 17:50 · Score: 1

Mod parent up!! This is by far the most relevant post in the entire discussion. The link leads to a video of Stanley's Software Lead giving a presentation about his project at CMU. Very technical, very detailed and lots of fun. News for nerds at its best!

Airs.. Yesterday!? by timeOday · 2006-03-29 07:18 · Score: 1

Thanks slashdot!

Some Random Thoughts about This by slcdb · 2006-03-29 07:18 · Score: 1

I watched this show when it aired last night. I'd actually been looking forward to it quite a bit since seeing a preview for it a week or so ago. Is it just me, or is Nova possibly the best show on television? I don't get so interested in every subject they cover, so I don't watch it all the time, but, I must say, every episode I have seen has been excellent. We could use more television like this, and a lot less American Idol and other BS.

There was nothing quite like seeing, for the first time in my life, real vehicles, weighing multiple tons, driving completely by themselves. Awe-inspiring stuff to catch a glimpse of the future like this. Even my wife (who is not geeky at all) really got interested in this show and was practically cheering when Stanley passed Highlander.

All this robotic car stuff is pretty slick. But, you know, I would have been so much more impressed to have seen one of the teams pull up in just a regular car with no special equipment, sensors, or modifications, and then watch they put a humanoid-like robot in the driver's seat to drive the car. How much longer before the tech advances to this step?

--
Despite what EULAs say, most software is sold, not licensed.

Excellent Show! by supergeekmake-it-so. · 2006-03-29 07:23 · Score: 0

While I didn't find the broadcast show as insightful as the original article in Scientific American article preciously posted, I did find the show very entertaining. It was interesting to see the different contestants, and the projects they spent so much time working on. I can honestly say I'm ready to have an automated vehicle. It will give me more time to do the things I like versus spending copious amounts of time on the road. Wouldn't it be cool to have mobile online access, and a vehicle to drive you from point a to b, and you get to be reading /. P-)

On the weekend of the race... by kpainter · 2006-03-29 07:32 · Score: 1

I was coming from Utah back to California. We had just stopped in Primm, NV to eat. Just after Primm, we saw what we thought was some crazy guy tearing up the desert after drinking way too much beer. The dust cloud behind this "guy" was incredible - I saw it from miles away. The vehicle was coming towards Primm from the California side and probable a mile off the freeway. As the vehicle past us, that thing was bouncing pretty good. I remember commenting to my girlfriend that that "his" suspension wasn't going to be the same after that. It wasn't until a couple of days later that I figured out what we had seen. Had I known, I would have stopped to watch and take pictures.

Details in the program by gcanyon · 2006-03-29 07:36 · Score: 3, Insightful

There were several points made in the program that I hadn't heard elsewhere (and I've been paying attention to the Grand Challenge since the initial press release).

-- The teams get the GPS waypoints a few hours before the race. The waypoints are purposefully vague, so the robots have the choice of driving off a cliff (or into one) while still being within GPS parameters. This is supposed to prevent the race from reducing to "Who can follow GPS the best?" The Red Team had a group of what looked like 20 or 30 people who immediately sat down with the waypoints mapped out on satellite imagery, going through and adding waypoints of their own and adding speed commands for their robots. This seems to me to be a big violation of the spirit of the competition.
-- The Red Team had two entries, which they programmed differently: one more aggressive, the other more conservative (on speed). The faster robot, Highlander, was pulling away from Stanley for the first part of the race, until some unknown issue starting causing problems. Nova didn't say what was wrong, but it looked literally like Highlander was slipping out of gear and rolling back down hills. It _might_ have been doing it on purpose, i.e. a software glitch, but it didn't look that way.
-- One of the Red Team's entries completed the last portion (the hardest portion) of the course with its main sensor non-functional -- it was stuck pointed 90 degrees to the side. This argues even more strongly that the Red Team's vehicles weren't doing much route-finding and were pretty much just following GPS waypoints.

The conclusion I draw from this is that we are still a long way from the DOD's goal of autonomous transport vehicles. In a combat situation, transports need to be able to avoid obstacles put in their way _by the enemy_. The only time during this challenge that the vehicles did anything like this was during the initial trials before the race, and that was very limited. The actual race course was hard -- off-road, dirt, narrow, slippery -- but it didn't have tank traps painted the same color as the dirt they rest on. It didn't have razor-wire barricades, forcing the cars to figure out a route through the bushes around them.

I'm confident that if I had been on the course fifteen minutes before the cars showed up, I could have stalled or disabled all of them. Pile a bunch of bushes across the road and all of them would have stopped. During the trials and race, none of them demonstrated the ability to work around such a very limited obstacle.

All of this is not to minimize what was accomplished. But we're a long way from sitting back sipping champagne while robots do the dirty work of war.

Re:Details in the program by Rick.C · 2006-03-29 08:13 · Score: 1

-- One of the Red Team's entries completed the last portion (the hardest portion) of the course with its main sensor non-functional -- it was stuck pointed 90 degrees to the side. This argues even more strongly that the Red Team's vehicles weren't doing much route-finding and were pretty much just following GPS waypoints.
Your point is certainly valid, but also consider that a robot with backup systems that rely on totally different strategies will have a better chance of success when (not "if") something goes wrong.
The "just following GPS waypoints" strategy got it across the finish line, albeit in second place. At least it finished.

--
You were 80% angel, 10% demon. The rest was hard to explain. - Over The Rhine
"Math in a song is good."-Linford
Re:Details in the program by demonbug · 2006-03-29 08:42 · Score: 1

-- The teams get the GPS waypoints a few hours before the race. The waypoints are purposefully vague, so the robots have the choice of driving off a cliff (or into one) while still being within GPS parameters. This is supposed to prevent the race from reducing to "Who can follow GPS the best?" The Red Team had a group of what looked like 20 or 30 people who immediately sat down with the waypoints mapped out on satellite imagery, going through and adding waypoints of their own and adding speed commands for their robots. This seems to me to be a big violation of the spirit of the competition.

At first look I tended to agree with you, but after thinking about it for a little while I think the Red Team's strategy actually made a lot of sense for the ostensible goal of the competition. Assuming the purpose of the competition is to develop a system of autonomous supply vehicles for the military, extensive route planning would probably go into any actual operation. Theoretically you would have good imagery of the entire area already, along with intelligence on major obstacles - such as "this bridge is out", or "this road is completely unpassable because of bomb damage". The operator would then plan a fairly detailed route based on the best current intelligence. The whole obstacle detection and avoidance is the real kicker in this scenario - you already basically have a route planned, which you send your convoys along, but you can never be sure that some hazard (disabled vehicle, fallen tree, what have you) hasn't obstructed part of the route. The point isn't to develop a system that can find its own route, it is to develop a system that follows a pre-set route but with enough autonomy to avoid obstacles on the way. While it is a lot of work for the Red Team to prepare for the course, you would only have to do that once, then send however many vehicles you need along that one path.

On the other hand, Stanford's effort would achieve the same ends without as much planning - a more elegant solution. My point is simply that the Red Team's approach does make sense in terms of the goals of the challenge, and I would hardly call it cheating (though the apparent complexity of their system compared to Stanford's does seem to be a strike against them). That said, Stanley was much cooler :)
Re:Details in the program by gcanyon · 2006-03-29 09:02 · Score: 1

The Red Team's strategy makes sense for accomplishing the goals as expressed by the rules, but the rules do a poor job of representing the actual goal of the military (IMHO). The DARPA staff said on several occasions, GPS alone won't win this race. Well, it didn't, but only because of some sort of unrelated glitch in the Red Team's entry. Highlander would have won if not for the mystery ailment.

Agreed that in a military situation you're likely to have extensive pre-planning of the route, but you're not going to have driven it before. If it were safe to drive you'd have a person doing the job in the first place ;-)

So the robots in the field will be limited to GPS, satellite or aerial surveillance photos, and whatever smarts you can give them. You are exactly correct that the system shouldn't have to find it's own route, but what I meant by that is exactly what you said, "...a system...with enough autonomy to avoid obstacles along the way." If I throw a dozen tires across a ten-foot-wide dirt road, is the robot going to: A. stop and wait for help -- I win; B. turn around and go back -- I win; C. try to go to the left and end up at the bottom of a ravine -- I win; D. try to drive to the right up a hill, roll over and die -- I win; or E. realize (perhaps by cautious experimentation) that the tires aren't really an obstacle and drive over them at reduced speed -- I lose.

Stanley was certainly impressive. Having seen what the Red Team did, though, I have to wonder how capable Stanley's vision system is, and whether they also beefed up their data set before the race. Note that on a dirt road Stanley's vision system, which looks at the smooth road under it and then scans for that ahead, would be particularly susceptible to blockage by used tires (black on brown).

I will be much more impressed when the completion does two things:

1. Gives the team a cd at the start of the race, which the team then has to put into the robot's computer sight unseen. Obviously the data format would be specified ahead of time, but the team would get no chance to enhance the data set.
2. Gives a group of people the chance to play the enemy, with the opportunity to sabotage the robots by altering the path. At first the "enemy" would be limited: limited time and equipment. As the years go by, for this to be realistic, the restrictions on the "enemy" have to be lifted. As I said, if I were the enemy, I doubt any of the robots would have completed ;-)

David vs Goliath by TimothyJones · 2006-03-29 07:41 · Score: 1

Most interesting stuff. I was glad to see "Stanley" win. The "Highlander" and "Sandstorm" obviously had a lot of tech in them but "Stan" was clearily more reflective of the challange's merit - create a robot that can make decisions. The Red team crammed their vehicles with so much data it was like programming a production line robot. Yeah, it was a robot and a damn impressive one at that, but "Stan" could and had to actually decide things - and it did too. The idea of the laser + video overlay was most brilliant. While watching the program I could not help but been thrown back to those 80's films where the underdogs try to save some place against a heavy muscle of well oiled, militarily organized, and funded up the wazoo industrial juggernaut. Not trying to put down the Red team, obviously a brilliant bunch, but the VW was way [i]brilliant-er[/i].

MOD PARENT UP- this is DAMN relevant by bugg · 2006-03-29 07:45 · Score: 2, Insightful

As a student at Carnegie Mellon who has discovered the extent of his school's ties to development (had I known prior... and no, CMU is not unique in this regard, the problem is everywhere) of military products and has since spoken out against them a few times, thank you for realizing that this DARPA stuff isn't all it's cracked up to be.

I'm perhaps one of four people (an exaggeration, I hope) on my campus that isn't gung-ho about helping the DOD build driverless vehicles, and it's lonely at times.

Whatever moderator marked this down as off-topic was clearly just trying to limit the scope of discussion in the same way that DARPA and military contractors are trying to limit the scope of their moral and ethical liability.

--
-bugg

My Friend at CMU by gers0667 · 2006-03-29 08:50 · Score: 1

I had a close friend at CMU that worked on both of their robots. I got to visit them twice and see their production. H1lander wasn't there the second time because it had a transmission failure. They had to take it to the dealer. Can you imagine an H2 which is completely gutted, loaded with computers and has no steering wheel because it steers itself and having to take it to the dealer.

Also, both CMU robotos ran some form of linux with a all of the hardware donated by Intel. I believe they had a 2TB RAID for storage, a hand full of itaniums and bunch of Pentium M's to run their systems. I didn't get the full specs because my friend is an EE, but the numbers he gave me were pretty astonishing. And it was all donated.

Re:My Friend at CMU by da.maestro · 2006-03-29 09:22 · Score: 1

And it just paid off. Cos the reason Intel donated all that stuff was that people would say "hey, that was Intel hardware in that robot. Intel must be pretty damn cool! I'm gonna go buy a P4!"

--
Every rule has an exception. Except this one. Oh bugger...

and the choice of vehicles... by vistic · 2006-03-29 09:39 · Score: 1

So Stanford's vehicle was smart, and Carnegie Mellon's two vehicles were "dumb".

And guess what vehicles they started with? Stanford built around a Volkswagen diesel (Passat? Golf?)... and Carnegie Mellon worked with.... Hummers.

Very appropriate.

It was definitely brains (Volkswagen with sophisticated software) versus brawn (Hummer with less sophisticated mapping).

Google videos of Princeton's car by RyanCowardin · 2006-03-29 10:14 · Score: 1

Here are two videos I found on Google Video giving you a driverside view of an entire qualifiying round and another where the car rear-ends a parked car (autonomously drunk?).

Princeton DARPA Grand Challenge - NQE Run 5 Princeton University Prospect Eleven 12 min 38 sec

Princeton DARPA Grand Challenge - Crash Video Princeton University Prospect Eleven 54 sec

Re:Google videos of Princeton's car by RyanCowardin · 2006-03-29 10:17 · Score: 1

Sorry, I posted same URL for both videos above :( Correct link to the crash video is here

Correct "In-Formation" by Anonymous Coward · 2006-03-29 11:55 · Score: 1, Interesting

A bit torrent link to "Why We Fight".

http://www.mininova.org/tor/68961

Purchase this movie if you at all enjoyed it. That is your civic duty. True

Lessons from the winners/losers by Vellmont · 2006-03-29 12:16 · Score: 1

The most interesting thing I found from the race was the different approaches of the Stanford team who won, and the other teams. Stanford chose to work on the more difficult of the problems, which is the software side of things. They left the hardware of the car to people more adept at such things (Volkswagon). It was interesting to see the other teams focusing on the hardware problem, and leaving the software as less of a problem. The other interesting thing was seeing the different managerial approaches. The CMU team was headed by a former Marine with this "RA RA RA!" macho attitude. I thought the programmer who commented that he had "pretty much given up on sleep" was really telling to this approach. I'm a believer that pushing this hard only leads to bigger problems in the end (it's been scientifically shown time and time again that people make more and more mistakes with less sleep). Maybe the Macho RA RA RA attitude works well on battlefields, but it doesn't sound like it works well for developing science and technology. The CMU team basically lost because their vehicle broke down. The Stanford car sounded like it had no serious problems, and worked like the Stanford guys designed it.

In the end focusing on your strengths, and letting others do what you lack paid off for Stanford. Knowing your limitations (and not simply denying them) is a good attitude for success at anything. It's great fun to see a team with an approach you like beat everyone else.

--
AccountKiller

Things that Nova left out by code65536 · 2006-03-29 12:51 · Score: 1

It was a great program, and it prompted me to re-visit the old Slashdot article on this and to look a number of things up. Things that Nova missed:

* It mentioned the Gray team being a dark horse, but in reality, they took only about half an hour longer than Stanley. If anything, it was probably even more of a newcomer than Stanley. CMU has been in the robot driving business for a long time (they had neural-net based self-driving vehicles since the early 90's), so for this unknown team to finish so close to the others was interesting.

* The whole passing thing was a bit overhyped. According to what I read, if there is a passing situation, the chase vehicles will find a wide open area and pause the vehicle that was being passed. So H1ghlander should have been still while it happened. At least one of the robots that failed the race did so when it had problems restarting from a pause.

Re:Things that Nova left out by Anonymous Coward · 2006-03-29 15:47 · Score: 0

It mentioned the Gray team being a dark horse, but in reality, they took only about half an hour longer than Stanley. If anything, it was probably even more of a newcomer than Stanley. CMU has been in the robot driving business for a long time (they had neural-net based self-driving vehicles since the early 90's), so for this unknown team to finish so close to the others was interesting.

An unknown team that does surprisingly well is the very definition of "dark horse".
Re:Things that Nova left out by mhh5 · 2006-03-30 10:39 · Score: 1

The Gray team sounds totally amazing... If they had won, they would have made a profit on their entry. I wonder how many other teams who completed the course could say that.

Also, I'm curious to know the differences between the 2004 course/requirements and the 2005 course? They didn't use the same course did they?

I was on Red Team year 1 by CrazyJim1 · 2006-03-29 15:53 · Score: 1

I was skeptic robots would ever be able to finish in my old slashdot posts. Apparently they got the sensors right in the 2nd year and five competitors finished. I shoulda stuck around with Red Team year2, but I lost my key to the building and they wouldn't issue me another one.

--
God spoke to me.

Princeton's team and Future Grand challenge by chrisb33 · 2006-03-29 16:04 · Score: 1

I've gotten involved with the Princeton team that competed in the challenge - the cool thing about Princeton's car was that it relied only on GPS and stereo vision (no expensive lasers). The car didn't finish due to a programming bug, but the team took the car back to the course and was able to complete it after the race was over. If you're interested in Princeton's approach and how the car performed in both runs, here's a PDF that explains everything. In general news, DARPA has implied that they are going to announce another challenge soon; all they have said is that it will be "in an urban environment." Should be awesome!

Re:Princeton's team and Future Grand challenge by JhohannaVH · 2006-03-30 05:58 · Score: 1

I was *VERY* happy to see what Princeton came up with. The stereo vision was fooking RAD! Congrats, and I can't wait to read that PDF. I'm going to be looking for lots more info on the Urbania Race!

--
Sorry man... the Internet pooped on me.

Now lets see them do it in Snow by mrpickle2u · 2006-03-29 23:37 · Score: 1

I loved this show. I cannot wait for the day I will be able have my car take over driving. I spend most of my day commuting to and from my work area. I would love to be able to do other work while on the commute. Cudos to all the people involved in this endevor. It was brilliant. One thing bothered me though. The Stanley vehicle used laser and video cameras and differentiated by color the paths to use. If this technology is to ever be used in the public sector it will have to work in all enviroments. I dont believe that the current sensors they used for the race would work on an area covered by fresh fallen snow. The next competition should be in Michigan's upper penninsula

Saturday/Sunday by JhohannaVH · 2006-03-30 05:31 · Score: 1

I don't know where you are, but my HD PBS station rebroadcasts Tuesday's NOVA in HighDef on Saturdays and Sundays. KPBS is the local station here in San Diego... you might check your local website and see if they are planning on doing that. I plan to watch it again in HD. And kick my husband's arse if he snores through it again! :P

--
Sorry man... the Internet pooped on me.

135 comments