Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Stanford and Volkswagen Create Autonomous Vehicle

CowboyNeal posted more than 9 years ago | from the race-is-on dept.

Robotics 235

nght2000 writes "Stanford University has created an autonomous driving robot to compete in the 2005 DARPA Grand Challenge Race. The race will be held on October 8, 2005 in the desert Southwest. The team that develops an autonomous ground vehicle that finishes the designated route most quickly within 10 hours will receive $2 million. The route will be no more than 175 miles over desert terrain featuring natural and man-made obstacles. The Stanford Racing Team's vehicle is a Volkswagen R5 turbo diesel Touareg that was donated by Volkswagen of America. The Stanford Team has been working with the Volkswagen Electronics Research Laboratory on the project."

cancel ×

235 comments

hah! (2, Funny)

Bananatree3 (872975) | more than 9 years ago | (#12585535)

My lego mindstorms vehicle can beat this car any day! Except maybe on sand dunes, but oh wel.

YAY!!! (2, Insightful)

Vombatus (777631) | more than 9 years ago | (#12585722)

Herbie Rides Again

Re:YAY!!! (3, Informative)

NanoGator (522640) | more than 9 years ago | (#12586078)

"Herbie Rides Again"

I can't believe that Herbie is taking precedence over KITT here. I know it's a VW and all, but yeesh, KITT's got der bliken lights!

First. (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#12585537)

First.

Re:First. (-1, Offtopic)

crypto55 (864220) | more than 9 years ago | (#12585543)

Ha! You aren't even first... And besides, your post is hidden in my threshold...

stupid jew (-1, Troll)

Anonymous Coward | more than 9 years ago | (#12586240)

if his post is hidden, how did you know to reply to it, dumbass?

Red Team (2, Informative)

Anonymous Coward | more than 9 years ago | (#12585544)

Correct me if I'm wrong but isn't the bona fide leader in this competition the Red Team from Carnegie Mellon?

Re:Red Team (4, Interesting)

dangerz (540904) | more than 9 years ago | (#12585592)

Yes it is as far as I remember. Actually, one of my friends was telling me they're writing software to give the car the ability to powerslide.

Re:Red Team (1)

john_anderson_ii (786633) | more than 9 years ago | (#12586321)

I too believe you are correct.
Now if only the could work around that 256kb directory struct size limit CODA imposes on all directories in a volume, I'd be a very happy guy.

Re:Red Team (1)

beefstu01 (520880) | more than 9 years ago | (#12586389)

That's what everybody thinks, but I wouldn't get to cocky if I were them. A lot of other teams have a lot of potential, and with site visits wrapping up soon, we'll see who the real competitors are. Remember, they made 7 miles (not even 5% of the course) last year, so there's a LOT of room for improvement. Stanford, Cal Tech, Cornell and MIT are just four other colleges competing, and those guys aren't stupid, so watch out for them.

The people's car... (5, Funny)

FlameboyC11 (711446) | more than 9 years ago | (#12585552)

...without people! Gotta love that.

MOD PARENT UP (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#12585564)

That's actually clever! Volk = German for "people" Wagen = "car" (more or less) C'mon, have some humor!

Re:MOD PARENT UP (0)

Anonymous Coward | more than 9 years ago | (#12585610)

Thank you captain obvious.

Re:The people's car... (-1, Redundant)

Vombatus (777631) | more than 9 years ago | (#12585729)

Herbie rides again

Good thing, too... (4, Funny)

interactive_civilian (205158) | more than 9 years ago | (#12585785)

I'm glad they made it autonomous because I heard that the back of a Volkswagen is a very uncomfortable place.

;p

Re:Good thing, too... (4, Funny)

fbform (723771) | more than 9 years ago | (#12586053)

I heard that the back of a Volkswagen is a very uncomfortable place.

Only on Slashdot would that statement be qualified by "I heard that". :-P

Re:Good thing, too... (0)

Anonymous Coward | more than 9 years ago | (#12586202)

Have you not seen the movie in question?

"He wants to do her in a very uncomfortable place."
"Where, like the back seat of a volkswagen?"

And no, it's really not that uncomfortable... one of my exes had a jetta.

Re:The people's car... (3, Funny)

Penguinoflight (517245) | more than 9 years ago | (#12585826)

Kinda adds new meaning to their slogan "Drivers Wanted" huh?

Re:The people's car... (1)

DrEldarion (114072) | more than 9 years ago | (#12586256)

The picture in the article has "Drivers Not Required" painted above the wheelwell.

Re:The people's car... (0)

Anonymous Coward | more than 9 years ago | (#12585996)

...without people! Gotta love that.

Ummm...without people *driving*, you must mean. I can't think of a better blessing upon mankind.

Re:The people's car... (2, Insightful)

pcmanjon (735165) | more than 9 years ago | (#12586248)

"So what's the purpose of this? It's a waste of money and it will never benifit anyone. Why do people waste so much money on projects like this."

Actually, it DOES help with the goal of making cars that can drive themselves eventually. This could help lots of people who can't drive a car, or who wouldn't want to. Eventually leading to every car thats made being automatic.

That's a good thing, and it's not a waste of time. It's progress under the guise of a contest, to make it fun and competitive. There's nothing wrong with this.

Look at the big picture.

Uhhhh... No... (2, Insightful)

creimer (824291) | more than 9 years ago | (#12585565)

Just when you thought it was safe to cross the street...

Re:Uhhhh... No... (2, Interesting)

EdelFactor19 (732765) | more than 9 years ago | (#12585651)

maybe theyll make some autonomous pedestrians for the cars to avoid; now that would be entertaining to watch!

Re:Uhhhh... No... (1)

NightSpots (682462) | more than 9 years ago | (#12585879)

It's stanford ... at least the streets are wide enough that people can run. Put it in MIT and you'd have a much harder time getting out of the way.

Re:Uhhhh... No... (0)

Anonymous Coward | more than 9 years ago | (#12585924)

"The ultimate goal, Dupont said, is safer roads as future cars might help their drivers avoid accidents."
The ultimate goal, DARPA realizes, is an autonomous SUV driving the roads near the Syrain border firing an autonomous 30mm cannon at anything it autonomously feels like.

Re:Uhhhh... No... (1)

creimer (824291) | more than 9 years ago | (#12586184)

The ultimate goal, DARPA realizes, is an autonomous SUV driving the roads near the Syrain border firing an autonomous 30mm cannon at anything it autonomously feels like.

It might work better in Texas. They could try to do that in California but they would have to remove the cannon, use California-certified fuel and give one to Arnold.

I worked on this project for a few hours (5, Interesting)

CrazyJim1 (809850) | more than 9 years ago | (#12585577)

I only did some roadmapping for CMU. Outside of creating true artificial intelligence, only luck can win this goal. You map a route then calibrate your GPS, and hope the vehicle can stay on the road you drew, and hope it doesn't hit any obsticles in the way.

this specifically won't work (5, Informative)

Anonymous Coward | more than 9 years ago | (#12585613)

The course is specifically designed to defeat the gps+road map method of solving the puzzle.

It is guaranted that the vehicle has to pass through a tunnel or other type of obstruction that disables GPS.

Also, it is guaranteed that all roads will have obsticles at random locations that must be avoided. I understand that there are points where the vehicle must do an obstacle course and avoiding it or jumping over it is banned.

Re:this specifically won't work (5, Interesting)

Anonymous Coward | more than 9 years ago | (#12585690)

I'm working on the project for a different team. This can work. The competition is aimed towards making military vehicles that can drive autonomous. The military will look at satellite photos and choose a path for the vehicle to follow. The vehicle is then given these GPS points and must go. There will be cases where GPS may not be available for a short period of time; this problem is solved by an inertial navigation system, which uses gyroscopic sensors and accelerometers to give location based on the last known GPS location. There will also be situations where there will be obstacles and the vehicle must navigate through them using lasers and cameras. They are creating a real environment to test these machines in.

Re:this specifically won't work (1)

BigFoot48 (726201) | more than 9 years ago | (#12585757)

I can't wait to see how the vehicles unlock padlocked gates!

Re:this specifically won't work (1)

Dr. GeneMachine (720233) | more than 9 years ago | (#12585926)

Pf... Steer straight and accelerate hard towards gate... Where's the problem?

Re:this specifically won't work (3, Informative)

Nefarious Wheel (628136) | more than 9 years ago | (#12585810)

GPS isn't the only positioning system in existence -- GPS plus intertial navigation could do it. Inav sums micro changes in direction along a path to give you a resultant vector.

Re:this specifically won't work (3, Informative)

john_anderson_ii (786633) | more than 9 years ago | (#12586359)

It's true that GPS and "turn here", "turn there" technologies won't work, if that was all it took the U.S. Military could have done it themselves.

I do recall reading in Leatherneck magazine about a project the USN was undertaking involving unmanned subs that were to be used as long range sonar platforms and possibly very long range torpedos.

While operating underwater GPS is useless, but dead reckoning (Speed * Time = distance, distance @ bearing = position relative to start position) is still useful. The subs they were working on used a combination of surfacing for GPS, dead reckoning, and sonar navigation to avoid obstacles to reach their goal. I haven't read Leatherneck since I retired from the USMC, so I don't know what became of this project.

I think the point of this exercise is to use a mix of technolgies to accomplish the task. The most efficient mix, in theory, will win.

Re:I worked on this project for a few hours (1)

vishbar (862440) | more than 9 years ago | (#12585619)

Is this competition of any significance, then? If it's just a bunch of cars that follow a predetermined route, then it doesn't seem too exciting. The organizers of the event should hold the event at a random course with a maze of radio-emitting beacons that the "robot" has to follow. The robot would be forced to overcome the obstacles on the fly as opposed to following a predetermined course....

Re:I worked on this project for a few hours (3, Informative)

Anonymous Coward | more than 9 years ago | (#12585682)

No one has come even come close to the finish line on this race, so it would be very significant if a team was able to finish it. In 2004 "The furthest any of the teams had gotten was the Red Team's 7.4 miles" in a 150 mile course. http://en.wikipedia.org/wiki/DARPA_Grand_Challenge [wikipedia.org]

China and Autonomous Robots: the Military Angle (0)

Anonymous Coward | more than 9 years ago | (#12585692)

Stanford University and DARPA should designate this contest (of robotic technology) as "top secret". This technology would be a boon for the Chinese military, which has been aggressively trying to create a robotic soldier.

The Chinese aim to use robots to project the Chinese cruelty to all corners of the globe [phrusa.org] .

Re:China and Autonomous Robots: the Military Angle (1)

KlomDark (6370) | more than 9 years ago | (#12585963)

Which seems weird, as China has more humans to use as soldiers than anyone else.

Re:I worked on this project for a few hours (2, Interesting)

Urusai (865560) | more than 9 years ago | (#12585934)

The university I attended was planning to field an entry, and I had considered briefly going into reinforcement AI, having taken courses with the prof doing the entry. I don't think these challenges are doing AI research any favors. The trick to winning is no doubt like IBM's chess machine--hardware engineering, brute force, and optimization, rather than better algorithms. You end up with degenerate research that improves diminishingly at sort of working on the contrived problem at hand.

Reinforcement AI has promise, but it seems to have too much hand-waving and magic black box functions for its own good. Unifying it with algorithmics and logic AI would probably be more useful, but not nearly as sexy as RoboJeep terrorizing the desert fauna. They should award points for the ability to project flame or ripcut undergrowth, now that would be bitchin'.

Re:I worked on this project for a few hours (1)

KlomDark (6370) | more than 9 years ago | (#12585946)

What, an accurate odometer and electronic compass won't do the trick?

And that's just the simple solution. A truly skilled solution would also involve a camera and software to identify the road boundaries.

mac = great (-1, Troll)

stinkfinger1310 (885389) | more than 9 years ago | (#12585629)

linux sucks ass but people think it's cool anyway...

Re:mac = great (0)

Anonymous Coward | more than 9 years ago | (#12585632)

That's the best you can do?

What if... (1)

WhyCantIBeYou (875852) | more than 9 years ago | (#12585630)

Do they build in a self-destruct mechanism? I know it's the desert, but surely there's a congregation out there watching the goings on.

Re:What if... (1)

RallyNick (577728) | more than 9 years ago | (#12586327)

Oh shit, the car ran over a bunch of people. Must self-destruct to remove any evidence!

market potential? (3, Funny)

moviepig.com (745183) | more than 9 years ago | (#12585636)

The...autonomous ground vehicle that finishes...most quickly...will receive $2 million. The route will be...175 miles...featuring...man-made obstacles.

Bulk purchases of these robots, modified for high-speed runs of less than 30 minutes, is under consideration by Domino's Pizza.

CMU did this year ago (0)

Anonymous Coward | more than 9 years ago | (#12585637)

And anyway, wouldn't a robotic vehicle be more likely to run into pedestrians like school kids?

Re:CMU did this year ago (4, Funny)

creimer (824291) | more than 9 years ago | (#12585654)

And anyway, wouldn't a robotic vehicle be more likely to run into pedestrians like school kids?

Only if Grand Theft Auto was pre-installed.

Re:CMU did this year ago (1)

Biogenesis (670772) | more than 9 years ago | (#12585669)

Hopefully, if I ever get to work on one I'm going to program everything we know about Darwinism into the thing.

Re:CMU did this year ago (1)

Velox_SwiftFox (57902) | more than 9 years ago | (#12585683)

I think you should base the first robotic vehicle that can repair itself on an old Beetle. I think I could train my dog to change the cylinders on one of those.

Re:CMU did this year ago (0)

Anonymous Coward | more than 9 years ago | (#12585847)

they did it a year ago because its an annual competetion. There aren't any school kids running around on the competition course.

They're a bit optimistic.. (5, Insightful)

ElScorcho (115780) | more than 9 years ago | (#12585639)

The team that develops an autonomous ground vehicle that finishes the designated route most quickly within 10 hours will receive $2 million.

Considering no vehicle has made it more than a couple miles in these races before, I find it pretty funny that they include the "finished most quickly" bit. If anyone could finish at all it would be a huge leap forward. Some of the footage last year was pretty amusing. One in particular I remember was a big SUV looking vehicle that was really moving, made it about 2 miles before it got stuck. Seems to me they'd be better served if they laid off the emphasis on speed for the time being and just got to the point where a sharp turn can be safely negotiated.

Robotic Technology and the Chinese Military (0)

Anonymous Coward | more than 9 years ago | (#12585703)

Stanford University and DARPA should designate this contest (of robotic technology) as "top secret". This technology would be a boon for the Chinese military, which has been aggressively trying to create a robotic soldier.

The Chinese aim to use robots to project the Chinese cruelty to all corners of the globe [phrusa.org] .

Re:They're a bit optimistic.. (1)

hugzz (712021) | more than 9 years ago | (#12585828)

I'm sure it would be reasonably easy to do the race really slow. Most companies could probably make a car that can finish the track in a few months. that's not really worth 2 million though. What is valuable is being able to have an autonomous vehicle that can actually move at a speed which is useful to humans

Re:They're a bit optimistic.. (2, Informative)

SuprCzr (881969) | more than 9 years ago | (#12585994)

Theres a time limit to make sure that no one tries this... i believe you have ten hours from when you start to finish the ~150mi course... you do the math.

Re:They're a bit optimistic.. (3, Funny)

sturat (139743) | more than 9 years ago | (#12586161)

Seems to me they'd be better served if they laid off the emphasis on speed for the time being and just got to the point where a sharp turn can be safely negotiated.

This is the same advice I give to my mother and it's yet to have an effect.

Not quite. (0)

Anonymous Coward | more than 9 years ago | (#12586328)

The competition is at least 10x more serious this time. The competitive teams could already surpass last year's best earlier this year and have had months to improve robustness.

There are a lot of teams out there that are making the mistake of assuming that the competition is as easy as it was last year...

But how many humans can do the job? (3, Insightful)

tftp (111690) | more than 9 years ago | (#12585642)

Driving a 4WD in a desert, with obstacles and detours, arriving at a destination within a time limit... I dare say not every human driver is up to the task. And they want to achieve this with a computer?

Re:But how many humans can do the job? (1)

PoopJuggler (688445) | more than 9 years ago | (#12585657)

They held this contest last year too. I don't think any vehicle made it more than 100 yards. One team made an autonomous motorcycle, which fell over about 5 feet past the starting line...

Re:But how many humans can do the job? (2, Interesting)

good-n-nappy (412814) | more than 9 years ago | (#12585807)

The motorcycle was pretty sweet though. It used only steering to keep it balanced rather than doing the whole Segway thing. You got to at least admire the engineering on that one. I heard the guy running it say that he was sleep deprived and forgot to turn on the auto-balance thing right before the race. That's why it only went about 5 feet. They knew they wouldn't be able to finish in time anyway.

Re:But how many humans can do the job? (3, Interesting)

Eivind (15695) | more than 9 years ago | (#12586195)

Actually, the course is by no means that hard. It's no longer than 170 miles, and you've got 10 hours, that means an average speed of 17 will do it.

Parts of that is paved roads, parts unpaved roads and parts "offroad". This means you can do like walking-speed on the offroad-parts and still manage it fine.

Infact I'd take a bet that 9 out of 10 got-drivers-license-yesterday humans would be able to do this in less than half the time allocated to the robots, probably a good driver would do it in a quarter the time the robots get. That'd require him to average 68mph.

Re:But how many humans can do the job? (2, Funny)

d474 (695126) | more than 9 years ago | (#12586230)

The desert is the easy part. What I'd like to see is thing commute in L.A. rush hour traffic.

What do you get when you cross ... (1, Funny)

lheal (86013) | more than 9 years ago | (#12585644)

Stanford University and Volkswagen?
  • Lunch. Cardinals love beetles. Mmmmm, beetles.
  • A really smart, pricey, air-cooled, diesel-powered, politically correct skateboard ... that floats!
  • A driverless car. Wow, that's kinda cool.

I wish I had more, but I kinda ran out of gas. Really I should have hit the brakes after the first one, but once I'm in gear I can't stop until I crash and burn.

Mod Parrent.... (2, Funny)

Zeebs (577100) | more than 9 years ago | (#12585666)

What slashdot really needs is a +1 *Groan* Mod, but I suspose you'd need to do some work under the hood for that. Someone should really get in gear on this.

Crap....

Re:What do you get when you cross ... (1)

kidgenius (704962) | more than 9 years ago | (#12585999)

Except that Stanford is not the "Cardinals" as in the bird, but the "Cardinal" as in the color red.

Re:What do you get when you cross ... (1)

lheal (86013) | more than 9 years ago | (#12586010)

>the color red

Oh. How gay.

Yes.. (0)

isny (681711) | more than 9 years ago | (#12585646)

but how big is it in standard Volkswagen units?
Oh...sorry

Watch for my Jetta... (1)

jmcmunn (307798) | more than 9 years ago | (#12585709)


Ha, I am going to enter my Jetta which will be piloted by my Robosapien that I picked up at Best Buy. It'll blow that Touareg out of the water!

I wish them well (0)

Anonymous Coward | more than 9 years ago | (#12585720)

I wish them well and want to inform them that, if their vehicle holds up as well as the rubberized door handles on my wife's New Beetle, they're doomed.

Re:I wish them well (0)

Anonymous Coward | more than 9 years ago | (#12585742)

I'm thinking that breaking a door handle on an autonomous vehicle isn't going to be a big issue.

Google / Stanford team too? (4, Interesting)

chachacha (833677) | more than 9 years ago | (#12585771)

I was driving through campus near the Stanford Golf Course the other day and saw a robotic solar vehicle emblazoned with the Google and Stanford logos. There was a large van outfitted with all sorts of sensors and gadgets on the roof and hood. Has anyone heard of Stanford attempting to build a robotic solar-powered car too?

Re:Google / Stanford team too? (0)

Anonymous Coward | more than 9 years ago | (#12585794)

That's the Stanford Solar Car project [stanford.edu] Not robotic, human driver

Herbie! (4, Funny)

rossdee (243626) | more than 9 years ago | (#12585821)

Didn't VW do an autonomous vehicle back about 1970 (in association with Disney)

But the Love Bug really lost its luster (1)

rjamestaylor (117847) | more than 9 years ago | (#12586032)

with the advent of HIV and all

Re:Herbie! (2, Informative)

Garabito (720521) | more than 9 years ago | (#12586176)

Yes, but they did it again. Fully loaded [go.com] now.

Re:Herbie! (1)

jerryasher (151512) | more than 9 years ago | (#12586371)

Yeah, Audi had one too around 1986.

Watch out for that tree! (1)

chachacha (833677) | more than 9 years ago | (#12585838)

It would be kinda' ironic if it crashed into a tall tree, then got broken into by a bear during it's journey.

Re:Watch out for that tree! (1)

BiggerIsBetter (682164) | more than 9 years ago | (#12585979)

George, George,
George of the Jungle,
Strong as he can be.
(Ahhhhhhhh)
Watch out for that tree!

"On the road of life... (5, Interesting)

samkass (174571) | more than 9 years ago | (#12585846)

"There are passengers and there are drivers. Drivers not wanted."

As someone who went to CMU, I'm of course rooting for the home team, but it is fun to read about the other guys. For the on-road stuff, they had those trucks zipping driver-less, pretty fast, through Schenley Park back in the 90's, so it'll be interesting to see if they can keep on the trail this time for the off-road challenge.

Hi Stanford & CMU (1, Interesting)

NitsujTPU (19263) | more than 9 years ago | (#12585892)

See you folks at the race.

-Cornell

Re:Hi Stanford & CMU (1)

hendrik42 (593357) | more than 9 years ago | (#12586009)

Earlier this month there have been site visits conducted by DARPA to narrow the field down to 40 contenders. Judging from the reports posted on the DGC Forums [darpa.mil] , the field is much stronger this year. A lot of people believe there will be at least one team to finish this year.

Does anyone know a bookie accepting bets on the outcome? With 117 teams still in the race and plenty of media coverage there would be a huge market.

Go Stanley!

You brake, I brake. (1)

bronney (638318) | more than 9 years ago | (#12585908)

Show me a computing power that enables you to run over skunks versus kids. If you see a kid, you look into the mirror, and brake enough. The car on the back brakes enough but hits your bumper anyway, broke it, you get out of the car, and it's just money. But you saved a kid. If the same thing happens with a skunk, how're you gonna feel. Or if you're following a robotic car and it brakes suddenly, and you didn't brake or steering away fast enough and smash your head in the windshield~.. hmm

Re:You brake, I brake. (0)

Anonymous Coward | more than 9 years ago | (#12586098)

You should reword that.

Re:You brake, I brake. (1)

Velk (807487) | more than 9 years ago | (#12586213)

There's a reason that in a rear end accident the driver behind is almost always automatically assumed to be at fault.

If you can't stop without hitting them if they brake suddenly, you are too close.

CMUers (0)

Anonymous Coward | more than 9 years ago | (#12585973)

-- read this as "Stanford plans to outdo CMU autonomous robotics researchers".

You're not going to take that lying down, are you?

I only have one thing to say.. (2, Funny)

robpoe (578975) | more than 9 years ago | (#12585992)

Fukengruven!!

Re:I only have one thing to say.. (1)

Exluddite (851324) | more than 9 years ago | (#12586268)

Given the outcome of last years race it'll probably be more like Farfromfinishing.

Combine with the other car dream (2, Informative)

Wizarth (785742) | more than 9 years ago | (#12586063)

One of the advances that would be a lot more likely once this is done is: Flying Cars.

The biggest complaint against flying automobiles is how every-one (and their dog) would be able to drive (fly) like a bat out of hell. Literally, in this case.

So, get autonomous driving working, get people used to it on the ground, then going airborne is just a next step.

I Cried (3, Interesting)

LordMyren (15499) | more than 9 years ago | (#12586147)

I cried when I saw how the DARPA desert race was done. I was thinking vehicles actually had to do pathfinding, you know, like, interesting stuff.

Thats simply not the case. DARPA hands out the final destination a day before launch and the teams madly scramble to find a route to send their vehicle down (on nice sat photos). Then they send the vehicle off on its own. What sort of fun is that?

Knowing this, I'm ashamed how poor last years competition was. The winning team was pretty sweet, but I certainly expect a lot more competitive entries this year. Hand most any college worth its salt $25,000 and let the CS & ME's go to. In a year they should build something which could at least contend with the DARPA incumbent.

As it stands the whole thing requires almost no intelligence. The whole point, from a computer engineers' biased persepctive, was to get people building robots aware of their surroundings. The Berkeley city auto-mapper robot is a perfect example; couple that with Sandstorm and then maybe I'm interested. But so many teams can make a robot which FAILS to track a GPS path while staying moderately on the road is just beyond me.

I understand the whole point is that the terrain is supposedly "hostile"... But when you're driving an `86 Hummer, its quite apparent that any area full of enough dangerous terrain to give you a problem will likely be seen on the sat-maps.

Myren

Re:I Cried (1)

bryce1012 (822567) | more than 9 years ago | (#12586225)

I see and respect your sickeningly low UID. Nonetheless, I think you're totally mistaken here.

Before you can walk you have to learn to crawl. Right now there are issues with even the simple stuff, like you said - these robots fail to track a GPS path while staying on the road. Surely you don't think that all 100+ teams just didn't put enough effort into that one aspect? So they have to ask, "Why?" What problems were being encountered? How can they be resolved? These are the simple issues that must be identified, solved, refined, etc.

Sure, your concept is much cooler and definitely more useful. All the same, it's obviously not completely feasible at this point.

Re:I Cried (1, Informative)

Anonymous Coward | more than 9 years ago | (#12586302)

The winning team was pretty sweet, but I certainly expect a lot more competitive entries this year.

There was no winning team.

You fucking idiot.

Re:I Cried (1)

chinakow (83588) | more than 9 years ago | (#12586314)

You do realize that no one "won" last year, right?

The team that failed the least horribly only made it a dozen or 2 miles before the converted Hummer broke an axle, some of the "finalists" never made the first turn at about 50 feet. so I would say that it is actually pretty tough even given a CD with all the GPS coordinates and course widths.

Of course all of this is from memory so everything above is probably factually incorrect except that NO ONE made the entire trip autonomously, within the time limit or not.

Unless you are talking about some other DARPA desert race besides the Grand Challenge, in wich case all of your above statements might be right. so take this all with a grain of salt.

Also, why are people so fascinated with low user ID numbers?

175miles @ 10 hours = 17.5mph (1)

YuriGherkin (870386) | more than 9 years ago | (#12586169)

Looking at the events (read: disasters) of last years race I really don't understand why people try and make their cars go so fast.

175miles @ 10 hours = 17.5mph

Ok, so travelling at an average speed of, say, 18mph you might not finish the race in time if you have any delays BUT you will probably get a lot further than anyone else because:

a) it's much easier to crunch the vast amount of data needed for navigation at a slower speed

b) if you crash at a slower speed, it's not so bad (duh!)

c) the chances of rolling are proportional to the square of your speed:
radial acceleration (which will roll you) = speed^2 * radius of turn

d) braking distance is equal to the square of your speed (kinetic energy = 1/2m.v^2), so at slower speeds it's MUCH easier to stop if something is only detected at the last minute.

Remember the humvee from Carnegie Mellon? Remember how it got a rolled a couple of times during their development because it took a corner too fast? (and crushed the expensive equipment that was mounted on the roof) Humvees are pretty hard to roll, and most modern cars contain electronics that try to stop a car from turning too fast and rolling ... that car cost $3million yet no-one thought to put in something that will do something like:

if speed > x then don't turn too fast!

It makes you wonder what they teach at that university.

Re:175miles @ 10 hours = 17.5mph (0)

Anonymous Coward | more than 9 years ago | (#12586197)

If it's all so easy why don't you just start your own team? Like those 195 other teams this year who have some of the nation's smartest persons working on this. Just some points to consider:
  • There are speed limits imposed by DARPA, based on safety considerations. Every time the race comes close to humans or something expensive (like a power tower), the robots have to drive 5mph.
  • Those speedlimits are just for the safety of others. In turns, mountains etc you don't want to go fast either, for the safety of your own car. So you'll be doing a lot of slow driving and you have to make up for it.
  • You don't know if finishing in 10 hours would be enough to win this race! Last year it would have but this year there are a number of strong teams.

Hey, VW, how about making diesel cars (1)

melted (227442) | more than 9 years ago | (#12586187)

Hey, VW, how about making diesel cars available in the US instead (I mean not just Golf and Beetle)? With the prices we're paying for gas right now, they'd sell like freakin' hot cakes.

Re:Hey, VW, how about making diesel cars (1, Insightful)

Anonymous Coward | more than 9 years ago | (#12586273)

What the hell vehicle do you want?

Golf. Check.
Beatle. Check.
Jetta. Check.
Passat. Check. (after a little bit of a dry spell.)
Touareg. Check (V10 Goodness, new for 2005)

Lupo?

http://www.tdiclub.com [tdiclub.com]

Re:Hey, VW, how about making diesel cars (1)

wahsapa (767922) | more than 9 years ago | (#12586350)

VW cant pass california smog. california has THE most stringent emissions regulations in the WORLD. which VWs diesels can't/barely can pass.

in fact, a couple months back i remember reading about a mans quest to find a new diesel beetle and no VW dealer would sell it to them because they are trying to 'conserve' their 'emission points' to sell the tourag v10.

you cant get the v10 diesel tourag in california btw, atleast not yet

Re:Hey, VW, how about making diesel cars (0)

Anonymous Coward | more than 9 years ago | (#12586360)

I have heard that the reason VW does not sell more diesels is due to emissions -- the diesel fuel in the US is not as clean as that in Europe, so it burns dirtier.

I have heard of people waiting over 1 year on a waiting list to get a TDI (diesel) VW.

Let me venture a guess... (2, Insightful)

d474 (695126) | more than 9 years ago | (#12586208)

FTFA:
"Pamela Mahoney...said her firm hopes that technologies conceived during the project might lead to "really interesting applications that could generate new start-ups.'"
Really interesting applications... like maybe, heavily armed "hunter-killers" patrolling around outside NWO prison camps looking for escapees to eviscerate? How about enforcing curfews in (American?) urban streets during martial law after a "terrorist" attack? Gee, how could DARPA possibly find a use for these technologies?

*Remove tinfoil hat*

Hire a Berkeley team and get it won (0)

Kmow (885426) | more than 9 years ago | (#12586279)

VW and Stanfurd ? BMW should contact Berkeley and get this thing won...Stanfurd people don't even have to finish their courses -- they can just drop out and start again at any time -- how can they ever meet a deadline ? Hey BMW, give Cal a call and squash these overpaid and underworked right-wing fart-arounds.

Rugged travelling salesman problem (0)

Anonymous Coward | more than 9 years ago | (#12586290)

It would be extremely interesting to see what technologies the contestants are putting to work in their quest to win this thing. I remember reading a piece about genetic classifier systems that used the example of "maze running ants" to describe a method of evolving solutions to maze running problems. It would be extremely interesting to see the same idea applied to this problem such that the navigation strategy of the vehicle is controlled by an evolving set of genetic classifiers which are rewarded by the degree to which they avoid peril and move toward the target.

From what I've read, genetic algorithms are one of the fastest ways out there to solve path optimization problems such as the "travelling salesman" scenario. On the surface it looks like a very similar problem to me. Anyone know if this is being or has been tried in this contest?

My school is in this competition (4, Interesting)

Antilles (49894) | more than 9 years ago | (#12586295)

I dont understand why their team is getting this much press, other than the fact that Volkswagen's PR dept is probably hyping stanford to get some marketing exposure for their company, as this year almost 200 teams applied to get site visits.

In terms of technology, well, outside of the Turing test, this is sorta like the Super Bowl of AI. My team/part of the project dealt with Machine Vision, which has proven to be quite difficult for a lot of people (including me!). Real time scene analysis is *very* computationally expensive, and you have to make guesses and inferences as optical signal data fluxes around constantly, a lot of the time completely rendering your approach useless.

Even though from life experiences I know that Life Isnt Fair, and the playing field is never level, some of these teams get insane advantages. I wont even go into CMU (ok, I will: they have basically Defense Contractor backing, parts, and consultants, and like 7 million dollars to spend on the project), and here stanford has sponsorship with volkswagen. I was suprised Cal Tech didnt get more major sponsors, but they might have for round 2 of the challenge. No one has near the advantage of CMU though, their main LIDAR cost more than a lot of people's whole car/setup.

Aside from that, for me this project has been a blast. The work, needless to say, is very unique and its almost like a mini-1960's space race, "first one to the finish line!". Its funny how some people try different angles, spend millions of dollars, and then get foiled by a rut in the road that hangs their car up (I'm tellin ya, if the sun shifts even slightly all vision input outside of lidar can basically go to sh!t if you arent careful, and if your lidar doesnt pick it up, well...)

Regardless of whoever makes it to the top 30, it will be interesting to see if anyone finishes this year. Darpa3, maybe?
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...