Forgot your password?
typodupeerror
Robotics Technology

Stanford and Volkswagen Create Autonomous Vehicle 235

Posted by CowboyNeal
from the race-is-on dept.
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."
This discussion has been archived. No new comments can be posted.

Stanford and Volkswagen Create Autonomous Vehicle

Comments Filter:
  • hah! (Score:2, Funny)

    by Bananatree3 (872975)
    My lego mindstorms vehicle can beat this car any day! Except maybe on sand dunes, but oh wel.
  • Red Team (Score:2, Informative)

    by Anonymous Coward
    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 (Score:5, Interesting)

      by dangerz (540904) <stuff@noSPam.tildastudios.net> on Thursday May 19, 2005 @11:03PM (#12585592) Homepage
      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.
    • 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.
    • 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.
      • Re:Red Team (Score:2, Insightful)

        by lowrydr310 (830514)
        Yes, but the Carnegie Mellon Team has a very strong advantage. Keep in mind that last year their vehicle rolled over during tests just a few days before the competition, and they had to replace just about all the electronics - they STILL made it farther than anyone else...

        Not only do they have a well designed system, they're using a Hummer H1. I know it doesn't matter what vehicle wins, but when you're competing in a DARPA funded contest, using a HUMMER is more impressive than a VW.

  • by FlameboyC11 (711446) on Thursday May 19, 2005 @10:56PM (#12585552)
    ...without people! Gotta love that.
    • by interactive_civilian (205158) <mamoru@gma i l . com> on Thursday May 19, 2005 @11:46PM (#12585785) Homepage Journal
      I'm glad they made it autonomous because I heard that the back of a Volkswagen is a very uncomfortable place.

      ;p

    • by Penguinoflight (517245) on Thursday May 19, 2005 @11:57PM (#12585826) Homepage Journal
      Kinda adds new meaning to their slogan "Drivers Wanted" huh?
    • by pcmanjon (735165)
      "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 no
      • by netsphinx (619340) on Friday May 20, 2005 @02:35AM (#12586467)

        God, yes.

        I live in Atlanta. I work on one side of town, I room on the other. I go 25 miles each way. Average speed of 25mph. That's 2 hours a day I spend in the car.

        If I could get into my car, type in a destination, and read, have breakfast, catch the last 10 winks, or write the great American novel while the car did the work, I would jump at it like a shot.

        I realize that what I want out of an autonomous car is available, mostly, as public transportation. Unfortunately, public transportation in Atlanta is a joke. To do the 25 miles from my house to the office takes 2 hours, on 2 different systems, with three transfers. That's 4 hours a day in transit, provided nothing breaks down and the buses aren't late. I tried it, and I had just enough time left over in the day to sleep. Not eat, just sleep.

        I saw a test car and strip of highway (somewhere in California, IIRC) that worked together as an autopilot. Drivers could enter the freeway, tell the computer what exit they wanted to get off at, and let the car drive itself. Little pips in the tarmac told the car where the lanes were, the on-board did the steering, and the central controller managed congestion by telling the cars what speed was best for the volume of traffic, when to change lanes, and when to wake (pardon me, alert) the driver that the exit was near.

        Anyone out there remember this? Is it still under development?

        Anyone care to speculate how soon I can get a robot chaffeur or auto-highway?

        And does anyone remember...Sally? Asimov fans will know what I mean.

      • DUI (Score:3, Interesting)

        by hawk (1151)

        In addidition to convenience, autonomous, or even street-directed, vehicles could nearly eliminate the problem with DUI.

        With smart streets, traffic control could also be much improved, with, for example, the freeway directing vehicles to shift position slightly for injection of merging vehicles.

        Speeds could be significantly increased, and vehicles could be placed on bulk carriers (e.g., trains).

        With good enough control and timing (many years after initial introduction), vehicles could be sent through int
    • by rackrent (160690)
      So does this mean we can all take a "Johnny Cab" just like Gov. Schwarzenegger in Total Recall?
  • Uhhhh... No... (Score:3, Insightful)

    by creimer (824291) on Thursday May 19, 2005 @10:58PM (#12585565) Homepage
    Just when you thought it was safe to cross the street...
    • Re:Uhhhh... No... (Score:2, Interesting)

      by EdelFactor19 (732765)
      maybe theyll make some autonomous pedestrians for the cars to avoid; now that would be entertaining to watch!
    • 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.
    • anyone else having "herby" flashbacks.... maybe just me.... i hope not though...
    • Just when you thought it was safe to cross the street...

      Don't be a chicken.

      ---------
      Remember, drive defensively! And of course, the best defense is a good offense!
  • by CrazyJim1 (809850) on Thursday May 19, 2005 @11:00PM (#12585577) Journal
    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.

    • by Anonymous Coward on Thursday May 19, 2005 @11:07PM (#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.

      • by Anonymous Coward on Thursday May 19, 2005 @11:23PM (#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.
      • by Nefarious Wheel (628136) on Thursday May 19, 2005 @11:54PM (#12585810) Journal
        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.
      • by john_anderson_ii (786633) on Friday May 20, 2005 @02:05AM (#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.
      • It is guaranted that the vehicle has to pass through a tunnel or other type of obstruction that disables GPS.

        Guess you're a little behind on GPS-gyros. Here's an example:
        http://www.brilliant-electronics.com/car_positioni ng_system_kenwood_knadv4100.htm [brilliant-...ronics.com]
      • t there are points where the vehicle must do an obstacle course and avoiding it or jumping over it is banned.

        Swell.

        *Now* what am I supposed to do with this JATO unit?

        I suppose that I could mount it in the back of my father's old Chevy wagon . . .

        hawk
    • 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.
  • by moviepig.com (745183) on Thursday May 19, 2005 @11:11PM (#12585636) Homepage
    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.

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

      Music, movies, microcode and... yep, here it comes. It'll be robots doing the delivery and not samurai or skaters, but near enough I suppose.

  • by ElScorcho (115780) on Thursday May 19, 2005 @11:12PM (#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.
    • 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
    • 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.
    • 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.
  • by tftp (111690) on Thursday May 19, 2005 @11:13PM (#12585642) Homepage
    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?
    • by Eivind (15695) <eivindorama@gmail.com> on Friday May 20, 2005 @01:16AM (#12586195) Homepage
      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.

      • by zero_offset (200586) on Friday May 20, 2005 @07:22AM (#12587410) Homepage
        You've clearly never driven off-road. Indeed, with your statement that somebody could average 68 MPH in terrain like this demosntrates that you've probably never raced in your life, either.

        Even in relatively benign terrain, a speed of about 15 MPH is actually moving pretty quickly. These aren't $2M one-time-use lightweight 500HP Paris-Dakar desert racers with a navigator, an 8-ton supply-laden chase truck. These are extremely heavy fully autonomous machines. If you read the rules, they're even supposed to refuel themselves without human intervention should it become necessary. It's really, really easy to break stuff at only 15 MPH, particularly when you consider how heavy these robots are.

        Also, the paved sections are very short -- I haven't looked at the 2004 course in quite awhile and I'm not sure if the 05 proposed courses are up yet, but it was something like only 10% of the entire route -- and then you're not permitted to exceed the speed limit, which I think was pretty low -- 50 MPH or thereabouts.

        It's very, very hard.

        • "clearly" in your world seems to mean very very fogged.

          First, "terrain like this" in this case means a mix of paved roads, unpaved roads, trails and "desert". It does *not* like you seem to think mean "offroad-only", I was never suggesting even a skilled driver would do 68mph average on the off-road sections.

          You're correct that the speed-limits migth prevent even a skilled driver from completing in a quarter of the alloted time, obviously if he can't go over say 55 even on the paved parts that's going

          • You are only reenforcing the fact that you have probably never really gone "off-road" or ever raced in real life. Off-road in this sense doesn't mean "gravel road" or sand as you seem to think; it means hilly rock strewn landscape. It is amazingly easy to flip or snap an axle (which happened to the leading team last year) and most drivers would simply not be up to the task.
          • Last year's Dakar rally had about 5400 km of 'special stage' (where the cometitors are timed, as opposed to liaison routes that are untimed, and add another ~5600 km to the trip), with the fastest competitors completing those in about 52 hours, ie about 100 km/h.
            There are stages where the fastest cars reach about 200 km/h. Other stages took more than 24 hours for some people (average 20 km/h), but most of that would be spent standing still and digging the vehicle out.
    • The desert is the easy part. What I'd like to see is thing commute in L.A. rush hour traffic.
    • I dare say not every human driver is up to the task. And they want to achieve this with a computer?

      Aspects of it are close to production ready now http://www.mmsi.com/autonomous.shtml [mmsi.com], including schedules, obstacle avoidance and more. The flaw with current autonomous vehicles for this test is the need to train them. I still reckon an autonomous 210 tonne dump truck would get further than most of the competition though, especially if they got in its way early in the race.
  • 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.


  • 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!
  • by chachacha (833677) on Thursday May 19, 2005 @11:42PM (#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?
  • Herbie! (Score:5, Funny)

    by rossdee (243626) on Thursday May 19, 2005 @11:56PM (#12585821)
    Didn't VW do an autonomous vehicle back about 1970 (in association with Disney)
  • by samkass (174571) on Friday May 20, 2005 @12:03AM (#12585846) Homepage Journal
    "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 (Score:2, Interesting)

    by NitsujTPU (19263)
    See you folks at the race.

    -Cornell
  • by robpoe (578975) on Friday May 20, 2005 @12:30AM (#12585992)
    Fukengruven!!

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

      You've got it very backwards. Airplanes have been flying autonomously for more than a decade. Flying is very well suited to automation, driving is a much more difficult problem. The aviation industry has reached the point now, under recent reduced separation rules, there's a lot of pieces of airspace where manually flying the airplanes isn't even permitted anymore.

  • I Cried (Score:4, Interesting)

    by LordMyren (15499) on Friday May 20, 2005 @01:01AM (#12586147) Homepage
    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
    • 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 o

    • Re:I Cried (Score:4, Interesting)

      by daniel_mcl (77919) on Friday May 20, 2005 @02:29AM (#12586439) Homepage
      Actually, several teams (including my school's) did use pathfinding, and did a pretty decent job of it as well. The CMU team was one that preprogrammed the entire path, and they got one of the best scores, largely because it's really, really hard to develop an autonomous robot in your spare time while attending classes all day. It also doesn't help not to be able to run very many tests on site.

      For instance, my school's robot was doing well until it hit a chain link fence. As it turned out, the chain-link fence was almost invisible to the car's vision system -- think about it, it's a bunch of air with these little tiny lines which are pretty hard to distinguish from debris in the air and such. You try writing a computer program that can accurately determine the presence of chain link fencing in a photograph and then see what you think.

      As for GPS, again it doesn't tell you whether there's a fence, cow, brick wall, etc. standing in the way, and GPS was blocked for large sections of the course. If you're suggesting dead reckoning instead, note that that's really, really hard even under ideal conditions and essentially impossible outdoors. If a car gets one degree off course and travels 60 miles, it'll end up a mile off of the road, perhaps gleefully crashing through houses / oncoming traffic.
    • The waypoints are given to each of the teams something like 3 hours before the beginning of the race. My school's team then takes the CD and puts it into the onboard computer system which then does everything. Certain other teams have (in the past :) simply used the time to specify an exact course themselves, resulting in little useful technology for the military like you said. Our vehicle staying within 20 cm of the computed path, mostly due to the actuators because the vehicle was built by us as oppose

    • ...and yet nobody has won. Methinks you underestimate the difficulty of this task a tiny bit (all too common in computer vision and AI). If more than two or three of this year's teams succeed, I will agree with you in saying it was too easy. But nobody says the challenge must end after somebody wins; DARPA will likely increase the difficulty and hold it again. After all, their goal is a useful combat vehicle and even the winner of this contest would still be a long way away.
      • Methinks you underestimate the difficulty of this task a tiny bit (all too common in computer vision and AI).

        In my experience getting a car to follow a precalculated path at decent speed in the first place is quite hard, even in a simulation.

        I did this for a game running on a karma physics engine, and I was not allowed to cheat with physics. Controlling oversteer and understeer, and accurately predicting the consequences of wheels loosing contact with the ground, is a lot harder than I expected, even in
    • I was thinking vehicles actually had to do pathfinding, you know, like, interesting stuff.

      Actually, if you had read a little bit about the competition, you would know that there start/end points and designated waypoints, along with acceptable corridors of varying widths between and around those waypoints. The "routes" that were pre-loaded could only be considered recommendations, at best.

      As it stands the whole thing requires almost no intelligence.

      While not a competitor, I was very close to one of th
  • 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.
    • by Gulthek (12570) on Friday May 20, 2005 @08:49AM (#12588006) Homepage Journal
      What the deuce? I've been driving around in a Jetta Wagon TDI for two years. The only reason we got a Jetta TDI instead of a Passat is that the Passat isn't available with a manual transmission.

      Golf, Beetle, Jetta, Passat, Toureg are all available with TDI engines. Try em out, but the waiting list is pretty lengthy because they are selling like freakin' hot cakes.

      My wife and I keep our TDI pumped with biodiesel too. Less emissions, less smell, and our gas was living plant material mere years (or months) ago. Staying in the current carbon cycle is better than releasing carbon stored millions of years ago.
  • by d474 (695126) on Friday May 20, 2005 @01:21AM (#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*
  • by Antilles (49894) <jpatterson AT realtycenter DOT com> on Friday May 20, 2005 @01:49AM (#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?
  • Well! If this robot as the same electrical wiring as all the north americain volkswagen made in mexico! he's not gonna make it at all!!!!!
  • It's a good thing, given they are using a Volkswagen, that part of the criteria for winning isn't being able to autonomously open or close the likely non-working power windows.
  • by PMuse (320639) on Friday May 20, 2005 @11:22AM (#12589663)
    there are passengers, and there are drivers. And there are vehicles that don't want either.

    Great. That's just great.

A failure will not appear until a unit has passed final inspection.

Working...