Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
Technology

Preparing for the DARPA Autonomous Vehicle Challenge 155

Little Hamster writes "Post-gazette.com has an interesting article on the DARPA funded 200-mile autonomous vehicle race across the California-Nevada desert. They interviewed teams from two of the early favourites, Carnegie Mellon University and the California Institute of Technology. The teams talked about challenges on driving at high speed over a combination of roads, rough terrain and brush-covered desert, where the robot would need to consider how fast it can make a turn, the possibility of spinning tires and the potential to become airborne when hitting bumps."
This discussion has been archived. No new comments can be posted.

Preparing for the DARPA Autonomous Vehicle Challenge

Comments Filter:
  • Just fly over the desert :P
  • by Anonymous Coward
    Just mount a versalaser on it, remove the laser safety shroud, set it loose in Iraq and let it carve "WWJD" on all the terrorist's foreheads...

    They'd kill each other after that...
  • by Anonymous Coward
    And if the source code that runs the thing ever goes public, then the vehicle gets remarkably easier to target, given another computer and a detailed topomap of the area.
    • by autopr0n ( 534291 )
      Well, it will always be "easy" for a computer to figure out the 'optimal' path through terrain. (of course, by "easy" I mean "NP-hard", but a computer could figure out the best easily-findable paths that another computer would probably use)

      This gets into game theory, i.e. choosing certain sub-optimal paths in order to reduce 'predictability'.

      If you're using simulated annealing or genetic algorithms to find a path, then you will probably be pretty unpredictable already, wether or not someone else has t
      • "Well, it will always be "easy" for a computer to figure out the 'optimal' path through terrain. (of course, by "easy" I mean "NP-hard", but a computer could figure out the best easily-findable paths that another computer would probably use)"

        Let's just hope that "other computer" it uses isn't using mapquest,lol

  • by digital bath ( 650895 ) on Thursday October 23, 2003 @05:04PM (#7295534) Homepage
    This is really cool.. technology like this could be used in consumer cars to reduce rollover/tire spin/etc. Maybe even 'smart' cars that drive themselves, leaving the human passengers free to sleep or get work done.
    • leaving the human passengers free to sleep or get work done.

      A nice thought, but in reality the passengers would just piss the time away reading Slashdot over a cell phone connection.

    • Maybe even 'smart' cars that drive themselves

      This will undoubtedly happen one day, but I think most people will be extremely reluctant.

      Though practically it could probably be compared with the leap to horseless once upon a time ;)
      • Insurance companies will HATE these, and set rates accordingly for a long time. If you get into a wreck, and the car was driving, why on earth should -your- rates go up? Why not fine the automaker? Oh, the lawyers will LOVE this.

        • I am interested to see how the insurance companies react if that Toyota that parks itself ever makes it to the US. The first wreck involving one of these will probably set the prescident for wrecks involving fully autonomous cars.

          Now that I think about it though, with something as simple as parking, insurance companies will probably send out something saying that you are not insured for any accidents resulting from using this feature.

          You would also have to have some way of verifying whether or not the fe
      • Special self-driving vehicle lanes for the highway would be pretty cool - they'd have the potential of running very smoothly, even if they don't move any faster overall than normal lanes. Should be safer, too.

        Then once the person is back on the surface streets it kicks back in to manual drive, perhaps. At least that might be an easier transition.
        • Special self-driving vehicle lanes for the highway would be pretty cool - they'd have the potential of running very smoothly, even if they don't move any faster overall than normal lanes. Should be safer, too.

          Do your part now [amasci.com]. You don't need to wait for automated vehicles.

          • Yeah. I already do that. It doesn't have quite the dramatic effect when I do it that he talks about (admittedly I only briefly glanced around). Someone taught me that way back when I was learning how to drive - basically avoid flashing your brakes at the person behind you and it'll smooth out at least a bit.

            There's still room for improvement, though.

            Speaking of the "no cause at all" part - or rather, the cause not being immediately evident, I have to say that the Seattle area is one of the worst. Seattle'
            • Yeah. I already do that. It doesn't have quite the dramatic effect when I do it that he talks about (admittedly I only briefly glanced around). Someone taught me that way back when I was learning how to drive - basically avoid flashing your brakes at the person behind you and it'll smooth out at least a bit.

              I was taught pretty much the same in school, but it's amazing how many of us (myself included, at one point) throw all that out the window. Since finding that page on traffic wave patterns nearly t

    • by kfg ( 145172 )
      Traction control is old hat. On an electric vehicle which uses a seperate motor to drive each wheel (the ideal setup, eliminating most of the drive train and making a differential totally redundant)it's actually not even that difficult. A few sensors and some computer logic to moderate the electricity to each motor, providing a specified amount of torque at each corner.

      Pretty sweet setup really. Too bad about the whole battery thingy.

      What might surprise you though is that Ford is already not only already
    • by Osty ( 16825 ) on Thursday October 23, 2003 @05:22PM (#7295669)

      This is really cool.. technology like this could be used in consumer cars to reduce rollover/tire spin/etc. Maybe even 'smart' cars that drive themselves, leaving the human passengers free to sleep or get work done.

      We already have all of that technology available already.

      • Preventing roll-overs: Buy a car that's not top-heavy. If you have a real need for an SUV that is top-heavy, don't try to drive it like a car, because it's not. It's a truck, and you should be aware of that (ie, avoid turning sharply, braking suddenly, etc). The newer cross-over and car-based SUVs (Chrysler Pacifica, Porsche Cayenne/VW Touareg, Infiniti FX models, etc) are much better in this respect. I'm referring mostly to the body-on-frame truck-based SUVs. I don't drive my huge F250 like I do my Boxster, simply because the F250 doesn't handle like the Boxster does.
      • Wheel spin: Traction control/stability management systems are quite intelligent these days, using modulated application of braking at the different wheels depending on what's need. Otherwise, keep your tires in good condition (check your remaining tread depth, air pressure, etc) and use the proper type of tire (summer ultra-performance tires are dangerous on snow or ice, of course) and you'll be much safer. It's scary the number of cars I see on the road with bald tires or low pressure.
      • Cars that drive themselves: Busses, trains, etc. Of course, this assumes you're in an area with a good mass transit system, which many of us are not. On the whole, though, I'd rather entrust myself to a human bus driver than an autonomous car, at least for the forseeable future. (That said, I never use mass transit, because it's simply not useful where I live, and I love driving :)

      Okay, so those may not be as glamorous as a fully-robotic car, but the technology is already there. And as far as future autonomous cars go, so long as I can still buy a car that lets me manage throttle, brakes, shifting on my own for fun, I'll be happy.
      • Yes the technology is out there - it's not currently tied together, though. This race will bring together all the technologies needed for a safe, autonomous vehicle.

        I agree with wanting to drive for fun, though. I'll take a stickshift over an autonomous car any day.
        • Yes the technology is out there - it's not currently tied together, though.

          Depends on how you look at it, of course. If I could afford it, I could buy a Bentley (a sedan, low center of gravity to help prevent roll-over) with traction control and hire a driver to drive me around. That seems pretty tied together to me :)

      • How are cars that drive themselves "out there?" A bus doesn't drive itself, and trains are mostly automatic because they drive on a fixed track, with speeds in a lookup table for segments of the route. That method may be scalable to speed limits on roads, but does not help with collision detection, routing, re-routing (in case of accidents or construction), red-lights/stop signs, etc. We've still got a ways to go before Johhny Cab drive us around.
      • "I don't drive my huge F250 like I do my Boxster..."

        Sir,
        I do not doubt your ownership of said automobiles, since I know better of this world than to assume. Neither would I want to imply that I am maligning your character, since I do not know you personally and cannot judge, but one must admit that statistically speaking a "Slashdotter" would be exaggerating a bit to say this.

        And personally, if I had a Boxster I'd be out driving that bitch!

        Regards,
        • I do not doubt your ownership of said automobiles, since I know better of this world than to assume. Neither would I want to imply that I am maligning your character, since I do not know you personally and cannot judge, but one must admit that statistically speaking a "Slashdotter" would be exaggerating a bit to say this.

          Follow the link in my profile, I think that'll do a fair job of verifying my statement ...

          And personally, if I had a Boxster I'd be out driving that bitch!

          The Boxster is my dail

      • Preventing roll-overs: Buy a car that's not top-heavy. If you have a real need for an SUV that is top-heavy, don't try to drive it like a car, because it's not. It's a truck, and you should be aware of that (ie, avoid turning sharply, braking suddenly, etc). The newer cross-over and car-based SUVs (Chrysler Pacifica, Porsche Cayenne/VW Touareg, Infiniti FX models, etc) are much better in this respect. I'm referring mostly to the body-on-frame truck-based SUVs. I don't drive my huge F250 like I do my Boxster
        • You seem to have missed that this is a race through a desert, partly off-road. The vehicles of choice will probably be hummers and buggys, and even these will flip if pushed too hard.

          I certainly didn't miss that. Instead, I was replying to the original poster's assertion that this race would leave to advancements in civilian vehicles, including abilities to prevent rollover accidents. I do not doubt that he is correct, I simply wanted to rebut his point by mentioning that there are ways right now to

        • There's no human in the car to keep safe. All they need to is provide an 'unflipping' mechanism, or put wheels on the roof.
      • I think one thing that is being missed here is that these autonomous vehicles are going across the desert. Think of those Baja racers leaping over sand dunes.... Some degree of self preservation will need to be designed into these things.
    • It might sound stupid but I like driving. I see it as an excuse to get time to myself, listen to music and forget about my worries as I concentrate on driving.

      I don't want to work any more than I do

      Rus
  • It's so frustrating watching DARPA technology. They get to play with lots of cool stuff, but 90% of it's about killing people, making nuclear war more practical, or causing other kinds of evil and terrorism, and the rest of it's mostly about protecting soldiers (who are out doing those things) or else cleaning up the mess from nuclear and chemical weapons manufacturing.

    On the other hand, they get to blow stuff up, use expensive computers, and build really cool networks....

    • by digital bath ( 650895 ) on Thursday October 23, 2003 @05:07PM (#7295557) Homepage
      But some of it ends up benefiting the masses as well - like that little thing called the 'internet' that you used to post that comment detracting DARPA, for one ;)
    • Boo-fucking-Hoo. Some people deserve to die. They just make it more fun.
      • Assuming you're not being ironic...
        No one 'deserves' to die, that's just your opinion. To some people US soldiers 'deserve' to die. Not that I'd like that, but the people who do, think themselves just as right as you. just because you _think_ it's right to kill, doesn't _make_ it right.
        Think of that next time you're having 'fun'.
        • Lighten up. But yes, some people DO deserve a DARPA engineered smart bomb launched from a radio-controlled plane to land right on their head and turn them into a fine red mist. C'mon... can you imagine the look on people's faces when they have a missle coming in through their house window? That's some funny shit. How about those air fuel bombs? Imagine the looks on peoples' faces when they're at the outer perimeter of the blast, and all of the air is suddenly sucked out of their lungs, and their bodies
    • by cK-Gunslinger ( 443452 ) on Thursday October 23, 2003 @05:22PM (#7295670) Journal
      but 90% of it's about killing people, making nuclear war more practical, or causing other kinds of evil and terrorism,

      Oh come on! What kind of crap is this? Perhaps you've heard of that little DARPA creation called the INTARWEB?! =P

      No one wants to make nuclear war 'practical.' 90% of research is about NOT killing people, as killing a lot of people typically doesn't help win wars. This isn't the middle ages where you can hope to wipe out an entire society in a single war. What DARPA is interested in is destroying *targets* - things like launchers, tanks, fighters, satellite links, etc. Successful live tests are those that *minimize* casualties, not maximize them. We've had the technology to maximize death for decades now.
      • No one wants to make nuclear war 'practical.'

        I'm sorry, but a lot of medal-wearing people do.

        killing a lot of people typically doesn't help win wars.

        Hiroshima, Nagazaki.

        This isn't the middle ages where you can hope to wipe out an entire society in a single war.

        Nah, you have to keep at it nowadays. Like, Have one president invade a country, then leave, let an embargo weaken that country, then have the son invade it again...

        Dude, seriously, war is about killing people. Always has been, always will
    • DARPA typically only funds projects or research that may be useful commercially as well as militarily.

      Yesterday's decentralized military communications system is today's internet. Today's robot-driven combat vehicle is tomorrow's smart car.

      That's why DARPA projects are public -- we get to use the technology too. Or perhaps you'd rather we just threw the money into some secret black box projects, never to see the light of day?
      • Re:Wrong (Score:3, Informative)

        by cyril3 ( 522783 )
        Or perhaps you'd rather we just threw the money into some secret black box projects, never to see the light of day?

        Well the Blackbird was pretty cool. In fact it was the coolest damm piece of tech so far developed.

        And I for one would rather see them flying around taking pictures than a bunch of autonomous laser tanks trying to miss civilians as they take out the eye of some dumb third world conscripted grunt who happens to be wearing the uniform of the 'enemy de jour' just so joe sixpack can read the pa

    • So you're saying that protecting soldiers, who are out doing those things because a representatively elective government told them to do it, is a bad thing? Maybe you'd prefer if these people, trying to do something that's right, died instead, because you either a. elected a bad government, or b. didn't do enough to ensure that a good government was elected, either way putting them in harm's way. I don't understand what kind of worldview you must have, but I think it's twisted.
  • Sounds dangerous (Score:3, Interesting)

    by El ( 94934 ) on Thursday October 23, 2003 @05:09PM (#7295571)
    Isn't anybody concerned about autonoumous vehicles running over spectators? "Hey, I thought it was a rock." I certainly wouldn't trust my life to a DARPA visual recognition system.
    • Well, if you're stupid enough to stand in front of a speeding motor vehicle controlled by a computer then obviously you've been either living in a cave for the past twenty-odd years or you're legally brain-damaged.
      • Well, then these should be particularly effective against Osama Bin Laden -- hasn't he been living in a cave for the past twenty-odd years, and isn't he legally brain-damaged?
    • Re:Sounds dangerous (Score:1, Informative)

      by Anonymous Coward
      Check out the website [darpa.mil]. They'll have a field referee vehicle following every entry. The field vehicle will have a kill switch implemented and tested by DARPA.
  • I remember seeing all kinds of stuff about this "up and coming" hovercraft technology. Then it just disappeared from the mainstream. Is there a reason this hasn't progressed further? Seems like a good solution for desert navigation.
    • Basically hovercrafts are a bitch to control... they slip all over the place and you have to 'telegraph' your moves well before you actually want it to happen.

      You get rid of some problems (wheel slippage etc.), but you add more.

      Plus they're just so loud!
  • .. what I really want is for everyone to have self driving cars. It's really much more efficient to roll a weight across a smooth path than it is to fly it over the same path. I'd like to be laying back on my couch in my car going 200.

    That would be cool.

    • Microsoft Autodrive XP has performed an illegal operation and will be shut down. Please stand by while Microsoft Autodrive XP sends an error report in order to serve you bet(&*....[CARRIER LOST]
    • I'd like to be laying back on my couch in my car going 200.

      You can do that now...once ;- )
    • Unless of course 'capacity,' 'distance,' 'speed' and 'fuel consumption' are considered as part of the efficiency calculation that generarlly works into 'cost.' I would dare say that in many circumstances a balloon is slightly more efficient than a dolly, for instance.
  • by apoplectic ( 711437 ) on Thursday October 23, 2003 @05:10PM (#7295589)
    Get these robots to drive NASCAR to entertain the automatons known as fans.
    • Get these robots to drive NASCAR to entertain the automatons known as fans.

      Before that, just have them post to Slashdot. Same effect, much more realistic milestone and nobody would notice.
    • I think that that's really an extremely insightful idea. What would be much better than a competition to get a robot car to navigate rough terain would be a car that could navigate high traffic conditions at a high speed. Thats where the real pay off is; we really have a strong desire for faster travel, but things like running into trees or other drivers at 150 tends to be a real obstacle.
  • by BagOBones ( 574735 ) on Thursday October 23, 2003 @05:12PM (#7295606)
    You ever wonder if video game developers haven't already solved many of the AI issues in terms of driving?

    The real problem would be getting the track information in real time and telling the AI what each object is.

    Then again I am sure game developers get to cut a bunch of corners because the AI knows the track perfectly because it is a part of its system.
    • by mrseigen ( 518390 ) on Thursday October 23, 2003 @05:22PM (#7295671) Homepage Journal
      There are probably lots of game hackers trying to use the best of the best in pathfinding algorithms. It'll be interesting to see if what the game industry has been using for years actually does keep a speeding vehicle from getting embedded in rocks, children, and sandstone walls.
    • Yes and no. As you say, you need to get the AI information about each object and what it is. I'm working on the Caltech team, and that is where the majority of time is being spent on the software side - detecting and classifying objects. It is an extremely difficult task given todays technology, a limited budget, and the variety of obstacles you can find. Some examples:

      How do you determine if there is an object, or it is just mud on the camera?
      How do you detect dust and filter that out?
      How do you det

      • How do you determine if there is an object, or it is just mud on the camera?

        Short answer: Saccades.
        Longer answer: Put a motor on your camera that allows limited angular motion. Put teflon-coated plexiglass in front of the camera (probably with a wiper). Saccade. Check angular parallax.
        Alternative Answer: Dual cameras.

        How do you detect dust and filter that out?

        Do horrible things to shadow elimination code.

        How do you detect a fence - the links are generally too small to be picked up on the camer
        • You make some valid points. As I said, there are answers to some of these.

          One thing I would like to comment on, regarding the fence...Of course, you look for fence posts...but what if there is an opening somewhere in the fence, and part of the race course is to go through that opening? You slow down too much if you creep along right next to the fence, and if you are too far away you won't be able to distinguish an opening. Also, given the vibrations in the vehicle, it can be difficult for any camera, re

          • Vibration control is a prerequisite to any successful camera system. Hell, we've got one, it's called a neck :-)

            >60fps cameras may also be of use, especially with hardware to realtime integrate each of the shaking images. The fact that this is almost certainly going to be a day drive helps _alot_.

            Focus is easy from a distance, and up close, you can actually do rangefinding based on standard autofocus techniques. Even a blurry image of a fence going by will get significantly darker as focus is correc
    • A big problem the designers have faced is that the terrain is unknown (the route isn't announced until that morning). Therefore, all the sensors must be on-board. The available sensors are GPS for general position, cameras/lasers/etc for things like rocks, gullies, etc. Since the course is 200 miles long, and there is a time limit, the vehicle must average over 20 miles per hour. The problem isn't finding a route, it's finding a safe path with limited sensors and with everything happening really quickly
  • About time that somebody did something about dangerous cellphone users. I would use one after the technology gets a good track record. I could work on a laptop and still get to work. Nice for all the drunks out there after work too. Stop by the bar and still get safely home.
  • A Real Change (Score:5, Insightful)

    by cluckshot ( 658931 ) on Thursday October 23, 2003 @05:18PM (#7295640)

    The first posters here don't have a clue as to the effects and circumstances of this. The purpose is not Autonomous Kill Vehicles though it might occur. Cruise Missiles etc already do this as does the Predator to one degree or another. The purpose here is to reduce the overhead cost on the army dramatically in hauling supplies etc over long distances with or without roads. To do this you need vehicles than can bypass disabled vehicles and overcome obstacles. They need to be free of drivers who get tired and eat up supplies.

    The real effect here will be civilian. The project which like it or not will happen regardless of DARPA someday soon, is going to very nearly completely alter how we live.

    To illustrate: suppose you are old blind and unable to drive. (It happens to the best of us) Now you will be able to go where you want without somebody driving you. Suppose you want to go to work but don't want to own a car? Mass Transit? No! you just get on your cell phone and call for a car. It arrives shortly and takes you where you want to go and without a driver. Freight? No more Truck Drivers and the wreaks from them being too tired. No more Taxi Drivers. Close most of the Hospitals because wreaks are not filling them up. Kids will not need parents to drive them somewhere.

    There is very nearly nothing more profound than this race! It will reorganize our world. The issue here is how will we adapt. This isn't an esoteric question. We had better face it now.

    For the Luddites amung us, give it up. Stopping DARPA will only give the technological edge to China. They will do the work. This is a very high amplification Technology. It Amplifies People a LOT. The issue as always will be the morals of those being Amplified, and will we allow this to cause others to be lost in the "noise."

    • Re:A Real Change (Score:2, Interesting)

      by khenson ( 706671 )
      You know... You're right. And reading your article I was getting more and more riled up about removing YET another right to the few things I actually enjoy on this planet - driving.

      But the more I think about it the more I like the idea of having alternative transportation for those deemed "incapable" of driving a vehicle.

      This way you would have to earn the right to actually control the vehicle you drive. We could test drivers like other countries do - inclement weather condition tests, obstacle tests, rea
      • Even the best driver in the world won't be able to compare to a robot, including you, Mr. Professional Driver.

        You won't have the inhuman reaction time ( I actually think human drivers should (and will) have to pay MUCH higher insurance rates than owners of bot-driven cars. But hey, if you submit to GPS tracking, a breathalizer-ignition, interior/exterior cameras, and that special driving test you mention, then you might be eligible for a 10% discount!

        --

        • Yeah... I have been driving since I was 12 years old (38 now) which is probably longer than you've been alive with zero - that's right ZERO - accidents - fender benders, whatever - all inclusive.

          The proof is in the pudding. I have a record that proves myself, do you?

          My post only suggested giving alternative transporation options to people that shouldn't be driving in the first place which leaves people who like to drive (which usually means they're good at it) a more open freeway.

          And hell no - I won't pa
    • Any watershed advancement like this produces (1) Advantages, (2) Disadvantages and (3) Chaos. Generally, that means (in order) (1) Profits and efficiency if you are on the receiving end of the technology advancements, (2) Unemployment, obsolescence or business/financial ruin if you are on the wrong end of the technology advancement and (3) some degree of Wild-West while laws, regulations and cultural adaptation has not caught up to the new status-quoe.

      It Amplifies People a LOT. The issue as always wil
    • Welcome to Johnnycab.
      Please stwate your destination.
    • god help up... pray that new jersey doesn't form a livery union, or else we won't see aoutomated driving for several hundred years to come. just ask the gas attendendts.
    • I studied human perceptual mechanisms as an undergraduate. In particular I recall an advanced seminar on perception (which included cognitive psychology and neurobiology as prerequisite courses) in which the issue of driverless cars was discussed at some length. One particularly illustrative example of the challenges faced by developers of such a vehicle involved a box falling off a truck on the highway. A human driver could judge in under a second, from the way the box bounced, whether it was a heavy and p
  • Male or Female (Score:1, Flamebait)

    by rf0 ( 159958 )
    You can just see it now can't you. The losers are going to be saying "Well we programmed the robots with female personality. Its not our fault that in 200 miles of flat desert it crashed into the only gate post on the entire course"

    Rus
  • ThisIsAnExampleAccount@yahoo.com [mailto]
    Please do not mod this message down. I am currently running an experiment to see which spambots are collecting addresses from Slashdot. Please do not mod down. In fact, if you could mod this up, that would be great. I will publish the results of this experiment as soon as it is complete. hopefully the results will be usefull to all /. denizens. Thanks! ThisIsAnExampleAccount@yahoo.com [mailto]
  • I mean, it'd only be really cool if they programmed the driving after KITT or the General Lee:

    -and the potential to become airborne when hitting bumps.
    Robot driver - "Hot damn, bet I could get some serious height jumping off those rocks over there! Balls to the wall, baby!"
    • Oh, come on! The General Lee wasn't even a robot car. It had actual hicks driving it! I don't even think there was a robot car on the show, unless you count Enis as a robot - which I do.

      Speaking of which, the Mach-5 had the ability to have saw blades come out the front of it so you could drive through forrests, chopping down trees as you drive.

      What I don't get is, wouldn't the tree stumps be a problem with that? What about the falling trees? Wouldn't some of them land on the Mach-5?
  • by ssclift ( 97988 ) on Thursday October 23, 2003 @06:08PM (#7295944)

    Let's see them drive that beast through Bruce County Ontario blizzard...

    .... tires rumble left ... time to steer right a bit ....

    .... tires rumble right ... time to steer left a bit ....

    .... honey, can you open the door and tell me how far I am from the edge of the road ....

    • I've been in a Bruce County blizzard. Damn scary when you only know you haven't lost the road because the brake lights appearing out of nowwhere in front of you aren't shining up out of a ditch.

      A self-navigating car that uses GPS, sees by radar, maybe checks position agains magnets embedded in the road every so often and can adjust for extreme road conditions would be pretty sweet in such a situation.

      Of course, that doesn't explain why idiots like us are out driving in a Bruce County blizzard.

  • The real entertainment is once these vehicles are crusing at notable speeds with cargo on board, force the creators of the vehicles to ride in their newly created automated machine of death...er, car.
  • Sounds cool, but it's not a real robot car until they give it Turbo Boost.
  • Comment removed based on user account deletion
  • I just returned from doing some acoustic testing at Georgia Tech and guess what was sitting 10 feet away from me and i got to inspect. A Humvee about to be raced that is Autonomous. They wouldnt say what it was for but I just got home after 7 hours of driving and saw this...Well ill be dipped, thats what the Humvee was for...cool...and GO Yellow Jackets!!!
  • by Animats ( 122034 ) on Thursday October 23, 2003 @10:54PM (#7297464) Homepage
    That's one of the best articles I've seen on this event.

    I run one of the Grand Challenge teams, Team Overbot [overbot.com]. We have a vehicle (a modified six wheel drive Polaris Ranger), a shop in Redwood City, funding, equipment, and people. We're well along; the vehicle has most of its actuators and some of the sensors working, and about a third of the software is running. We're one of the five DARPA-accepted teams.

    Many of us are Stanford alumni or students, but this is not a Stanford project.

    • We need three more good programmers in Silicon Valley. "No pay, some risk, a fraction of the prize." If you're interested, we want to see 1000 lines of C++ you're proud of. You'll need to put in at least 250 hours between now and March. Click here to join. [overbot.com]

    Our basic technical approach is to build a rugged, reliable vehicle with conservative control strategies. Others may be faster, but we expect they'll get into trouble at high speed. Our top speed is 40MPH. The real problem with the Grand Challenge is not going fast on the easy parts; it's getting through the hard parts.

    The 6WD chassis we're using is one of the most bump-tolerant platforms around. It can go over railroad ties at top speed without problems and without going airborne. The center of gravity is low. The front and mid axles have independent suspension; the rear axle is a swing arm. This simplifies low-level vehicle control. All wheels can be driven, although at higher speeds, we will switch from 6WD to 4WD.

    We have five computers on board. Three are small PC/104 machines, and two are Pentium 4 machines. All run QNX (the OS for when it has to work.) All are industrial-strength ruggedized units. The actuators are all servomotors driven by industrial microcontrollers. All this hardware is off-the-shelf industrial control gear.

    Sensors include LIDAR, doppler RADAR, sonars, cameras, INS, GPS, etc. Some of them are used in unusual ways. That's all I'll say about that.

    The pathfinding strategy is indeed borrowed from video game technology. It's more structured than Brooks-type behavior based robotics, and it's less structured than Latoumbe-type planning. There are three layers of control; the top one we call the "back seat driver", because it has only advisory authority over the "driver".

    We have road map and topo data onboard, but it's used more as a hint than as rigid guidance. We take the waypoints DARPA gives us (on a CD, at 0430 hrs the morning of the race) and load it in. There's no offline preplanning. Wouldn't help in the real world.

    If nobody wins this year, which is quite likely, we'll be back next year with a faster vehicle.

    Post questions and I'll answer them here.

    John Nagle
    Team Overbot

    • Isn't 40MPH a bit slow? I seem to remember some back of the envelope calculations stating that you need to be up to about 70MPH on the road segments to keep the average high enough for the nastier terrain.

      I don't know about auto-pilots but I have driven real SUVs (Land-rover) seriously off road. For a human being it isn't exactly easy and when there is no track at all to follow, 20MPH can be difficult to maintain. As a human, even with the ground clearance of a real SUV, you are very aware of the danger o

      • It's been awhile since I read the rules, but I do remember that DARPA actually has speed limits in many areas. I could be wrong, but I also seem to recall reading something about 45 MPH being the absolute maximum. Maybe not, though.

        Personally I doubt anyone will win any time soon, the course is intentionally difficult.

      • Going 120MPH, rather than 40MPH, for 20 miles of flat, hard plain (one likely section of the course shown in DARPA's pictures is such an area) gains 20 minutes. (10 minutes vs 30 minutes).

        Going 30MPH, rather than 15MPH, over 20 miles of tough terrain, gains 60 minutes. (90 minutes vs 30 minutes).

        That's why rough-terrain performance is more important than flatland performance.

        The Polaris Ranger has a thick ABS plastic skid plate over the whole bottom of the vehicle.

        But this isn't about the vehicle.

        • It had ocurred to me that having something looking at the ground ahead for bumps would be kind of useful - even for a human travelling at speed. The problem is soft ground. The boulder may only be a foot high, but if you are going to sink a foot, then in a Landy at least, that can be a problem. The opther issue is whether to go optical (LIDAR) or RF (RADAR). The problem with optical is if you have to go through vegetation, the boulders are masked. I then thought about X-band or above RADAR (but sub-mm waves

Factorials were someone's attempt to make math LOOK exciting.

Working...