Please create an account to participate in the Slashdot moderation system

 


Forgot your password?
Close
typodupeerror
×
Technology Science

Teach A Robot To Drive, Win A Million Bucks 385

Posted by timothy from the and-spend-it-all-in-vegas dept.
An Anonymous Reader writes "DARPA has released the details of a 'Grand Challenge,' with a $1 million prize. The challenge is to build an autonomous vehicle which can 'navigate on its own over a 250-mile desert course in less than 10 hours.' from L.A. to Vegas, 'without external communication or human control.' The contest is to be conducted in March 2004, and is open to all comers. Can we get at least one entry to represent slashdot?" We've mentioned this contest a few times before: any intended entrants out there want to disclose your secret plans?
This discussion has been archived. No new comments can be posted.

Teach A Robot To Drive, Win A Million Bucks More

Teach A Robot To Drive, Win A Million Bucks

Comments Filter:

  • dislose? (Score:5, Funny)

    by Anonymous Coward on Sunday March 16, 2003 @06:17PM (#5525156)
    dislose? Does that mean find them?

  • Sounds Easy To Me (Score:5, Funny)

    by ZeroLogic ( 11697 ) on Sunday March 16, 2003 @06:17PM (#5525162)
    Just make it really really big, with treads, and a huge freaking mulcher on the front. Then, just let it travel in a straight line from LA to Vegas. Crushing everything in its path!

    • Re:Sounds Easy To Me (Score:5, Insightful)

      by Anonymous Coward on Sunday March 16, 2003 @06:27PM (#5525212)
      "For example, an extremely large vehicle that simply travels on a straight line between two points by climbing over or breaking through everything in its path (and destroying what cannot support that movement) is not the type of intelligent solution that is sought." - DARPA Site

      Obstacle intimidation algorithms not allowed. :/

    • Or: (Score:2)

      by mcc ( 14761 )
      Just ask Kenner for the original plans for this thing [map.com], and build it at 2500:1 scale..

      Okay, okay, it would be totally against the rules. But it would be really cool!

  • sounds like fun (Score:4, Funny)

    by Scorchen ( 641292 ) <scorchen.gmail@com> on Sunday March 16, 2003 @06:18PM (#5525165) Homepage
    robot prime suspect for fridays hit and run accident which resulted in the death of several school aged children..
    • Police ask that citizens be on the lookout for the suspect known as "The Slashdot Cruiser". Do not approach, do not try to apprehend.
    • I doubt anybody would notice if this happened on Chicago's south side. Seems like they have a few hit & runs every day there.

      But speaking of school aged children, is there any way this could be tied in with the story about the guy who built a tank for his kid?

  • Top Secret. (Score:4, Funny)

    by Anonymous Coward on Sunday March 16, 2003 @06:18PM (#5525169)
    "We've mentioned this contest a few times before: any intended entrants out there want to dislose your secret plans?"

    I could, but then I would have to kill you. :)

  • Uh, riiight.... (Score:5, Insightful)

    by xintegerx ( 557455 ) on Sunday March 16, 2003 @06:20PM (#5525176) Homepage
    The challenge is to build an autonomous vehicle which can 'navigate on its own over a 250-mile desert course in less than 10 hours.' from L.A. to Vegas, 'without external communication or human control.'

    Somehow I have the feeling that 99% of the teams competing will try to figure out inventive, creative ways of using and obfuscating 'external communication or human control' as the first step. :)

    • Re:Uh, riiight.... (Score:5, Funny)

      by TopShelf ( 92521 ) on Sunday March 16, 2003 @06:30PM (#5525226) Homepage Journal
      sounds simple enough... stick a midget inside!

    • Re:Uh, riiight.... (Score:5, Funny)

      by Nathdot ( 465087 ) on Sunday March 16, 2003 @09:19PM (#5526030)
      The challenge is to build an autonomous vehicle which can 'navigate on its own over a 250-mile desert course in less than 10 hours.' from L.A. to Vegas, 'without external communication or human control.'

      I'm pretty sure autonomous operation is of utmost importance to DARPA. On goes the tinfoil hat but:
      PHASE 1: 'navigate on its own over a 250-mile desert course in less than 10 hours.'
      PHASE 2: Transform into robot-humanoid form.
      PHASE 3: Identify targets. Lock. Fire.
      (PHASE 4: Profit!)

      The only question you've gotta ask is, in today's ambiguous political environment, who are the autobots and who are the decepticons?

      Seriously, call me a troll, but would DARPA be interested in an autonomous vehicle capable of navigating desert terrain, without also considering coupling it with an autonomous weapon system? Or maybe I just spent too much time playing Command & Conquer back in the day.

  • Before we teach the robots how to drive... (Score:5, Funny)

    by Ron Coscorrosa ( 711 ) on Sunday March 16, 2003 @06:22PM (#5525183) Homepage
    Can we teach the humans to, as well?

  • Its a long shot... (Score:5, Funny)

    by kinnell ( 607819 ) on Sunday March 16, 2003 @06:22PM (#5525185)
    but just pointing an old car in the right direction with the steering wheel and accelarator jammed would have a small chance of victory. It would make a lot more sense than playing the lottery, and on the off chance that it did work, it would piss off DARPA no end.

  • Hrmmmmm (Score:3, Informative)

    by Anonymous Coward on Sunday March 16, 2003 @06:23PM (#5525192)
    I was jkust talking with a fellow from the same university I attend, and there is a group that is has done this for a one mile range.

    (It's a robot that finds a specific building within a one mile radius and does other things involving the building)

    I hear they've got the "flying to a building within a 1 mile radius" part done. Wouldn't it be not much more difficult to extend the radius to 250 miles? What would be involved?

    • Re:Hrmmmmm (Score:3, Funny)

      by xintegerx ( 557455 )
      I hear they've got the "flying to a building within a 1 mile radius" part done. Wouldn't it be not much more difficult to extend the radius to 250 miles? What would be involved?

      Lots and lots of square miles.

  • So. (Score:2)

    by Renraku ( 518261 )
    I guess the US Military has this one won. Just show them a cruise missile and launch it across 250mi of the area and then crash it. Or if they want to be nifty, have a parachute warhead that contains the 'brains' of the thing and can deploy wheels or landing gear to deploy at the end of the course.

  • Piece of Cake. (Score:3, Interesting)

    by drink85cent ( 558029 ) on Sunday March 16, 2003 @06:24PM (#5525198)
    All you need is to hook up a camerea up do an artificial neural net and spend a couple hours teaching/progamming it to steer and throw in a cpu and run a rule based system with a well defined set of rules(for navigation,traffic laws, etc) and we're set. Piece of cake.

    • True (Score:5, Insightful)

      by leerpm ( 570963 ) on Sunday March 16, 2003 @06:31PM (#5525237)
      But the devil ends up being in the details. While it probably would not be too hard to design a vehicle that could do this in a couples day or so, 250 miles in 10 hours means the vehicle would have to be averageing 25 mph. At 25 mph, there is not a whole lot of room for error. You would need a system that could react to environmental issues that came up very quickly such as obstacles, or dead end routes. You would also need to a system that could actually sense/see far enough ahead to steer the vehicle in the correct direction without running into things.

      • Even Faster Than That (Score:5, Informative)

        by sacdelta ( 135513 ) on Sunday March 16, 2003 @07:08PM (#5525381)
        From the rules:
        2.19.3 Maximum Finishing Time


        In order to qualify for the Grand Challenge cash award, the maximum corrected finishing time of the winning team must be less than six hours. Additionally, to ensure safe operation during daylight hours only, all vehicles must be removed from the route ten hours after their departure.
        If you want the money you have to do it in 6 hours. This is just over 40 mph. But some of the route is paved which should allow for higher speeds for parts of the course.

        The rules also state that the route will be navigable/avoidable by a standard 4x4 pickup (HINT HINT).

        Having driven out in the desert, even on the dirt roads, most of it can be driven at 60+ mph. You just have to be ready for the parts that can't be driven faster than 5 mph.

    • Re:Piece of Cake. (Score:3, Insightful)

      by inburito ( 89603 )
      The complexities in this problem are enormous so trivialising them is apparently interesting.

      Maybe we'll just hook up slashdot to an artificial neural network and spend few hours teaching/programing it to do moderating and throw in a cpu and run a rule based system with a well defined set of rules (for detecting trolls, redundancies, etc.) and we're set. Piece of cake.
  • Now if someone could just teach the residents of Florida how to drive...

  • how to succeed in AI contests without really tryin (Score:5, Funny)

    by kurosawdust ( 654754 ) on Sunday March 16, 2003 @06:27PM (#5525216)
    The challenge is to build an autonomous vehicle which can 'navigate on its own over a 250-mile desert course in less than 10 hours.' from L.A. to Vegas, 'without external communication or human control.' ...any intended entrants out there want to disclose your secret plans?

    I plan to build a 250-mile-long car.

  • The real goal is... (Score:2, Insightful)

    by Anonymous Coward
    low cost research for DARPA. I'm guessing that the prize money is a tiny fraction of the amount of money DARPA would normally pay for a university research group to accomplish the same task.

    The good thing about this approach for the contestants if that they don't have to put up with the endless stream of DARP required reports, meetings, and politics.
  • I'm going teach a chimp to drive and use cruise control!

    Hoi-claven!

  • Slashdot Entry (Score:5, Funny)

    by Anonymous Coward on Sunday March 16, 2003 @06:32PM (#5525239)
    If someone from Slashdot enters a vehicle, it should definitely be named "Autonomous Coward." :)
  • With no external communication and tracking allowed, these robots will end up... who knows where? Who knows where?

    That's right, who knows where! Be ready as the creators will have 5 hours to scout the desert for their robots before the sandstorm hits (or something)! :/

    Nah, I'm sure the robots will be allowed to shoot a flare or something! Oh wait:

    "...a vehicle that clears a path by setting everything in its way on fire, or a vehicle that digs large holes, are unacceptable.

    Hmm.. :/

    Go ahead and try
  • They had a robot driving the van at the end, sort of. It was remote controlled but still.. then the little camera turned and faced the guy who opened the door. That was funny. Reminded me of Short Circuit..

  • Somewhat ridiculous requirement.... (Score:3, Insightful)

    by adzoox ( 615327 ) on Sunday March 16, 2003 @06:36PM (#5525257) Journal
    I don't see ANY autonomous system NOT reying somewhat on GPS. At least, not even as a redundancy or backup.

    Because something can be done doesn't even mean it can be feasible/useful if possible. By example, I'm sure someone could completely fill up a car with electronics and make this work. What they need is to have "design/weight bonus" to the prize. I think this theory is proving very true in the TV industry right now. People just like Plasma TV's because they look cool and takke up a lot less space - it's certainly not for the picture quality that a similar sized high end (cheaper too) rear projection TV can provide. A similar product is the iPod, it's not only the smallest for the most capacity but has great design and great integration. Even Creative's ZenPlayer hasn't gotten the reviews of the iPod.

  • How to do it (Score:3, Interesting)

    by cehardin ( 163989 ) on Sunday March 16, 2003 @06:39PM (#5525268)
    I think about this problem off and on and I think that this project is conceivable. The key is to break down the software into separate pieces, each utilizing different types of computing. Mixtures of AI and traditional programming can be used to make this a reality.

    My idea of the basic input system idea is based on layers:
    Layer one: the camera(s)
    two: various neural nets, each designed to filter out specific things. Fo example, one net would id cars (and their relative speeds), another the middle of the road (lanes), another the whole road. Maybe even one to find speed limit signs!
    and tree: traditional algorithms which intepret the data from the neural net and use it to compute cars location, other cars locations, where the road is, what speed to go, etc etc.

    This would allow the surrounding envornemt to be broken down into very simple data structures that traditional Algorithms can handle. I think the key to this problem is to divide and conquer, using the best tools for each part.

    It should ot be difficult to train a NN to identify the boundaries of a road in the desert. The info from this can be transformed into 2d space and voila, you got a simplified but accurate view of the cars surroundings. Now just add NNs to id cars and you can use that for collision avboidance. I can go on and on, but you get the idea.
    • I like how you're thinking, and it sounds like it would be sufficient for the purposes of this contest. But let's not let these things roam off the test courses until they become more sophisticated. For example, collision avoidance should be upgraded from the simple "don't run into anything" to "classify object X as a human child, and object Y as a tumbleweed, and give 'avoid X' priority."

    • It should be so easy... (Score:4, Insightful)

      by CreateWindowEx ( 630955 ) on Sunday March 16, 2003 @08:15PM (#5525710)
      Neural nets and "traditional Algorithms" aren't magic bullets, and each subtask you mention "id cars (and their relative speeds)", "find speed limit signs" is a hard problem. While neural nets do have uses in limited cases, they never lived up to all the hype. There's a very big difference between toy problem-domains like "blockworld" or "wumpus world" and the real world, and a lot of very plausible-sounding methods just don't scale to reality.

      People have been working on "smart cars" for decades, thowing every technique you mention (and quite a few more) at the problem, and I don't think we're close to having a robot car that could be trusted to drive unsupervised in real traffic...

      However, feel free to prove me wrong by winning the contest!

  • A pittance. (Score:4, Insightful)

    by I Am The Owl ( 531076 ) on Sunday March 16, 2003 @06:40PM (#5525269) Homepage Journal
    Can anybody imagine how much R&D would have to go into even an attempt, much less a successful one? $1 million doesn't even scratch the surface...

    • Re:A pittance. (Score:5, Insightful)

      by worst_name_ever ( 633374 ) on Sunday March 16, 2003 @06:52PM (#5525311)
      $1 million doesn't even scratch the surface...

      I think it's safe to assume that the winner of the contest (as well as, perhaps, the first few runners-up) will very shortly find himself the recipient of multiple large DoD contracts for further research into autonomous robot tanks^H^H^H^H^Hvehicles.

      • Also, there is already a great deal of effort into similar questions of machine autonomy. A contest like this might take some intriguing, yet unfocused research and motivate the researchers into creating something concrete.

  • The hard part (Score:5, Funny)

    by Jim Ethanol ( 613572 ) on Sunday March 16, 2003 @06:43PM (#5525275) Homepage
    The challenge here is real-time processing of vision data to handle obstacle avoidance, etc.

    They say that you can use "public navigation signals. So a GPS (and backup) receiver, along with a Digital Elevation Map of the area would be half the battle. But real-time stereoscopic vision is a bitch. The nice thing is that you can fit a whole lot of computing power into a medium sized car.

    I suspect another big problem will be colliding with other bot cars... I'm thinking about running a Ford Pinto, which due to the placement of it's gas tank, will explode on impact. At least that away the other robot cars will FEAR mine and stay away ;)

    -JE

    "You're always going to have problems moving a body in one piece" -- Brick Top
    • The challenge here is real-time processing of vision data to handle obstacle avoidance, etc.

      That's easy! Get the guy who built the automatic Tetris playing machine (here) [slashdot.org]. If you can play good Tetris, you can obviously drive ok.

  • Hm... (Score:3, Funny)

    by foxtrot ( 14140 ) on Sunday March 16, 2003 @06:43PM (#5525276)
    Does slapping a fedex label on yourself and jumping in the nearest drop box count as "external communication"?

  • Perhaps not that hard? (Score:5, Informative)

    by ryants ( 310088 ) on Sunday March 16, 2003 @06:45PM (#5525285)
    This is from Artificial Intelligence: A Modern Approach, by Stuart Russel and Peter Norvig, published 1995:
    ALVINN (Autonomous Land Vehicle In a Neural Network) ... is a neural network that has performed quite well in a domain where other approaches have failed. It learns to steer a vehicle along a single lane on a highway by observing the performance of a human driver. ... The results of the traning are impressive. ALVINN has driven at speeds up to 70 mph for distances up to 90 miles on public highways near Pittsburgh. It has also drive at normal speeds on single lane dirt roads, paved bike paths, and tow lane suburban streets.
    The only problem is the training... the system is unable to drive on roads that it doesn't have training data for. I glanced quickly at the DARPA rules and didn't see anything that would invalidate a "build a similar course and train on it" approach. So take ALVINN, build lots of courses that sound like the sort that DARPA is planning, and train, train, train!

    References:

    • Re:Perhaps not that hard? (Score:2, Informative)

      by Anonymous Coward
      ALVINN is one of several subprojects of the long running NAVLAB project at CMU. I took classes from the professors working on this project and XAVIER(a robot that can navigate halls teaming with people w/o bumping into them). They use multiple systems based upon different approaches(neural nets, bayian, etc.) and the systems vote to decide the correct decision. It don't have to train upon a given path, but upon any road that is of similar terain(ie just train the system upon desert roads). I don't want
  • Can we get at least one entry to represent slashdot?

    Sure ! I'll just donate my working prototype on behalf of this worthy cause. After all, I don't need a million bucks that badly... I'm sure VA Linux/Slashdot can use the money more than I can.

    • Re:Slashdot entry (Score:4, Funny)

      by Theodore Logan ( 139352 ) on Sunday March 16, 2003 @07:16PM (#5525412)
      I knew at least one pessimistic bastard would post some nonsense of this sort. Personally I think getting an entry to represent Slashdot is a great idea, and I also happen to think it's quite doable. No need for crappy sarcasm.

      I envision something like this:

      1. Some dude(s) donate(s) a car and a camcorder.
      2. Some hardware hackers wire a computer to interface with the car and the camcorder.
      3. Someone starts a sourceforge project.
      4. One million Slashdot monkeys do their best to develop some kind of AI.
      5. ???
      6. Profit!

      Maybe it wouldn't win, but it'd be a damn amusing project, obviously the point of it anyway.

      What do you say, Slashdotters? C'mon, it'd be fun. Let's do it!
      • Must be tired. Just noticed who's funding this, and I'm not so sure I would like to be a part of it anymore. But disregarding that you'd essentially be doing work for the US military I still think it's a great idea.

        • "Must be tired. Just noticed who's funding this, and I'm not so sure I would like to be a part of it anymore.

          And with those words, the pioneers of what would have been a fault-tolerant computer communication network called "The Internet" allowed a beautiful idea to die.

          Autonomous vehicles have incredible potential for changing the way society works. Just think about all the millions of hours wasted in the car, how many lives are ended by user error (about 50,000 a year in the US), and how much smooth

      • I have a '94 Saturn. Let's rock.
      • Step Five:
        After allowing Slashdot Monkeys to do write it, it races halfway across the desert, notices some specific terrain feature that someone named "Tr011 k1ng" wrote the code for navigating, then drives in a pattern that looks like "Fi0r5t P05t 0wnz0rz j000!!!!111" from the air.

  • Subject goes here (Score:3, Funny)

    by InsaneCreator ( 209742 ) on Sunday March 16, 2003 @06:46PM (#5525292)
    Can we get at least one entry to represent slashdot?

    I doubt it. But do notify us when there is a baloon race. We could donate loads and loads of hot air! :)

  • Great! More DARPA money (Score:5, Interesting)

    by brejc8 ( 223089 ) on Sunday March 16, 2003 @06:48PM (#5525297) Homepage Journal
    Its very annoying being a researcher with moral objections. DARPA is offering $40mil towards asynchronous research. Our research group is one of the best in the area but after discussing the situation we decided not to to take the money. Most of the group (including me) don't really want to do military research. One of the projects most suited to the group would be making some processors for missiles and I definately wouldnt be happy about that.

    There is the case that we could do a pure research project for them. No direct link with weapons but simply making tools to make asynchronous processors but we may be blocked from publishing research and still (more indirectly) killing people.

    I never though that in computers you would have to think so hard about what money and projects to accept but this is one I would skip. Its obveous that DARPA want some long range seeking technology but they want good engineers (ones who wouldnt work for them directly) to do their work and warm them over in the pretence that its a fun game. I can't think of many engineers who wouldn't want to have a go at this challenge.
    • I want to say I fully respect the moral objection to working on DARPA projects, and consider it valid.

      But, when I was working on the first DARPA ALV (automous land vechicle) project in the 1980s, you really couldn't draw a clear line between DARPA research and research supported by other funding sources, like NSF and NIH.

      One of the grad students wrote a parody of a tech report generating program that would create a new tech report given a few key words and the funding agencies. Input like "blob", "ident

    • You're just looking at the problem all wrong.

      You're not providing the guidance so the missle kills someone, you're providing the guidance so the missle DOESN'T kill all the doctors and patients in the hospital next door to the target.
      • Yeah sure the US delibretly avoids civiliands and making better missiles might be beter, but unfortunately the US also exports more military equipment than anyone else (I was told). As much as I don't like shrub (W jr) having the ability to kill at distance I would like it even less when these weapons are used by US's more draconian allies.
        • So we should get rid of our long range fighting capabilities?

          This is like saying "We should destroy our nuclear (newquelar) capabilities to promote world peace!". The whole point of having this kind of tech is so that even if enemies do get them, we can fight on their level, or (even better) above it.

          That is why we must keep developing weapons. Just because we stop doesn't mean everybody else will. If you outlaw guns, only outlaws will have guns.

          You can't even spell, so I don't think you're in the least
    • One of the projects most suited to the group would be making some processors for missiles and I definately wouldnt be happy about that.

      It's a given that missle technology is going to more forward over time.

      That said, are you sure you'd rather it be some other country's missles that get better sooner? Taking this decision a step further, would you rather that some other country get firepower superior to that of your own?

  • Mars rover concepts (Score:5, Interesting)

    by cybermace5 ( 446439 ) <g.ryan@macetech.com> on Sunday March 16, 2003 @06:50PM (#5525305) Homepage Journal
    The robot ideally needs to be able to navigate without fear of being stuck on a 2" pebble 100' from the starting line. Obviously you can't map 250 miles of terrain down to millimeter resolution, but you can design the robot to render such obstacles nonexistant.

    One concept is a large inflated sphere with light tread patches on the outside. The power/electronics pack is suspended inside with cables running to various points on the sphere. By adjusting the lengths of the cables, the sphere can shift the center of gravity and roll forward. A 6 to 10 foot sphere would allow most small obstacles to be avoided, then the robot only needs to note current position and the general surrounding topography.

    Major difficulties with this concept are high winds (unless they are blowing in the right direction!) and steep uphill gradients.

  • It is not open to all comers (Score:5, Interesting)

    by lfourrier ( 209630 ) on Sunday March 16, 2003 @06:54PM (#5525317)
    3.1 Team Must Be U.S. Entity

    The Challenge is open only to US entities. This includes U.S. corporations, U.S. non-profit organizations, U.S. universities, U.S. citizens, sole proprietors that are U.S. citizens or permanent residents, and partnerships of U.S. citizens or permanent residents.

  • Monkeys (Score:2, Funny)

    by Avsen ( 556145 )
    Everyone knows that any finite path can be traversed by an infinite amount of monkeys driving an infinite amount of cars (with infinite gas) over an infinite amount of time.
  • with accusations of wasting your tax dollars, think of it this way: would you rather pose this challenge to geeks at large or to folks in the employ of DARPA? Doing it the way it's always been done has resulted in tons of wasted $$$.

    Personally I have NEVER seen creativity anywhere like I have seen here on /.

    If it can be done, someone on here has probably done it already.
  • My family has a 160acre ranch and several junked vehicles we use as "go karts"

    If anyone in the San Jose Bay area can prove to me you can do the software/servo's and other software, I can at least provide a peice of shit car and a ranch for "beta testing"

  • Yeah, right. (Score:2, Flamebait)

    by WasterDave ( 20047 )
    Drive itself across a desert for ten hours then, like, get pizza or something? I think not. What they want is something that will drive itself for ten hours then go fucking BANG! and take out a whole shitload of unsuspecting Iraqi's.

    We're just, like, interested to see if it can be done. Here, have a million bucks. Sure, fuck you.

    Dave

  • Misunderstanding, possibly not reading (Score:5, Interesting)

    by rzbx ( 236929 ) <slashdot@rzb x . o rg> on Sunday March 16, 2003 @07:11PM (#5525391) Homepage
    It seems a lot of slashdot folk here don't read before they post. Some are already talking about avoiding other vehicles on the road. First off, do you really think they would allow a bunch of robotic vehicles to drive along side drivers? Second, it does mention across the desert both off and on road, but does not say anything about public roads where it must avoid other vehicles.
    Another thing mentioned was GPS. Someone complained about not being able to use GPS. If that person had done some reading (FAQ on the page) then they would have seen that a public GPS or a private autonomous GPS receiver is allowed.

    Now my thoughts on this challenge.
    A few things I think are most important here are:
    4x4 type of vehicle (truck, SUV, Hummer, Jeep, etc.) (Automatic prefered for ease of use)
    A must have GPS receiver.
    Infrared obstacle detection device (180 degrees) about 100 meters.
    Also, another device to analyze the terrain about 180 degrees around the front of the vehicle out to about 100 meters.
    Attach the GPS, obstacle device, and terrain device to a computer and also have the computer hooked up to the acceleration pedal, brake pedal, and shifter to put into park or drive.

    The terrain device would be the most complicated. Then all you would need is a few good programmers that can work with the data the different devices provide and your set. I'm not sure if such terrain devices exist outside the military, but I'm sure some laser/infrared/etc. engineers out there could produce a basic one. This project isn't as complicated as it sounds, but it would take some good engineers and programmers to finish. Just my thoughts.

  • Gambling junket (Score:2, Funny)

    by mabu ( 178417 )
    Nice to know that DARPA is now getting into the casino shuttle business.

  • this is a hard one - probably no winner first year (Score:3, Interesting)

    by bhdaly ( 646097 ) on Sunday March 16, 2003 @07:13PM (#5525398)
    According to the article:
    Examples of obstacles include ditches, open water, rocks, underpasses, and construction. All obstructions on the route can be either accommodated or avoided by a commercial 4X4 pick-up truck.

    Anyone that has gone offroad can attest to how hard it is to go 25mph consistently or on average. Add in to that the fact that you will have to backtrack and figure out alternate routes means your vehicle is going to be thinking fast and driving very fast.

    The article mentions part of the route will be on paved roads, so maybe you can make up a lot of time on those stretches.
    Definitely not a trivial challenge. but a fun one for sure. Some of the non-trivial ingredients: the offroad vehicle, gps for detecting way points and finish points, camera for detecting obstacles and terrain, algorithm to determine fastest speed for current terrain, feedback to determine whether you are getting close to tip over, algorithm for determining alternate routes.

    what else?
    • I haven't read the rules, but are hunter-killer pairs allowed? In other words, deploy your truck, but have a set of smaller (disposable) scout vehicles move ahead and transmit telemetry back to the main vehicle.

      Load your truck with about 20 scouts, and have them deployed on a half hour basis in sets of 3 about 10-20 miles ahead in order to map terrain and establish an optimal path for straight line, maximum speed movement. Scouts that fail to make it back before the truck guns it are considered casualti
  • 1- get a "Bender" costume

    2- change pulleys on my lawn tractor

    3- ?

    4- win race! profit!

    *possible step 3, carry 12 gauge, pick off pesky little tinny, whiny blinkenlights competition you see on the way
  • I can see it now; "Sorry Mr R2-D2 but your GPL doesn't cover for driving in Seattle."

    Or..."I gonna have to ask you to step out of the car Sir"..."Um, I *am* the car" ;-)

    Sorry, I'll get my coat...
  • any intended entrants out there want to disclose your secret plans?

    *quickly throws robot costume in the closet and shuts the door*

    NO! It's a secret! Go away! And geez, don't you know how to knock?

  • Team Slashdot? (Score:5, Interesting)

    by JWSmythe ( 446288 ) <jwsmytheNO@SPAMjwsmythe.com> on Sunday March 16, 2003 @07:55PM (#5525615) Homepage Journal
    G'morning all.

    This sounds like fun.. Personally, I don't have *ALL* the skills required to pull this one off, but if anyone's forming a team in the Los Angeles area, I'm in.. I have skills everywhere from the technical aspects of making a vehicle work to engineering of the hardware involved.

    I'm thinking something like a slightly modified S-10 Blazer, or K5 Blazer. Positraction (not available on the older S-10's) is a must. Probably the K5 would be the better choice, for extra room in the engine compartment for controls.

    I did a quick read through their forums. There's some interesting (and optimistic) talk of stereo vision through, laser vision/guidance, and ground evaluation through radar.. A few of the people sound like they have a clue, and some others didn't even read the rules..

    Some of them are talking about exotic hardware solutions, that they'll probably spend all the available time building, and then wonder why they don't have a working vehicle to go with it. Some others were talking about cool Xeon based systems, and forget that they get hot, and this is going to be running in a vehicle in the desert for 10 hours. One mentioned the hardships of hard drives, and doesn't even realize that you can use Compact Flash as your hard drive, and do stuff from there. No one yet mentioned using Linux.. :)

    My thoughs on a practical vehicle is a late 80's Chevy K5 blazer. Radar (like the backup radar in late model Lincoln's) to evaluate for local blockages. Vision system, like a stereo camera hooked up to a Linux box (this is where I'm at a loss. I don't think I could do this software).

    Steering control would be an electric motor with chain drive just before the steering box. That way, no major changes to the steering need to be done.

    Acceleration is a simple motor pulling on the throttle assembly, just like the vacuume accuator on cruise control.

    Braking would need to be something more substantial. probably a pneumatic ram on the brake pedal lever itself.

    I'd suspect it'll take a few computers to run it, but in something the size of a K5 blazer, we'd have no only room to mount it, but more than enough room to mount it preventing shocks... The computers would need to be hard-drive free though.. Compact flash cards of say 512Mb would be just about all we'd have to work with. That should be sufficent though.

    The site says they're providing several checkpoints which are mandatory to pass through/stop at. There will also be mandatory waypoints, which define the path. Fairly easily, go from waypoint to waypoint. If there's an obstical, decide for left or right turn to go around.. More than likely the easiest thing would be to use GPS to establish a location (when available), and use other public navigation beacons the rest of the time.

    Anyone who's flown knows how many radio navigation beacons are available. :) Radio stations make for decent markers too. Since you have something the size of a truck, it would be a piece of cake to triangulate distance and direction to any one becon, and use any two to fix location.

    When you detect an obstical, mark it on an onboard map, and figure out a way around. That would be for big obsticals like canyons or mountains. Small obsticals, you steer around.

    I can design and build anything required to make the vehicle itself work. Navigation will be up to someone else. This is/will be a team project, so as many hands as we can get involved would be cool.

    Can we get Cmdr Taco's permission to put "Slashdot" down the side of the truck? :)

    Who's in? Reply here first, then we'll get in contact in real life.

  • The story isn't clear, but reading the article reveals that it must be a ground vehicle. Pity; I had a great suggestion: a Tomahawk cruise missile.

    Matter of fact, I have a second great suggestion: run the challenge from Vegas to LA.

  • Italian Linux-based project should compete (Score:5, Funny)

    by HuguesT ( 84078 ) on Sunday March 16, 2003 @08:04PM (#5525657)
    No offence to Italian drivers, but this little project developed an autonomous vehicle using Linux, that could drive on Italian highways. Pretty impressive!

    the ARGO project [unipr.it]

    If you've ever driven in Italy you should be impressed too...
  • Let's just say it involes some blinking LED's, a few junk motherboards, 4 Square yards of tinfoil, and kidnapping Jeff Gordon.
  • Does anyone else think that a 1 million dollar prize is a little low for someone that can actually pull this off? Just given the value of the people's time, equipment, not to mention the cost of transporting the vehicle to LA and costs associated with the competition itself, anyone doing this for less than a $100,000 would have to be quite frugal.

    Also, I didn't see anything about rights to the technology you develop.. does DARPA get that if you win, or do they have to negotiate seperate contracts with the

  • I suppose the obvious solution would be to find a relitivly straight road between the two points and build a small, gas powered vehicle to follow the line on the insideside of the road,between highways. Assuming no cars are pulled over, you're good... Of course getting off the highway is a slight problem... but what fun would it be without a challange?

  • Caltech/JPL (Score:3, Interesting)

    by majordomo ( 111692 ) on Sunday March 16, 2003 @08:47PM (#5525859) Homepage
    I have on good authority that the Jet Propulsion Laboratory has a huge lead over most competition. They already have autonomous vehicles that can travel at ~15 mph over very rough terrain. Keep your eyes out for the Caltech/JPL team to make some real waves.
  • Elwood Blues: It's 106 miles to Chicago, we've got a full tank of gas, half a pack of cigarettes, it's dark and we're wearing sunglasses.

    Jake Blues: Hit it!

  • My favourite quote (Score:4, Insightful)

    by nebbian ( 564148 ) on Sunday March 16, 2003 @11:31PM (#5526543) Homepage Journal
    If a Field Judge is unable to continue in the Safety Vehicle, and that inability is of a temporary nature expected to take less than ten minutes to resolve, the Field Judge shall instruct the Safety Vehicle driver to stop, and shall record the time of stopping so that the time stopped may be subtracted from the elapsed time for the team.

    Perhaps that should read:
    If a Field Judge needs to take a leak, then teams must stop when asked. Team members, on the other hand, are expected to be able to control their bladders.

  • Comments by an entrant (Score:4, Informative)

    by Animats ( 122034 ) on Monday March 17, 2003 @12:05AM (#5526710) Homepage
    We're entering this. [overbot.com] A few comments.
    • You can't game your way around the rules. You have to describe your approach to DARPA in writing, and DARPA reserves the right to change the rules after entrants have submitted their technical specs. They want a useful autonomous vehicle, not a trick.
    • The rules have changed several times, and will change again. There's supposed to be a more or less final version on 1 April 2003. Right now, the announced plan is Barstow to Las Vegas in 10 hours.
    • You can't preplan the whole run using map data, aerial imagery and GPS. DARPA will do things to make that not work, like placing some obstacles on the route. Note that you get the route, in the form of about 1000 waypoints, two hours before the race.
    • DARPA does not guarantee that the course will be cleared of other persons and vehicles. Early versions of the rules said that the course would be cleared, but then DARPA changed the rules. [overbot.com] Now it's only a "best effort" thing. Some competitors pulled out at that point. There will be sweeps ahead of the robot vehicles, vehicles following behind with remote emergency stop buttons, and road closures, but somebody still might not get the word. The route isn't on military bases; it's on Bureau of Land Management land open to the public. DARPA claims they will come up with an insurance carrier that will provide liability coverage, but so far, that hasn't happened. Vehicles thus need very good safety systems.
    It's a nice engineering challenge. All of us have solved tough problems in the past, and we've all done serious robotics work. This looks within reach, although difficult.

  • Hang on, hang on... (Score:4, Insightful)

    by Simon Brooke ( 45012 ) <stillyet@googlemail.com> on Monday March 17, 2003 @06:16AM (#5527849) Homepage Journal
    This is a competition to get an autonomous vehicle 250 miles over mixed terrain in 10 hours - i.e. an average speed of 25 miles an hour. The vehicle explicitly mustn't carry a crew and it doesn't seem to have to carry any payload.

    The heavier the vehicle is the more kinetic energy it has so the more problems you have negotiating obstacles. Furthermore, the heavier it is the more likelihood that it will damage itself in collisions or rollovers. Also, the heavier the vehicle is, the more energy it will consume, so the more fuel it needs to carry, so the heavier it is...

    The solution to this problem, from a chasis point of view, is to build the lightest machine possible consistent with carrying a laptop computer, two video cameras and a small radar. If I were building it I'd aim for a lightweight carbon-fibre moncoque shell with a generally curved shape; large, lightweight wheels like mountain bike wheels; a small air-cooled four-stroke engine - say 100 to 250cc; a cone type continuously variable transmission; and a robot wars style self righting mechanism. I'd aim for at least 100 miles per gallon on-road fuel economy and carry four gallons of fuel in an underslung fuel tank for a fully fueled up weight of under 150 pounds.

    Structurally the key thing would be to protect the cameras and the radar. Not only do you not want them to be damaged, you don't want their mounts to get bent even the slightest bit out of alignment.

    On the road sections of the course you'd use stereoscopic vision to establish road position as with the Italian ARGO project mentioned earlier, possibly with the object detection assisted with radar. You'd go as fast as you possibly could on road sections to build up average speed.

    Off road you'd use primarily radar to assess forward obstacles. The strategy would be to steer a near direct course deviating around small obstacles. If a large obstacle was encountered, you'd backtrack 100 yards, turn 30 degrees one way, and go forward; if that didn't work you'd recursively back up more, turn the other way, and try, until you had passed the obstruction, at which point you'd plot a new direct course and carry on.

    But the key things, it seems to me, are keep it small, keep it light, keep it simple.

Slashdot Top Deals

Do you suffer painful elimination? -- Don Knuth, "Structured Programming with Gotos"

Close