Catch up on stories from the past week (and beyond) at the Slashdot story archive

 


Forgot your password?
Close
typodupeerror
×
Robotics United States Science Technology

Will There Be A Winning Autonomous Robot in 2005? 158

Posted by timothy from the time-for-a-darpa-change dept.
An anonymous reader submits "This summer is heating up the DARPA Grand Challenge as multiple top notch schools begin to announce their entry into the competition. The newest organization to announce its entry was the Florida Institute of Technology. Their project is known as Oasis - Autonomous Racing, and they have a team of over 45 students, professors, and advisors that are currently hard at work designing their vehicle and raising funds to pay for it. The DARPA Grand Challenge is a race between vehicles that should be designed to travel up to 300 miles in less than 10 hours through the desert or other harsh medium without any human interaction. The 2005 competition has a $2 million grand prize as authorized by congress. With all of the new entrants does anyone think that the competition will be won the second time around?"
This discussion has been archived. No new comments can be posted.

Will There Be A Winning Autonomous Robot in 2005? More

Will There Be A Winning Autonomous Robot in 2005?

Comments Filter:

  • Doubtful (Score:5, Interesting)

    by 7Ghent ( 115876 ) on Saturday June 05, 2004 @09:40PM (#9347825) Homepage
    Well, considering that the best performer for this year didn't even make 15 miles, I'm hopeful that someone will actually complete the course, but not in under 10 hours.

    • Re:Doubtful (Score:5, Funny)

      by wakejagr ( 781977 ) on Saturday June 05, 2004 @09:46PM (#9347848) Journal
      how about an award for getting past the first turn? that first left turn was too much for quite a few of the contestants in the first challenge.

    • Re:Doubtful (Score:1, Insightful)

      by JPriest ( 547211 )
      300 miles in 10 hours is 60 mph (96 kmh) average. The 300 miles is the way the bird flies, actual driven miles after obstacles is more. Also, having to compensate slowdowns for maneuvers, the vehicle will need to frequently manage traveling at nearly 100 mph (160 kph) to complete to course on time.

      Considering this is not a paved road (or even a path to follow) this task might be difficult for even many human drivers without the right vehicle.

      I hope the new contestants learn a great deal from last years chal

      • Re:Doubtful (Score:5, Funny)

        by Jack Porter ( 310054 ) on Saturday June 05, 2004 @10:08PM (#9347975)
        Not sure where you went to school, but IIRC 300 miles in 10 hours is 30 mph.

      • Re:Doubtful (Score:4, Funny)

        by Nugget ( 7382 ) on Saturday June 05, 2004 @10:26PM (#9348041) Homepage
        At first I thought that this post represented a new slashdot low (Math is hard, let's go shopping!) but then I noticed that the damn thing has been upmodded twice.

        JPriest may just be having a caffeine-free day, but who are the two jagfucks who thought this was interesting and insightful?
        • LOL I noticed that after I posted but figured I would see how long it took for someone to respond with the correct numbers.

          PS. I think I pulled the 60 mph # from an article I read on the first challenge a long time ago, did the numbers change since the first challenge?

          • PS. I think I pulled the 60 mph # from an article I read on the first challenge a long time ago, did the numbers change since the first challenge?

            No. It's always been 300 miles in 10 hours. If someone said 60mph, their math was very, very wrong.

      • Re:Doubtful (Score:2, Informative)

        by renec ( 16822 )
        Is that the new math?

        You know how to convert to metric, but when you divide 300 by 10, they get 60. I'm assuming you asked google about the metric conversions.

        The average speed is 30 mph, or a bit under 50 Km/h

    • Yeah, I think they should also make the course harder. Let me hunt their robots; sniper rifle on a ridge... Fun for everybody. Also, add a battle bot aspect. If you can kill the other competors that totally shouldn't be forbidden.

    • Re:Doubtful (Score:5, Interesting)

      by ciroknight ( 601098 ) on Saturday June 05, 2004 @10:06PM (#9347960)
      I don't doubt it for a minute. Being a Florida Tech freshman in the fall, I want to try to get involved with this project. I've worked on stereo optics systems before using two webcams and I can tell you that this kind of system holds great promise at winning the race. In combination with great laser range-finding and possibly optical range finding (something like us humans do), even acustical systems, a machine has just as good of a chance to pilot a car as it can an aircraft or anything else.

      Another thing: use the 2d images to build a 3d map on the fly, approximenting object sizes by finding the edges of the object in the pictures, and you should be able to navigate around and over them quite easily. The car also plays a key roll; it needs to be adapted into a dune buggy of sorts; huge soft tires and great suspension.
      Scary that we're working on this for the government though..

      • Re:Doubtful (Score:4, Insightful)

        by Quixote ( 154172 ) on Sunday June 06, 2004 @12:14AM (#9348367) Homepage Journal
        Another thing: use the 2d images to build a 3d map on the fly, approximenting object sizes by finding the edges of the object in the pictures,

        Try finding the edges in a bush or a clump of tumbleweed...

        • Re:Doubtful (Score:4, Interesting)

          by ciroknight ( 601098 ) on Sunday June 06, 2004 @12:36AM (#9348473)
          Trust me, I understand that too, but that's when you have to get into surface approximentations and such. If a surface looks scattered like a clump of grass, then it's booleaned from a screen of black. The resultant image should be easy enough to pattern match to images of trees, rocks, brush, or anything else in a library. Dunno how well this would work in real-life, but this is what I did with my little toy model and it worked well.

          Another way might be to test the density of the object, or to use color like we humans do.. If somethings green or yellow and sparce, it's more likely tumbleweed or a bush, otherwise it's a rock.

          Lastly, at certain speeds, objects of certain sizes should be tossed out. If it's the size of a small mellon *smaller than a water mellon lets say*, then just throw the object out. It's not going to effect the car going at a speed of 35-65 MPH if the car's built right.

          Just a few ideas. If I do get the chance to be in the project like I'm hoping, I'll get to test a few of them. Otherwise it's probably just idle chatter. Either way, it's something to think about.
          • I'm not sure your car tires will like hitting, say, a pointed rock at 60 MPH even if it is smaller than a watermelon. You will have to be REALLY careful about what you toss out.
          • And when you're travelling at (say) 30mph, the motion blur will make it even more difficult.

            I do work in machine vision and image processing. There is a huge leap between what's possible in theory, and what's practical.

            I'm not trying to discourage you (or anybody) here, so if you _do_ manage to get something that works well, I'll be very happy to read how you did it.

            BTW: there are rocks which look yellow and scatter light, looking sparse. In the desert, almost everything's yellow.

      • The car also plays a key roll

        Exactly. Remember playing with you first RC car? It got stuck on all sorts of things and flipped over and got stuck upside down.

        Then they came up with those dual track-driven machines [ebay.com] that didn't even have servos, just cheap DC motors. Not only did they do all steering via the "tank-treads", but by designing the body to fit between the belt/track/treads, the designers ensured the machine could be flipped completely over without getting stuck. Not to mention that it navigate
      • Nice try to sound smart, but its not like your the first to think that robots should have sensors.

        Red team's sensors [redteamracing.org]

        It utilizes scanning radar, stereo vision, and scanning laser ranging. Position and orientation are estimated by six-axis inertial sensing and axle encoding that are fused with GPS by an Applanix pose estimator. Additionally, position is sensed by OmniStar GPS.

        Generating models from digital sensor data is not simple. Integrating sensor data with machine intelligence is a profound chal
        • First of all I'd like to thank you for being so condesending.

          Second of all, no, I'm not the first to invent, implement, design, or think about sensing. It's a _necessity_ for this project. All robots must be capable of this in order to complete the trek.

          2D images to 3D mapping actually did work for me, though yes, I do know the limitations of it. My idea for the project would be to use many more cameras taking pictures one at a time at set intravals and from different angles and more or less do rev
      • In combination with great laser range-finding and possibly optical range finding (something like us humans do), even acustical systems, a machine has just as good of a chance to pilot a car as it can an aircraft or anything else.

        As a licensed pilot, I call bullshit. There's more to piloting an aircraft than actuating controls to get you from point A to B. There's a hell of a lot of decision-making that requires context (for just one example, see here [google.com] for the idea, and here [faa.gov] for why it doesn't work), not to

    • Re:Doubtful (Score:5, Interesting)

      by rmohr02 ( 208447 ) * <mohr.42NO@SPAMosu.edu> on Saturday June 05, 2004 @10:15PM (#9348013)
      Ohio State had a team that entered this year, and they worked on their entry right next to the workspace of a project team I'm a part of. I heard, albeit secondhand, why most entries didn't work, and the only real reason is that the teams were unfamiliar with the course (e.g., Columbus doesn't exactly have a large desert to test the entry in).

      A couple nights before the competition was to take place, it rained on the "course", as it is. Thus, there were many relatively large bushes in the desert when the competition started. This was not something most teams had planned for--however, they did plan for large rocks. Thus, a 9' tall truck would drive up to a (now relatively small) bush, detect it, determine it was a rock, and then try to plot a course around it rather than simply driving through it, which would have worked fine. With the number of bushes that had sprouted up, it was only a matter of time before a truck's computer got swamped trying to avoid all of the "rocks".

      I look forward to hearing about next year's competition, for which I'm sure teams will think to find a way of differentiating a bush and a rock.

      • Re:Doubtful (Score:4, Insightful)

        by homer_ca ( 144738 ) on Saturday June 05, 2004 @11:58PM (#9348308)
        That's the perfect example of something that's easy for humans and hard for robots. It's one thing to detect the presence of obstacles. It's another to identify obstacles and determine their risk to vehicular progress. We know oil is black, shiny and slippery. We know rocks usually look jagged and the color of dirt, and they're hard when you run into them. We know that it's a long way down if you fall over a cliff ledge. If there's a cliff wall going up on one side of the road and down the other side of the road, we know that falling off the cliff is much more dangerous than hitting the side of the mountain, at least at low speeds. It's common sense things like this that humans just know, and it's hard to program every possible scenario into an AI.
        • Of course, I hope "smart" vehicles don't just learn to identify obstacles merely by their risk to vehicular progress. If these robotic cars ever plan to be useful, they're going to have to learn not to run over things just because they can and it is computationally more efficient.

          This does remind me of that "made for TV" Knight-Rider reunion where Michael's new car ran over a deer because it was calculated to be more efficient that slowing down. We all know that David Hasselhoff is a great actor.... Act

      • Re:Doubtful (Score:2, Insightful)

        by murmurr ( 703247 )
        Ummm, those bushes don't spring up overnight. Not to more than a couple of inches, anyway. Nevertheless, since there was some sort of "roadway" for the entire length of the route, there was really no need to distinguish between rocks and bushes. If your vehicle was intended to steer around a 2" rock, then you had made a fatal mistake before leaving the gate.
        • First of all, I heard this secondhand, from a grad student who knows many of the people on Ohio State's team. I don't know the size of the rocks nor the bushes either.

          Also, there may have been a roadway for the length of the route, but one of the big points of the Challenge was that teams would have to hit 20 checkpoints given to them immediately before the race starts and dynamically find routes to them. It seems to me that while you may be able to go directly to the end of the race on a road, you would
      • While there were some bushes off to the sides, the main roadway (dirt) was clear of any plants. Most likely the vehicle (TerraMax in this case) got off course and was unable to get back to the road. They needed a watchdog feature, if you back up 20' and there's still an object, ignore it and go forward. They backed up for half a mile before hitting the kill switch. Also, there wasn't any rain... The skies were clear and ground dry when we got there at 4:30am...
        • Well, as I said, I heard this secondhand. It seems like you were there, so I don't claim to know more than you. I just didn't see any posts mentioning something similar to what I had heard, so I posted.

          It does sound like the gist of what I said is correct though--the truck saw a bush and, rather than driving through it (which TerraMax could do without much trouble), it tried unsuccessfully to find a way around it.
    • is whether the winning robot will have a "CAPS LOCK" key.

    • Good (Score:1, Offtopic)

      by Adolph_Hitler ( 713286 )

      We humans will remain useful as long as robots are stupid.
    • Unless there are some incredible advances this time around, there's no way anyone will even go 50 miles. I would say maybe in ten years. I think it's less of an issue of raw computing power, and more about developing more effective techniques in processing the information.
    • ...the OSS community come up with an entry?

      Do as much as possible in simulation, including physics modeling and damage. An excellent proof-of-concept.

  • For God's sake.. (Score:3, Funny)

    by GeneralEmergency ( 240687 ) on Saturday June 05, 2004 @09:41PM (#9347828) Journal

    ...I hope nobody names their AI unit "SkyNet".

    Now, where did I leave those keys to the bunker?

  • Short answer ... (Score:5, Insightful)

    by Manip ( 656104 ) on Saturday June 05, 2004 @09:42PM (#9347833)
    No.

    I don't think anyone will win this time around. The problem is that the current technology can't deal with unknown situations/objects, maybe in a controlled enviroment with selected things added and removed but in a desert there is very little chance. If someone does win it will be more down to luck than actual computing power.

    • Re:Short answer ... (Score:3, Insightful)

      by ejaw5 ( 570071 )
      I think if you do a bit of research, you can find microcontrollers and the sensors needed to accomplish the task. Not to simplify the Grand Challenge, the objective is to have a vehicle traverse through a desert terrain while avoiding other vehicles and obstacles. Given enough time, any good electrical enginnering student(s) can come up with some good ideas on solution with some possible hardware choices.

      The Challenge to DARPA isn't the technology, but the testing phase, or lack there of. How many of th

    • Re:Short answer ... (Score:5, Insightful)

      by Waffle Iron ( 339739 ) on Saturday June 05, 2004 @10:36PM (#9348069)
      The problem is that the current technology can't deal with unknown situations/objects, maybe in a controlled enviroment with selected things added and removed but in a desert there is very little chance.

      What it boils down to is that there's something horribly wrong with the current approach to "AI". Nature solves problems very similar to this with a totally different approach. Take a cockroach for example. Its task is probably much harder than this "grand challenge". It must survive in the world for several weeks or months while: finding its own fuel, avoiding hostile predators, finding a suitable mate, and include a control system that supports walking in any orientation along with controlled flight through the air.

      What computing horsepower drives this task? A few milligrams of wet neurons that probably consume a few microwatts.

      Even if a cockroach weren't up to driving one of these vehicles through the desert, any small bird probably has enough signal processing power to handle the chore. They certainly are able to handle flying through a thicket of tree branches, a pretty tough challenge in itself. How much does a house finch brain and vision system weigh? Maybe 1 gram?

      Back in the 80s I majored in AI briefly, and I quickly came to the conclusion that the incredible pattern matching abilities of living organisms can't be effectively modeled by piping numbers through a single accumulator register. The highly interconnected architecture of a brain is totally different. (Many of my professors seemed to think that they had some deep secret insight to "intelligence" because they were hacking in Lisp. What was really happening was that they were caught up in their own cleverness in using recursion and macros to create layers of abstraction. But that's just tricky discreet math, not self-awareness.)

      Now that computers are 1000X faster, my assessment is still valid. In fact, computers probably aren't even nearly 1000X faster at the algorithms that living organisms use to deal with the real world, because all of the computer speed tricks rely on locality of reference (caches). A brain, OTOH, is a fully associative processor that can compare an large chunk of input with a good amount of its entire memory in a single atomic operation. Its power comes from not having locality of reference.

      IMHO, attempts at these kinds of projects are always going to result in clumsy, kludgy, stupid machines until some totally new approaches are developed for processing and information retrieval.

      • Re:Short answer ... (Score:2, Insightful)

        by Wog ( 58146 )
        And these design differences, my friend, are what seperate the mind of man from the mind of God.

        Burn, karma, burn!
      • A cockroach hmm? Try BEAM robotics, perhaps the unibug? [lanl.gov] Analog only, yet still much better than most digital bots. I'd say that's a good enough new approach to start out with.
      • What makes the cockroach smart?
        Evolution. The "dumb" animals tend to die before they can mate(or at least produce a significant amount of offspring)
        In academia and industry(well, industry is somewhat debatable, I know plenty of companies that should have died out years ago :P) there is evolution. Good ideas get funding, bad ones don't and tend to thus die off. It took a long long time for the cockroach to evolve, 20 years is a drop in the bucket.
        Once again evolutioin will prevail.
      • I agree for the most part. Except:

        "What it boils down to is that there's something horribly wrong with the current approach to "AI"."

        I think that this depends which "current approach" your talking about. I don't personally know those working with AI, but when you get down to it, just about all scientists are in a sense are working on AI. Every field is related in some way or another. A programmer is working on an AI that works in binary, taking various input from any kind of device, doing the math, th

        • Mod me down (Score:2, Informative)

          by wonkavader ( 605434 )
          But while I'm interested in the beginning of that paragraph, and the end, I'm not gonna read what's in the middle.

          The return key is your friend.
      • IMHO, attempts at these kinds of projects are always going to result in clumsy, kludgy, stupid machines until some totally new approaches are developed for processing and information retrieval.

        That, however, is exactly the point of these kinds of challenges. If you throw a ton of money at a handfull of military/private researchers, they are most likely to travel down the path of the known. If you manage to get a bunch of people (students, most likely) competing, then simply because you have a *bunch*
      • 1000x

        Your post suggests that we understand how the mind learns and thinks - say a neural network.

        While simulating a neural net in a finite register model may be ineffecient - it is nonetheless a suitable test of the theory of thought.

        In short. If the problem is merely speed - we should come to the same quality of conclusion - given more time.

        building silicon to more effeciently run a given set of instructions is not out of reach - if the algorithms truly perform.

        They don't.

        Learning has as much to do w
  • But is a year a great enough span of time for teams to overhaul their entries?

    It is not like the teams were only miles from finishing the race: most teams couldn't even handle a few hundred yards.
  • Do you have to pay taxes on the $2mil?

  • It's not about winning... (Score:4, Insightful)

    by Wiser87 ( 742455 ) on Saturday June 05, 2004 @09:45PM (#9347847) Homepage
    The whole point of the race is to see how well non-government groups solve these problems and to gain new insight on how to use technology.

    Just getting something that works makes them winners.
    • The whole point of the race is to see how well non-government groups solve these problems and to gain new insight on how to use technology.

      Just getting something that works makes them winners.

      Huh? Define "something that works". None of them completed the course so you obviously mean something less than that. A robot that manages to get out of the starting area? One that doesn't flip over on the second turn? I'd say none of them are winners, but now they have valuable experience. Don't devalue the future

  • Going out on a limb... (Score:5, Insightful)

    by DocJohn ( 81319 ) on Saturday June 05, 2004 @09:53PM (#9347881) Homepage
    I know we're going to hear mostly naysayers here, saying "Well, gee, they couldn't even make it 15 miles this year, what's the chance of anyone actually winning in a year's time!?"

    I think there's a good possibility that someone can win it. Think about it. This past year, none of the teams had any first-hand, direct experience with this course or the challenge. So now every team has all of the experience and data from this year's challenge, and could not only see what went wrong with their team's entry, but the problems faced by every other team (motorcycle entry notwithstanding).

    I think the computing power is there. If the teams learned anything from this year, it should be that GPS isn't sufficient in and of itself. You need to far more creative. Every system should have 2 or 3 redundant subsystems.

    I think it can be done, and I think there are enough creative people working on the problem that it wouldn't surprise me to see a winner next year.

  • Short answer... (Score:4, Interesting)

    by sinner0423 ( 687266 ) <sinner0423@gm[ ].com ['ail' in gap]> on Saturday June 05, 2004 @09:55PM (#9347892)
    No. Last time a good 30%, I believe, didn't even make it out the gate. I seriously doubt any of them will "win". Well, I'm sure they're all winners, like in the special olympics, but i don't think they will FINISH the course.

  • With the closed nature of the competition, no. (Score:5, Insightful)

    by dexterpexter ( 733748 ) on Saturday June 05, 2004 @09:56PM (#9347901) Journal
    If the prior entrants are any indication, than no. Those entrants shows just how unprepared they were. As a engineering student on a team that has built/is building an autonomous robot (not associated with DARPA), my evaluation of the vehicle designs left me terribly disappointed. In fact, part of me things my own team could have thrown our present navigation hardware/software onto an ATV and been more competitive than the other DARPA entrants. In fact, had DARPA not been so selective in their choosing of robots to enter the competition (which, in my opinion went against the spirit of an open competition), we might have done just that.

    A few responders have said that the technology just isn't there for autonomous navigation. I disagree. It just needs to be refined. Robots for the IGVC can navigate unknown environments respectably, and these are unfunded, poorly staffed projects ran by undergraduate students.

    I believe that the next competition's entrants will make it much further than this years, but looking at the stock, similar designs that DARPA let through, looking at bells and whistles rather than creativity, my hopes are not high for having a winner. They need to re-evaluate the meaning behind an "open" competition of ingenuity and consider that the most expensive, technologically-advanced robot is not always the answer.

    Look at the first year IGVC. Colleges spent thousands of dollars on big, relatively the same robots and the University of Tulsa came in with a PC bungeed to a child's car and beat them all. I don't pretend that the IGVC robots are competitive against the Grand Challenge ones, but the point is still the same: make it an open competition, and perhaps we might see some *real* ingenuity and then, in the future, a winner.

    Money d.n.e. ingenuity

    That said, I tip my hat to the previous entrants. How neat is this competition!? (even with its limitations)

  • Highly doubtful (Score:5, Funny)

    by OblongPlatypus ( 233746 ) on Saturday June 05, 2004 @09:58PM (#9347909)
    According to the May issue of Wired, the best team got through only 7.4 of those 100 miles before breaking down. There are some funny quotes in the Wired article, showing just how miserably far away we are from true autonomy:

    What went wrong: "Lost GPS signal. Forgot there was a mountain between it and next checkpoint. Tried to drive through mountain."

    Lesson learned: "Go around mountains, not through them."

    What went wrong: "Interpreted small bushes as enormous rocks and repeatedly backed away from them."

    Lesson learned: "Get new sensors that can distinguish between bush and rock."

    This all sounds pretty pathetic, but having just completed a master-level course in artificial intelligence, I suddenly understand just how difficult some of these issues are to solve. Let's face it: We won't see anything even approaching true autonomy in anything but tightly controlled environments for years to come.

    I conclude with the best quote; not really AI-related, but still simply hilarious:

    What went wrong: "On-off switch located on side of vehicle. Bumped into a wall on way out of start area. Turned self off."

    Lesson learned: "Put the on-off switch somewhere else."

    • I mean 142 miles, not 100. 142 is the number Wired quotes.

      The /. blurb mentions 300 miles, but the Q&A on the DARPA page says "will not exceed 300 miles". Apparently the course is randomly selected and only revealed on the race day, to make sure the vehicles aren't trained for the specific race course. I'm assuming the Wired quote means that the course that was picked for this 2004 challenge was 142 miles long.

    • rallying (Score:4, Interesting)

      by SuperBanana ( 662181 ) on Saturday June 05, 2004 @10:23PM (#9348036)
      Lesson learned: "Get new sensors that can distinguish between bush and rock." This all sounds pretty pathetic, but having just completed a master-level course in artificial intelligence, I suddenly understand just how difficult some of these issues are to solve.

      Watch a rally. Rally drivers have codrivers w/notes, and prior knowledge of the course...but I believe with Baja it's mostly seat of the pants; Paris-Dakar has got to be since it's so damn long, but I could be mistaken. They average well over 60mph on a course that's got to be much worse than anything DARPA came up with. Of course, they have astronomical component failure and driver error rates (as well as the occasional wildlife incident- one rally team hit a cow at well over 60mph, it was NOT pretty- I think they also got arrested, because it was a serious crime in the host country, akin to murder, to kill a cow), and at 60mph, rocks look like bushes and bushes like rocks, until it's way too late to do anything about it. Rally teams just bolt up more plating on the important stuff, and hope for the best.

      What went wrong: "On-off switch located on side of vehicle. Bumped into a wall on way out of start area. Turned self off." Lesson learned: "Put the on-off switch somewhere else."

      While not defending them, it was probably an emergency disconnect switch, which you do want to be highly accessible for those times when, say, it starts driving away (or towards something) and shouldn't have. Yes, DARPA required radio safety switches, but do you really want to trust your life to just a radio disconnect?

      Honestly, some teams were just stupid in their use of money and priorities- I got a huge kick out the team that had a giant plasma display TV in the passenger side of the cabin. What the -fuck- was that for, watching the Superbowl while the car drives you to the next checkpoint?

      • Baja (Score:3, Informative)

        by crisco ( 4669 )
        Depending on the class, the Baja (and other desert races) contestants depend heavily on co-drivers, GPS and proper preparation. They run over the entire course before the race (hence the 'PreRunner' style of trucks) and rely on maps, GPS and the co-driver's experience.

        Motorcyles and the trophy trucks averaged nearly 60 MPH on the last Baja 1000, other classes are slower.

        I wish Rally driving were more popular over here in the US of A, so much more excitement than big ovals.


    • What went wrong: "Interpreted small bushes as enormous rocks and repeatedly backed away from them."

      Lesson learned: "Get new sensors that can distinguish between bush and rock."

      This is how a toddler learns: bushes do budge, rocks don't budge. Except for the ones which looks like bushes but are made of rocks. Pushing the bush and see if it gives way, that's a good way to see if it is a rock or a bush. Then decide if you want to fall on it or not.
    • The main impression that I get from the Wired list [wired.com] is "WTF, did they test their vehicles at all??"
      Because 4 vehicles out of 13 didn't even get out of the start area!
      I develop software for living, and while it is admittedly for easier tasks than autonomous desert-crossing, we test our product in hundreds and thousands of different situations and throw all kinds of shit at it to make sure it doesn't just die in some weird deployment scenario. I am really curious how much effort these teams spent on just testi
    • What went wrong: "On-off switch located on side of vehicle. Bumped into a wall on way out of start area. Turned self off."

      Lesson learned: "Put the on-off switch somewhere else."

      I get to see this almost weekly in real life: My Roomba, which I'm very happy with otherwise, occasionally turns itself off by bumping its switch against those springy door-stopper things. Maybe the newer ones have the switch located on top or something. :-)

  • How hard would it be... (Score:3, Insightful)

    by JawnV6 ( 785762 ) on Saturday June 05, 2004 @09:59PM (#9347914)
    to hide a Little Person inside one of these things? Baron Kempelen got away with such a scheme for quite a while... The Turk [museumofhoaxes.com]
    • Just make it radio control via some highly unusual method. For instance, you could "transmit" data by intermittantly jamming GPS signals, and as your bot already has a GPS receiver no one would be the wiser.

  • It might happen... (Score:5, Informative)

    by sgtsanity ( 568914 ) on Saturday June 05, 2004 @10:01PM (#9347926)
    BTW, for all those interested, Wired ran a list of what went wrong [wired.com] for each team. It reads very comically, but a lot of these things are very "DUH!" after you've gone through the first time. I forsee a lot better results, as teams will have that much more practice. Hopefully some will come up with some more general solutions, rather than brute-force processing the terrain around the known area of the route.

    • Re:It might happen... (Score:3, Informative)

      by Anonymous Coward
      None of the teams managed to do much brute-force terrain processing, because in general, their sensors didn't work.

      The one that got the farthest just ran off of pre-computed GPS waypoints, and as the GPS accumulated drift error, it started driving to one side of the road, then in the ditch, then off road, until it hit something and stopped.
    • Thanks for the link - great laugh.

      Especially the six wheel ATV that had the on-off switch on the outside of the vehicle and turned itself off when it hit a wall!

  • 2million in 1 year is the hard bit. (Score:1, Insightful)

    by Anonymous Coward
    The technology certainly does exist to achieve it. However from a project point of view the limits are the 2million and 1 year to do it.
    If you were to have 3 to 5 years, 20 programmers, say 6 electronic engineers and a few mechnical engineers i think It would be rather easy. I dont mean grad students either, I mean people with 5 to 10 years and a few seniors from relevant fields. Of coarse this isnt going to happen for 2million and management of a team this size would require integration time of around at

  • Yes. (Score:4, Funny)

    by simetra ( 155655 ) on Saturday June 05, 2004 @10:48PM (#9348092) Homepage Journal
    His name: Al Gore.


    Thanks, I'll be here all week. Be sure to tip your waitress.

  • DARPA? (Score:1, Funny)

    by Anonymous Coward
    all this; just so the cia can run over arabs without even having to use a remote.

  • Slashdot entry (Score:5, Funny)

    by Anonymous Coward on Sunday June 06, 2004 @12:37AM (#9348477)
    Surely with all the talent on Slashdot, we could create a winning entry?

    Name suggestion: The Autonomous Coward

    • You could use my patent-pending AI for the Slashdot entry. It's name is "Brick on the Accelerator".
      Don't worry after the race, we'll can release the source code.

      Sad thing is it could have beaten several of last year's entries.
  • ... so I could build a vehicle that looks and seems real, but holds a "little person" in a hidden compartment.

    Yes, in the end it would, of course, be disqualified, but think of the fun you'd have while it lasted. 100% accurate voice control anynone? :-)
    • 100% accurate voice control anynone?

      Assuming, of course, that your midget isn't deaf.

      "Turn left!"
      "What?"
      "TURN LEFT!"
      "WHAT?!"
      "Don't shout at me, you're the one who can't hear me!"
      "WHAT!?!"
      **crunch**

      Although if I had to choose between a deaf midget or a blind one, I guess I'd have to choose the one that can see what's coming.
  • I predict that this will finally be won by a Cat D6 (bulldozer) based vehicle. Drive through small things. Don't get caught up in barb-wire fences. A little GPS and some vision thing for detecting deep holes and you're there.

    • There is a rule against damaging the terrain (Score:5, Informative)

      by dexterpexter ( 733748 ) on Sunday June 06, 2004 @02:32AM (#9348745) Journal
      The only problem I could see with this is that driving through things was not seen as an acceptable solution by DARPA. It stipulated that the terrain and obstacles must be left unharmed. I think there are reasonable allowances made, such as running through "weeds" and leaving faint tire tracks.

      Sending a bulldozer through something, however, would likely cause harm.

      The motive behind this, if I get to guess, is that they are looking for a more covert vehicle. Something that has torn through the terrain and left chaos in its wake is more likely to be tracked/disabled than something that can quickly and nimbly navigate across the terrain.

      I think that your idea is a fine idea, though. If they are looking at application for war situations and covert navigation is not an issue, I think that you are onto something.

      When I first heard about the competition, that was my first reaction, too. Why not just create a tank and plow through the terrain along the most direct route? A review of the rules showed that they had already taken into consideration this solution and created a rule against it. I can see their reasoning, though.
    • I liked the idea of a surplus hummer with retofittings. If a hummer can't get you where you need to be, then you have a problem, not your car.

      On that note, is there a chance for a unified software system? Could the schools try an open source AI system for input from monitors(varrying types, depending on the vehicle's equipment) and output into stearing and accel/deceleration?
    • AAah the American solution. Can't beat it by ingenuity? DESTROY IT!
      • How else did we get to be the remaining superpower?


        From this year's results, clearly the problem is too difficult to solve all at once at this time. So you simplify, simplify, simplify. Get a D-6 solution to work - lots of space & power for computers and you won't be tempted to go too fast. Then you make it more complex, and use the previous solution as the groundwork for something more complicated. Stepwise refinement.

  • Most of them will never work (Score:5, Informative)

    by Animats ( 122034 ) on Sunday June 06, 2004 @01:28AM (#9348636) Homepage
    With the possible exception of CMU, nobody had a system that could avoid a ditch or a pothole. Stereo vision won't do a good enough job on dirt for long range ditch/pothole detection. All the laser rangefinders except CMU's were fixed line scanners, so they couldn't possibly profile the ground ahead reliably from a bouncing vehicle.

    CMU's approach is a big hammer. They took a stock line-scanning laser rangefinder and put it in a huge 3-axis gimbal, which they then actively stabilize. That should be able to profile terrain, but it's a huge mechanical kludge. If you miss a spot because you hit a bump, you have a hole in your data. At that point you can either slow down and rescan, or plow ahead blindly. They may eventually complete the course with that rig, but no way is it a commercially viable technology.

    The next generation of sensor technology may be ready in time. There are at least three groups with usable sensors in the prototype stage. We're talking to two of them. But that's all I'm going to say for now.

    John Nagle / Team Overbot [overbot.com].

    (We're recruiting. See our jobs page. [jobs.html] No pay, some risk, a fraction of the prize, we cover all expenses. Silicon Valley only. We have our own shop in an industrial park in Redwood City. If you're local, come over and see the thing.)

    • Why not a combination of stereovision, range finding, and a digital horizon to enable real time mapping based off a visual system. Seems conceptually simple enough is there something in that picture I'm missing as it would seem fairly easy once properly calibrated to discard bad data based of changes in the visual system or abrupt unpredicted changes in the horizon. Then make determinations based off the risk of what data is left of whether or not to slow down and catch up on the data before proceeding.

      I
      • Why not a combination of stereovision, range finding, and a digital horizon to enable real time mapping based off a visual system?

        Stereo vision has two fundamental limitations. First, it doesn't work very well unless the scene has clean, sharp edges to match up. Second, the accuracy decreases rapidly with range, beause you're measuring a narrow triangle from angles at the base.

        The algorithms for stereo vision aren't all that forgiving. There are basically two flavors. One finds and matches "feature

        • They're getting better, but its still years away from usefulness. This past week I checked out some new work that used temporal data streaming to fill in whats between the discrete frames (much more like how human vision works). This allowed much more detail to be considered, with lower noise errors that plague stereo vision traditionally.

          However it still required structured light to work well, meaning outside the lab it wont work well.

          One problem that I see with stereo vision research at the moment is
        • I've thought about how using stereo from motion would work as well. I think that in order for this to work one would need to have a fairly stable mount for the camera. Then you'ld probably want to have some accelerometers in order to help in correlating the frames of successive images. I figure that for the grand challenge you'ld probably need 5 or 6 cameras (fairly low resolution 640x480) with various focal length lenses, short for looking near the vehicle, long for imaging a small region well ahead of t
        • I have to many student loans to pay back to begin anything like this at the moment I was just curious as to why people have had such trouble. I would assume a fixed focal point with a predictable parallax would work much better than detecting from the outside in. I've seen it go the other way and work very well, so why not reverse the process to determine spatial relationships within the confines of the resolution of the image it is fed. I'm sure using this type of algorithm with a high speed fpga could
    • (We're recruiting. See our jobs page. No pay, some risk, a fraction of the prize, we cover all expenses. Silicon Valley only. We have our own shop in an industrial park in Redwood City. If you're local, come over and see the thing.)
      I think you made a mistake in your URL, I think this is the URL I think you meant to post :P [overbot.com]

  • I'm not so sure (Score:2, Informative)

    by Einer2 ( 665985 )
    From what I know of the race course, these vehicles have to average 30 mph going cross-country through the desert. If it's anything like the terrain around the Tucson area, I'm not sure that I could average that without piling straight into a saguaro.
  • I think the major problem of the past challenge is that no one looked into the possibilities of fuzzy thinking. Like the ability to assign threat levels to various levels in the terrain and picking the lowest threat level as the appropriate path to the goal. This is a simple enough project and why nobody was able to make it work I don't know. Perhaps it is the fact the project was not as open as it could have been or people thought the competition would be tougher than it was.

    I think many lessons were l

    • Re:I think they will (Score:3, Informative)

      by jbrocklin ( 613326 )
      Actually, I've read most of the technical papers that the teams were required to submit, and many of them did use a "track and assign danger levels" as a way of finding a best path (most used this as a way of keeping the vehicle inside the boundaries of the course - assign the off-course sections with infinite danger and the vehicle will never go there).

      Overall, the majority of the problems that people were with unplanned problems, such as going up a hill and not switching down gears, stopping to check ter
  • As with RoboCup, I expect the gap between the first and third years to be huge. And to think our little QuickCam/Linux RC cars won robocup #1 [isi.edu].

    Anm
  • If they really want to create an autonomous robot, let's see them make one that they can't get to come back.
  • Forgive me if this has already been addressed (I am obviously not an engineer or anybody capable of building a robot), but why not use some sort of sonar type way of viewing things, like bats do?

Slashdot Top Deals

Two can Live as Cheaply as One for Half as Long. -- Howard Kandel

Close