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

 


Forgot your password?
Close
typodupeerror
×
Robotics Hardware

Tom's Looks at Two DARPA Grand Challengers 169

Posted by timothy from the thrum-thrum-thrum dept.
skeeball writes "As a follow-up to this article, Tom's Hardware has a behind the scenes article on two of the teams competing in the DARPA Grand Challenge 2005. "The Defense Advanced Research Projects Agency (DARPA) hosted the first Grand Challenge Project last year, offering a reward of $1 million. This year, the prize money has been doubled, making the competition all the more interesting.""
This discussion has been archived. No new comments can be posted.

Tom's Looks at Two DARPA Grand Challengers More

Tom's Looks at Two DARPA Grand Challengers

Comments Filter:

  • Big money in defence (Score:5, Interesting)

    by mfloy ( 899187 ) on Monday July 18, 2005 @09:43PM (#13100094) Homepage
    This just goes to show all the money that is being tossed at defence research. If you can even give the smallest example of how your research can be used for defense you are almost guarenteed to get grant money. I know many researchers who do just that just to get their projects funded.

    • Re:Big money in defence (Score:3, Funny)

      by Anonymous Coward
      Whoever would have thought the government likes to remove fences? This whole time I thought they were errecting them! Heh-heh, I said erect.
    • None of these developments will be used for true "defence". They won't be there to protect the average American citizen. But judging from the past several years, there is a very good chance that they will be used for offensive purposes. Perhaps against Iran or Syria.

      These days the defence industry isn't about defense. It is about creating offensive weapons used to instigate conflict in non-American, resource-rich areas.

      • I have actually talked to one of the handful of DARPA people who hatched this idea in the first place.

        Interestingly, the primary motivation for this is for cargo and supply-line applications.

        I am not saying that it couldn't be used for ground-based unmanned attack vehicles eventually, clearly it could. Eventually. But that kind of use would require a much smarter and more flexible maneuvering capability.

        If you think about the requirements for a supply truck, they are pretty simple. Get from point A to

    • Re:Big money in defence (Score:5, Insightful)

      by fjf33 ( 890896 ) on Monday July 18, 2005 @10:22PM (#13100319)
      And you think that 1 million dollar is a waste? That is probably the best money DARPA has spent. They are getting a LOT more than 1 million dollars worth of reaserch by doings this. The field was advanced more in these two years than ever before. I much rather they do this than give the money to some University so that a graduate student can waste it. Whenever there is a competition people get innovative. I think this is great. Besides DARPA's reason of being is to put money into things that no private enterprize would. Things that have no direct application in the next 10 years or so but that seed the field for the private industry to pick from there and make a project that they think they can make money in 2 to 3 years which is the maximum horizon for private industry.
      • I can remember back in the 80's, the AIM-54 Phoenix missile was derided for being $1 million a shot. The MIM-104 Patriot PAC-3's we're now deploying everywhere are about $2 million each. I think 2 or 3 missiles would be worth it, if we can spawn a generation of autonomous airplanes, cars, tanks, whatever. This is the Internet's ARPANET. These are the first steps, and it will demonstrate clearly what works and what doesn't. Then someday, rather than sending in a C-141 full of paratroops, we can send in

        • we can send in a planeload of small tracked vehicles to do the "dirty work" of urban warfare.

          ...and potentially lose the deterent and historically shared commonality that the cost of war is largely measured in lives lost for either side of a conflict.

          The capacity to wage war has rarely, if ever, been precisely equal. As a highly technological approach, the capacity to wage war in this manner will not be shared by all.

          If the time comes, I certainly would hope that the powers that be have also reached

          • We have had the atomic bomb for around what 70 years now. It has these capabilities. Given the ability to completly destroy your enemy seems to cause atleast some rationality to enter into the minds of the controllers of such weapons.

      • Re:Big money in defence (Score:4, Insightful)

        by mbius ( 890083 ) on Tuesday July 19, 2005 @04:52AM (#13101741) Journal
        I much rather they do this than give the money to some University so that a graduate student can waste it.

        Psst...Don't let on I told you this...(leans in close)...that's where scientists come from.
      • Afaik, no one's won the challenge yet.. so they haven't actually spent the money.
    • ...or a ring of dollar bills around the entire planet?

  • Article Link? (Score:3, Funny)

    by sH4RD ( 749216 ) on Monday July 18, 2005 @09:43PM (#13100095) Homepage
    Thanks for the article link! I love having it at my finger tips here on Slashdot!


  • "The Defense Advanced Research Projects Agency (DARPA)


    hosted the first Grand Challenge Project last year,


    offering a reward of $1 million.


    This year,


    the prize money has been doubled,


    making the competition all the more interesting."

  • Article Link (Score:5, Informative)

    by Kozz ( 7764 ) on Monday July 18, 2005 @09:44PM (#13100105)
    Too bad the submitter didn't Link the Article itself [tomshardware.com].

  • Article link (Score:4, Informative)

    by rdwald ( 831442 ) on Monday July 18, 2005 @09:45PM (#13100116)
    Right here. [tomshardware.com]

  • Semantics (Score:4, Insightful)

    by Savatte ( 111615 ) on Monday July 18, 2005 @09:48PM (#13100135) Homepage Journal
    This year, the prize money has been doubled, making the competition all the more interesting

    um, how does more prize money make the competition itself more interesting?
    • "let's make this interesting" is a common phrase in the english language meaning "let's increase the amount of money we are betting". You might also have heard "let's up the stakes" which is a phrase taken from Poker that means the same.

    • More prize money, more teams, more interesting

  • However... (Score:5, Insightful)

    by lightyear4 ( 852813 ) on Monday July 18, 2005 @09:52PM (#13100156)

    ...it would be a MUCH more interesting contest if the teams did better than the last time around. (the best team only got 7 miles [imagiverse.org] out of 175 total.)

    I wish the best of luck to all of those competing.
    • On the contrary, I think the fact that the best teams in the entire world only made it 7 miles is the interesting thing. And a little humbling.

    • there is a reason it is called the "grand challenge" instead of the "mediocre challenge"

      this thing isn't meant to be easy! that the best team only made it 7 miles shows how difficult it is. that the best team only made 7 miles shows we have a lot to learn.
  • Comment removed based on user account deletion

  • The Line up is not complete! (Score:4, Informative)

    by locokamil ( 850008 ) on Monday July 18, 2005 @09:59PM (#13100192) Homepage
    Just so all you geeks out there know, the final lineup for the DARPA GC has not been decided yet.

    Several teams with extremely competent designs will be site tested by DARPA officials during the week of August 15th.

    Keep your eyes on the Princeton University team (disclaimer: I'm heavily involved in developing software and lasers for them). We barely missed the cut in April, but we're gearing up for the second round of qualification tests in August. We've taken an approach very different from the other teams (we love to hate on CMU and Stanford for their bloated budgets and hardware), insofar that we've refused to let our budget rise over $40000. Furthermore, our work is done ENTIRELY by a team of six undergraduates, three of whom are freshmen (I'm the only senior on the team).

    Is this a shameless plug for the Princeton team? Hell yeah. But I just felt that it should be known that there are people in this competition who are trying to THINK their way out of the maze instead of BUYING their way out of it.
    • Why would I keep my eyes on them? Like you said, you guys missed the cut in April. What's to say you won't miss it again in August? And like you also mentioned, it is being done by people without much education nor experience. The best of luck to you, my friend, but please don't go into this competition with too much of an ego. It may be hurting once you get your ass kicked by the big boys.

      • I forgot to mention that we went into the April test with a little bit more than one month of development time...

        Yesterday, we had an 12 hour stress test where we covered all of last year's course, and a little bi more-- without any outside assistance. All we have to do now is work on speeding the car up a bit... but we've left enough slack in our systems to allow for that.

        I generally put my money where my mouth is-- this is no exception.
        • That is very interesting. Can you describe your setup a bit more? Since you worked in the software portion of it, could you please elaborate? What sort of computing hardware are you using? Did you choose to go with a traditional embedded OS, or have you written one from scratch? What language is the software itself written in? What are some of its notable capabilities?

          • Off the shelf hardware: we use one P4 3.2Ghz for general control, and an Athlon64 3800+ for vision processing. Software wise, it's a bit of a hodgepodge-- we fully recognize the need to clean it up. The control comp is using Windows Server 2003, and most of it is written in C#, simply because it helps us to develop interfaces with our control hardware quickly. The vision computer runs gentoo Linux, 2.6.12 kernel. All the vision code is written in C-- simply because that's what most of us are most comforta

          • Re:The Line up is not complete! (Score:5, Interesting)

            by locokamil ( 850008 ) on Monday July 18, 2005 @10:52PM (#13100457) Homepage
            Off the shelf hardware: we use one P4 3.2Ghz for general control, and an Athlon64 3800+ for vision processing.

            Software wise, it's a bit of a hodgepodge-- we fully recognize the need to clean it up. The control comp is using Windows Server 2003, and most of it is written in C#, simply because it helps us to develop interfaces with our control hardware quickly.

            The vision computer runs gentoo Linux, 2.6.12 kernel. All the vision code is written in C-- simply because that's what most of us are most comfortable with. Whether or not we port our C code to C#, or back port our C# code to C remains to be seen.

            Notable features? We use three primary sensors: GPS, Vision (stereo and single lens cameras) and LIDAR. We take immense pride in the fact that our primary lane detection camera is a $100 webcam operating at 640x480 resolution. Our design is robust enough that the car can continue on its merry way even if two of the three primary sensors are taken out of action.

            We absolutely refused to shell out 10K (250K in some cases) for a commerical LIDAR solution. We basically built, stabilized and hardened our own LIDAR. The judges are out on whether or not its better than commercially available solutions, but it certainly equals any (reasonably priced) solution out there-- and my buddy and I built it for only 2.5K.

            Algorithm-wise, we're taking the mountaineer option instead of the God option. That means that we're using genetic optimization techniques in conjunction with kalman filters to 'grow' our way around obstacles and stay within bounds instead of detecting every single obstacle in an x km radius, plotting it and calculating splines/best possible courses through the minefield. The three inexperienced freshmen came up with this solution... and in most of our benchmarks, it doesn't take more than 45% of our control CPU's power to use this algorithm.

            We're not trying for overkill. Our objective when we started the project was to find out what was *just* enough to get past the course. This means that we've been able to keep our costs under control.

            I'd direct you to our website... but we've not had the time to put one up. Eventually, we'll get around to it-- but right now, the car has taken priority.
      • I started as a Stanford CS (AI concentration) grad student in the fall and found the following in the list of available courses:

        CS294 DARPA Grand Challenge
        Goal is to develop an entry into the DARPA Grand Challenge to build a ground vehicle that can drive autonomously from Los Angeles to Las Vegas. $2 million aware to winner; success requires major advances in core problems in artificial intelligence including robotic perception and high-speed control. Focus is on team-based design, development, implement
    • I suppose they have to prove that the vehicle isn't being guided/helped remotely? That must be a non-trivial task...

      By the way, I hope no camels die. (kidding, I know there are no camels on the US - but there are probably many other animals on that desert, I guess :P)

  • That's so Tom's Hardware (Score:5, Informative)

    by Animats ( 122034 ) on Monday July 18, 2005 @10:08PM (#13100240) Homepage
    That's so Tom's Hardware. "7 Pentium M CPUs!", and no word about the algorithms. They could have at least said more about the sensors. Actually, everybody's sensors suck. The radars can't profile terrain, the LIDAR units are only line scanners, the stereo vision systems have trouble locking up on dirt, and the vision systems are a long way from being intelligent. True 3D LIDAR is coming, but not this year. The Grand Challenge rules prohibit the use of the best available 3D LIDAR system, because it was developed with Government funding and wasn't available by August of last year.

    So we have a line-scanning LIDAR on a tilt head, like CMU, which is an adequate but bulky solution..

    We have two industrial Pentium 4 machines running QNX [overbot.com], on our Grand Challenge entry, along with five Galil programmable motor controllers. We have room for 3 CPUs, but the compute load fit on two of them, so we took the third one out.

    Technically, QNX was an excellent choice, but because few people know it and many don't want to learn it, using it has made recruiting difficult.

    • Why is the vision processing so poor? I remember back in 1997 reading a paper on a system that could read American Sign Language in realtime using an Indigo Graphics Indy 2 workstation with builtin camera. Today's processing power is many times greater and better imaging can be accomplished by modern CCD's, so what is the fundamental problem? Are there just no algorithms capable of pulling the fundamental data like contour lines out of the image in real time, or can they do the basic but just get messed up

      • Re:That's so Tom's Hardware (Score:5, Informative)

        by Animats ( 122034 ) on Monday July 18, 2005 @10:47PM (#13100437) Homepage
        Why is the vision processing so poor?

        Because, despite decades of work, vision processing of unstructured scenes still sucks.

        There are things that work in computer vision. You can do stereo, if the image has strong edges in it. You can pick out big moving objects. You can find the horizon. You can work out your own positional movements from video. You can find faces, align, and recognize them, sort of. You can find known objects in any orientation (which is very useful in industrial systems.) You can follow roads.

        Beyond that, not much works.

        • Are there toolkits available for this? Like maybe something for SciLab I'd love to let a linux bot roam around my yard if it could recognize the boundaries.

        • The problem is, I think, is that people don't understand how the human brain processes these sorts of images, which is why most people are having limited success doing image analysis on computers like this.
          • The problem is, I think, is that people don't understand how the human brain processes these sorts of images, which is why most people are having limited success doing image analysis on computers like this.

            Not entirely. I agree that part of the problem is that not only do we not understand how the image processing capability of the human brain works. Some of the rest of the problem is that we also don't know how to reproduce the years of specialist training surveillance experts spend to be able to detec
    • That's so Tom's Hardware. "7 Pentium M CPUs!", and no word about the algorithms.

      Yeah, I wonder why Tom's Hardware didn't have much to say about the software and instead focused on the hardware that makes these beasts work... Hmmmm.

    • While it's true that the article hardly touches on the interesting aspects of these teams' design choices, I did find the closing somewhat interesting- the contrast that one team concentrated all their money/effort on the sensors and control of a normal car, while the other team concentrated their money/effort on a vehicle with bad-ass off road capability and didn't worry as much about the sensors and driving systems.

      Who would I put my money on? Well, from all the pictures I've seen of the course, I'd bet

      • on the sensors and control of a normal car

        Actually, no. Stanford's VW Touareg was provided by VW with the ability to be driveable via a serial port. This is apparently a mod they use internally for testing.

  • Yah, Tom's Hardware does it again. I guess we'll have to wait for the actual race to see whether or not the big companies will steal the show from the university researchers. Personally I think the teams that have done this on a budget will perform better than the companies that are pouring millions into it. Just because they have to come up with more intelligent solutions.
  • But seriously, come on, we all know the DARPA challange is just a warmup for next years buggy race.

    To bad PiKA will still beat the robotics department, an unmanned buggy just cant compete againt frat boys and 5 foot tall female drivers.

    http://www.andrew.cmu.edu/user/buggy/ [cmu.edu]

  • Those look nice, but (Score:1, Interesting)

    by Anonymous Coward
    My money's on the TerraMax vehicle from Oshkosh Truck.

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

  • How did they manage to write (Score:4, Informative)

    by btempleton ( 149110 ) on Monday July 18, 2005 @10:30PM (#13100365) Homepage
    A long article, full of photos and pointless details, and yet after a dozen pages tell me nothing?

    Amazing.

  • Seven Pentium-M CPUs (Score:3, Funny)

    by Humorously_Inept ( 777630 ) on Monday July 18, 2005 @10:33PM (#13100378) Homepage
    /* just kidding

    Sure, Tom. Give Intel product all the coverage in the world, but what about AMD?

    "AMD-powered DARPA Grand Challenge competitor overheats and explodes. Kills millions and incinerates $2 million prize. Intel steps up and offers 2 million Pentium MMX Bunny Man dolls ca 1997 to winning team."

    just kidding */
  • What ever happend to Oshkosh Truck and there MTVR? I liked the idea of making an autonomous 6x6 heavy truck. It would prove an extream help in a combat zone as supply convoys can be robotic removing drivers from harms way. Cargo handling can be done once the convoy reaches it destination by humans. Imagine for a minute that you are a solder driving a wheeled tanker hauling 5000 gallons of diesel when an RPG strikes the tank. You're either dead or badly burned. If it were autonomous well uncle sam lost mon
    • "Imagine for a minute that you are a solder driving a wheeled tanker hauling 5000 gallons of diesel when an RPG strikes the tank. You're either dead or badly burned."

      Would that solder be hot or unplugged? Either way, solder or soldier, either will be badly burned.

      One thing they can try with the truck, since DARPA is in the giving mood, is to divided the tanker into modules that have a safety factor calculated to eject the segment that is just about to be hit by the RPG, this way, the contain can be e
    • Somebody linked it just above. Terramax [terramax.com]

      After seeing photos of the hardware, and learning how loaded with tech these things are, I have a hard time imagining that the prize will not be won this year.

  • should there be a "should"? (Score:3, Interesting)

    by H310iSe ( 249662 ) on Monday July 18, 2005 @10:45PM (#13100431)
    "While there should be no misconception that the ultimate goal of DARPA is to turn autonomous vehicles into killing machines"

    Feel I should at least mention the idea that doing really, really cool development for DARPA is the kind of thing you need to ask ... should I?

    Not sure if this is possible w/o yafw (yet another flame war) but someone has to say it ... these people could be doing the exact same research without involving the US military... couldn't they? And, um, I suppose it's possible they could actually not give that research to the US military after they'd perfected it...

    OK, I can see that one way or another if you build it the US military will get it, but it doesn't have to be soooooo, like, readily handed over. Could at least make them ask or something...

  • RIP SAW (Score:2, Interesting)

    by ThisOne ( 152719 )
    My buddies from prep school are in this and if you want to see some whiked pissah video clips (wmv), check this out:

    Fully Remote Control:
    http://howeandhowe.com/videos/remote.wmv [howeandhowe.com]

    Adrenaline Junky:
    http://howeandhowe.com/videos/Movie_0001.wmv [howeandhowe.com]

    It never ceases to amaze me what New Englanders can do over an 8 month long wintah!

  • Some Errors (Score:3, Informative)

    by kf6auf ( 719514 ) on Monday July 18, 2005 @11:09PM (#13100532)

    A couple of corrections:
    Two Teams Compete for Best Robot Car in DARPA Challenge
    I would just like to point out that the headline is off by over an order of magnitude! We here at Caltech and many other people at many other schools are also competing to have the best robot car too!

    The vehicles are given no more than 10 hours to complete the 176-mile route, which will be kept secret until the beginning of the race.
    The map is given to each of the teams several (3?) hours prior to the start of the race. One result of this subtle difference is that teams can program a general path into the vehicle and have it deviate from it only as necessary instead of just popping the DVD into the computer and having the computer do everything.

    Something that people should keep in mind is that many schools are using the program as a learning experience and solely out to win the competition, but provide their students with not only a limited budget, but make them do things themselves even when it might be cheaper and undoubtedly easier to simply buy premade parts elsewhere. The use to the military will not be the machines that are built with all sorts of fancy equipment and sensors that Tom's Hardware liked to talk about, but the algorithms and techniques that are used to guide the vehicles.

    Scott

    • The map is given to each of the teams several (3?) hours prior to the start of the race. One result of this subtle difference is that teams can program a general path into the vehicle and have it deviate from it only as necessary instead of just popping the DVD into the computer and having the computer do everything.

      CMU tried that last year. They'd obtained custom aerial and LIDAR imagery of the route, and had a semitrailer full of people at workstations manually programming the route in the two hours

  • Tommy, another project for this competition, was featured at the lastest JavaONE in San Francisco in July. You can find the link to the group here [perronerobotics.com].

    In addition to some really interesting technology, they've got a great video demonstrating the vehicle in action that drew whoops and applause in their talk at the conference.

    -- Scott

  • So, in the future... (Score:2, Interesting)

    by Jambon ( 880922 )
    ...who will be responsible when someone gets hit by an autonomous vehicle?

  • Probably futile.. (Score:2, Insightful)

    by dtietze ( 708094 )
    .... but would it really be too much of an effort to include half a sentence (roughly) in the write-up telling us what the DARPA Grand Challenge actually IS ABOUT?

    I know I could RTFA, but why should I be forced to, just to find out wether I would actually be interested?

    This seems to be a recurring pattern on Slashdot posts. Which doesn't make it any better, it just makes it consistent.

    Dan.

  • ...that this was written up on Tom's *Software* ? The hardware side's pretty interesting, but the software's where this baby's gonna be won and lost. It'd be good to see a high level overview of the algorithms involved.

Slashdot Top Deals

One man's constant is another man's variable. -- A.J. Perlis

Close