Forgot your password?
typodupeerror
Science Technology

CMU First To Qualify For DARPA Grand Challenge 210

Posted by timothy
from the pole-position dept.
Anonymous Coward writes "As of 18:00 March 9th, Carnegie Mellon's Red Team is the only entry to successfully complete DARPA's Grand Challenge Qualification Inspection and Demonstration (QID) before the main event on March 13th. The NY Times has this article detailing this first step towards winning the Grand Challenge."
This discussion has been archived. No new comments can be posted.

CMU First To Qualify For DARPA Grand Challenge

Comments Filter:
  • Google News Version (Score:4, Informative)

    by byolinux (535260) on Wednesday March 10, 2004 @09:57AM (#8520422) Journal
    No reg needed! [nytimes.com]
  • My University Too (Score:5, Informative)

    by rmohr02 (208447) * <mohr.42@NospAM.osu.edu> on Wednesday March 10, 2004 @09:57AM (#8520424)
    One of the other competitors [osu.edu] is from my university. Looking at the relative sizes, I hope the hummer in the article doesn't get in TerraMax's way.
    • by MalaclypseTheYounger (726934) on Wednesday March 10, 2004 @09:59AM (#8520442) Journal
      Immediately springing to mind is the scene from 'Ocean's Eleven' when the Monster truck is racing the R/C mini-monster truck, and it runs it over.

      This is the Department of Defense, after all, so maybe they will allow 'extra programming' to be done to find competitors (foes?) and destroy them?

      Turn this whole thing into a huge BattleBots contest instead of a Cannonball Run contest .. I'd pay to see that...

      • Immediately springing to mind is the scene from 'Ocean's Eleven' when the Monster truck is racing the R/C mini-monster truck, and it runs it over.

        Have some respect, please. That scene is from the new, and not as good version of Ocean's 11, not the original.
    • picture comparison (Score:4, Interesting)

      by morcheeba (260908) * on Wednesday March 10, 2004 @10:41AM (#8520747) Journal
      Here's a size comparison [oshkoshtruck.com] from the Oshkosk website... their truck is 9 feet tall, a hummer is 6 feet.
    • Nice photo of the vehicle. But if you know Umit, tell him to get his photo retaken! It's difficult enough to do a good shot in a striped shirt, but those are wrinkles!

      Seriously, I'm a photographer- tell him to get a new press head shot.

      Pretty slick design tho. I somehow think this is going turn out to be a contest of overdesigned rather than 'clever'....
  • The Homer? (Score:2, Funny)

    by pixelbend (628541)
    Is it just me or does the Sandstorm bear a striking resemblence to "The Homer" [culttvman.com]?

  • by normal_guy (676813) on Wednesday March 10, 2004 @09:58AM (#8520430)
    I can't be the only one who questions motives when the $1M prize is being sought after by a team with more than $2M already invested. What is the eventual payoff?
    • $4 and a dinner at Wendy's!
    • by Anonymous Coward
      the educational experience of making such a machine? :p
    • by sczimme (603413) on Wednesday March 10, 2004 @10:03AM (#8520469)

      The real prizes:

      the knowledge gained throughout the project

      getting one's name published for taking an active role in the project (which can lead to further opportunities)

      the overall experience, i.e. 'Hey, I did that"

      The pursuit of intellectual challenge is not about money...

    • by drspock (87299)
      The real payoff, as the Red Team and everybody else knows, is a future DoD contract, for many millions, or billions, of dollars.
    • by fuctape (618618)

      Fame and name recognition. In the year 2050, you'll hear, "On the Chinese front, a Sandstorm batallion was attacked. There were, of course, no casualties, thanks to the autonomous technology pioneered in 2004."


      You've got admit that it'd be amazing to be credited with an 'historical' level invention.

      • This is exactly the goal. I was at C-MU in the late 70's when Lynn Conway came and spoke on behalf of the Pentagon about the autonomous vehicle program. Basically, Berserker tanks capable of making independent judgements about what to kill. Very scary stuff, and the AI technology has not advanced much since.
    • by Ethon (759020) on Wednesday March 10, 2004 @10:13AM (#8520533) Homepage
      As stated in one of the replys to your post, the DoD will probably be offering a long term contract to manufacture similar vehicles for actual combat/whatever use. The DoD has already done this with the new-gen X planes, as seen on PBS' NOVA. [pbs.org] The DoD's JSF competition will probably end up paying the winner (Lockheed) some $1T in total contractual monies.
    • Actually, it's more like a 4:1 (cost:prize) ratio.
    • by Ralph Wiggam (22354) on Wednesday March 10, 2004 @11:39AM (#8521302) Homepage
      I've read a few articles about the Grand Challenge and they all seem to focus on CMU, the favorite. From what I understood, pretty much all of that $2M-$3.5M cost figure came in the form of free stuff from Intel, Boeing, and many others. It's not like the grad students are writing $150,000 personal checks to buy parts.

      The students probably can't pocket any prize cash anyway because of ethics rules. If they win, the students will get a rocking party and even more top notch equipment in their labs.

      It's not a race to prove you're better than the other teams and get prize money. It's a race to advance the state of a specific technology. Do you think people are going to get rich winning the X-prize?

      -B
    • From articles I've read (unfortunately I can't recall where) the whole DARPA event was used to "scare" one of their existing research partnerships (CMU) into getting their @$$ in gear and producing an automated vehicle - which apparently CMU was lagging on. The event was to show that DARPA could get great research from other sources if CMU didn't shape up.

      The result is that CMU stopped dragging their feet, which accomplishes the main goal of DARPA $1 million challenge.
  • Mars Rovers (Score:2, Interesting)

    by BenBenBen (249969)
    Just out of curiosity, how well would the rovers' "route picking" routines cope with this challenge?

    I read that the operator says "go from here to here" and the onboard 'AI' chooses the best route in a 3d visualisation - is this software open-source, and could it be used in this challenge? I can't see any major differences, other than the relative lack of parked cars on Mars (2 pathfinders and a beagle, iirc)

    Should DARPA have emailed NASA before starting this? ;)
    • Re:Mars Rovers (Score:2, Interesting)

      by genneth (649285)
      Pretty well, except for the speed thing, and the distance covered. From what they say, an average speed of 25 miles per hour will be needed to even complete the course in time. The rovers can presumably plod along and if it gets stuck it stops and asks for human intervention. The rules of the competition designate that no communication is allowed. From a piece that I read somewhere like New Scientist, it seems that with 4 Itaniums and 4 Xeons they're still not computing obstacle avoidance fast enough. For t
      • 200 mile course, at 10 hours = 20 MPH minimum speed to finish. Obstacles, of course, will slow down the vehicles, so the vehicle must be able to go much faster than this on 'clear' road to be competitive. The issue there is safetly - can an autonomous vehicle going 50 MPH stop in time when it detects another vehicle or an obstacle out to the maximum range of its sensors (I think a couple hundred meters)?
    • Re:Mars Rovers (Score:3, Informative)

      by MindStalker (22827)
      Actually it DARPA specifically required that no government agency help allowed. (though universities are quasi government, but you now..) Anyways I heard that the university that developed software that went on the mars rover also has a different team that worked on this project, but wasn't allowed to use the software. Though it probably wouldn't have worked as the rover goes real slow and spends a lot of time analysising the environment to get the safest path. This project will require real time calculatio
    • Just out of curiosity, how well would the rovers' "route picking" routines cope with this challenge?

      Could they complete the course? Possibly.

      Could they complete the challenge? No.

      The Mars rovers have a top speed of 2 in/s, or 0.11 mph (5 cm/s or 0.18 kph for the more enlightened). This would certainly never complete a 200 mile course in 10 hours.

      The Rovers' visual system is geared to their speed too. The cameras are not running continuously -- the rover stops, takes a picture, determines hazards, move
    • Re:Mars Rovers (Score:3, Insightful)

      by citanon (579906)
      Caltech manages JPL, the NASA lab that developed the rovers and their associated software.

      Originally, the Caltec team was using rover software. However, when DARPA changed contest rules a couple months ago, it went back on its earlier ruling and said that Caltech was no longer allowed to use the rover software because that software was not commercially available.

      This led to Caltech redoing much of the work on their vision software. They are now using the modified version of a commercial vision package.
  • by theguywhosaid (751709) on Wednesday March 10, 2004 @10:06AM (#8520489) Homepage
    they divided your time by the cost of your machine.

    its impressive when you build a mega$ robot, but a minimal robot that manages to finish is way cooler
  • by Ethon (759020)
    TAIWWP :( Does anyone know of anywhere hosting pictures of these unmanned robot vehicles?
  • by gravityZ (210748) on Wednesday March 10, 2004 @10:11AM (#8520523)
    ... doesn't this basically lead directly to the US military dropping off Robo-Tanks in foreign countries as they please? We know that a steady diet of wars figure heavily in the plan [newamericancentury.org] for the forseeable future. The Robo-Tank cuts down on friendly casualties, thus making conflicts more palatable to the public.

    Now I find this as cool as anyone else, from a technological standpoint. And it definitely has civilian applicability. But let's face it, this contest isn't about finding cheaper ways to haul cargo or reach remote locations.
    • But let's face it, this contest isn't about finding cheaper ways to haul cargo or reach remote locations.

      Sure it is! Those Robo-Tanks have to be transported and positioned on the enemy line, courtesy of the Robo-AssaultLander. And they can't refuel and rearm themselves now, can they? Robo-SupplyLine to the rescue!

      GTRacer
      - Still cooler than an Osprey

    • by Belisarivs (526071) on Wednesday March 10, 2004 @10:50AM (#8520843)
      But let's face it, this contest isn't about finding cheaper ways to haul cargo or reach remote locations.

      Sure it is. Logistics are a *huge* problem for the military, especially one that moves as fast as America's. Remember in Gulf War II that some of the most public incidents of American losses involved supply convoys, not front-line forces.

      With this sort of technology, supply-lines become more like conveyor belts than masses of convoys. They elminate the need to teams of humans to transport fuel, water, ammunition, etc. to the front lines. This increases the pool of human resources available to the military for other jobs, while eliminating the worry of casualities inflicted by enemy interdiction missions.

      Sure, automatic tanks will logically be a followup, but I think the military's mid-term goal is automating the logistics.

    • by demachina (71715) on Wednesday March 10, 2004 @11:03AM (#8520962)
      Based on recent experience I would take the military's word for once, though only once. If you look at Iraq most of the casualties weren't in combat. Soldiers in fast moving, heavily armored, M1 tanks really weren't that vulnerable.

      Its probably going to be a real long time before you trust a robotic tank to discriminate friend or foe and to decide when and when not to start lobbing shells. Combat really should have a person in the loop who can react quickly to a complex and changing situation, one that often requires nuance. I wager an RPV tank is the only thing you may see anytime soon.

      But if you look at Iraq the place where the Army is VERY vulnerable is convoying supplies from one place to another since they are sitting ducks for improvised explosive devices and ambushes. I could see robotic transports as priceless for this if they can cope with a predefined route, not run anything over and deal with obstructions.

      Supply lines have always been the achilles heel of occupying armies. Indications are the U.S. military doesn't really need much help in the conflict phase, but it does need a lot of help to minimize the casualties and manpower needed to occupy its colonial empire.
      • I should add robotic vehicles would also be very useful for scout vehicles that are designed to make first contact with a concealed army, find mine fields and generally do a lot of dangerous scouting work which doesn't require discharging weapons. Scout vehicles would just beam back intelligence, draw fire, and be cheap enough to be expendible.
      • by mykepredko (40154) on Wednesday March 10, 2004 @12:32PM (#8521808) Homepage
        You might be interested in knowing that, according to AW&ST, the army/air force in Iraq has found in many cases that it is more efficient to transport cargo within Iraq via C-5, instead of 12 large trucks.

        The reason was because the loading and unloading areas could be secured but not the highways in between.

        Check out the February 23rd Issue.

        myke
  • Ack! (Score:5, Funny)

    by ferralis (736358) on Wednesday March 10, 2004 @10:12AM (#8520528) Homepage Journal
    I would sure hate to be a geologist, prospector, or hermit in the desert that day.

    Gelogist: [mumbling to himself] Finally! Proof that the formation of this arroyo was caused by--

    [Geologist is flattened by an army of driverless cars driving at upwards of 60 mph, one of which detects the collision too late and actually backs up, running over him again, as failing avoidance mechanisms kick in]

    • Re:Ack! (Score:5, Funny)

      by Chalybeous (728116) <chalybeous@yaDALIhoo.co.uk minus painter> on Wednesday March 10, 2004 @10:17AM (#8520556) Homepage Journal
      I have a funny feeling some film studies geek is going to follow the action with a DV camera, and edit the raw footage into a movie using the soundtrack from "Cannonball Run"...

      I, for one, welcome our autonomous vehicle overlords - even if they do sound like Burt Reynolds.
    • Like that's any more dangerous than an adrenaline-filled division of 18-year-old armored vehicle drivers coming at you.

      Disclaimer: I am a veteran and a supporter of all who serve or have served in our armed forces. But it's a simple truth that the training for the judgement calls that the military has to make at a moment's notice (and cops also) is just as tricky a thing as the technology required to identify obstacles or to determine the difference between friends, foes and noncombatants.

      RP
  • by dave420 (699308) on Wednesday March 10, 2004 @10:15AM (#8520545)
    I know it's much more complicated than this, but they're giving it the knowledge to navigate a route, not the intelligence to come up with its own route. Surely that's missing the whole point of this competition? I read in the last /. article that they're using a loophole in the rules to get so far.

    Seeing as DARPA wants to turn this technology into a military robotic transport, I don't know how valuable it's going to be if it has to be pre-programmed with terabytes of data just to move. What about if they invade somewhere they don't have good maps of? Somewhere with a dynamic landscape (desert, rocks etc)?

    I'm all for innovation, but exploiting poorly-worded rules just to win for winning's sake is an empty victory at best.

    • They are going to be traveling through a dynamic landscape, they aren't just driving over sand dunes or across open desert. They are given waypoints, but the waypoints are each a mile or two apart which leaves plenty of room for pathfinding in the middle.

      If the military invades with these, they aren't just going to tell it to go somewhere and kill someone, they are going to give the machines very specific directions. If they dont have a map...they could probably get one in a few hours anyway, so I don't

      • DARPA are looking to create vehicles that drive themselves. Vehicles that drive next to manned vehicles, and act the same. These vehicles have to react like people - if a bomb drops in the road ahead, it has to know to stop and drive round. It has to figure out the best route available. If it's dumbly programmed with waypoints, one crater and it's toast.

        This robot sounds like it fulfils the rules, not the competition. There's a huge difference.

      • If the military invades with these, they aren't just going to tell it to go somewhere and kill someone

        Does anyone else have the urge to start chanting

        MEGA-WEAPON
        MEGA-WEAPON
        MEGA-WEAPON

        Or is it just me???
    • by Tom7 (102298) on Wednesday March 10, 2004 @10:34AM (#8520689) Homepage Journal
      From what I understand, the "loophole" allows them to use 1m satellite imagery of the route and, in two hours, plan something for the robot to follow. The robot still has to see its way when it's going, to avoid ditches and rocks and other things--it needs to do "local" route planning at 35mph. Even if the route were totally pre-programmed, the problem of following that route would still be pretty hard over hundreds of miles. You can't just do "dead reckoning."

      What about if they invade somewhere they don't have good maps of? Somewhere with a dynamic landscape (desert, rocks etc)?

      This is in the desert, and they're doing it with only satellite imagery.

      There's a huge amount of mechanical and software engineering in this thing. I think that someone must have exaggerated this "loophole" to you, because it is far from making the project easy (as far as I know, it doesn't help them in the quals at all). The robot is impressive!

      • So they have hundreds of terabytes of information in the back just for shits and giggles? Why isn't anyone else taking that path?

        It doesn't have to think about navigating - they're telling it how to do that. It has to only deal with getting round obstacles in its path. They're removing 1/2 of the problem so they can put their effort behind the other half, which the other teams aren't doing. It just smacks of unfairness, that's all.

    • Red Team is using "the best map in the world" to guide it. They have used topo maps, aerial photography, and a bunch of undergrads to painstakingly map out the terrain of the possible courses.

      All competitors are given the actual route as a series of GPS waypoints a few hours prior to the race. Red Team is going to send those waypoints back to CMU, have the big iron there figure out the best course based on all the map data, and then download that course to the robot prior to the start. In a way this is cool, but it seems like they are using a loophole. A much more interesting problem would be to navigate a course that you know nothing about other than the waypoints.

      The other teams are using techniques that require more onboard intelligence and route finding. The most interesting vehicle is from Cal. They have a motorcycle. Even though I went to Stanford I am rooting for the Cal motorcycle to do well since they have the most unique vehicle. Hopefully the team of Stanford alums (already dropped out) can come back next year and beat them.

      • You are right that it would be much cooler if the robot could find its way without the map, but for the purposes of the military it is plenty good that it reads a map and only does obstacle avoidance in real time. This is the way that a tomahawk cruse missile works and it works pretty well. One of the first things that the military does in a conflict is update the maps and reconnaissance for the area.

        This also would great as a civilian technology. If I could drive my car to the interstate and hit an autopi
      • The point of the Darpa project is to advance technology for driverless military vehicles, primarily for convoy work. To my mind, creating a computer system to quickly plan out routes based on intelligence is an important part of a practical solution.

        Not only does it more accurately reflect the technology's intended use-case in the military field (convoy operators would lilely be given a general route a couple hours before a mission, instead of simply told, 'get it to this point and leave right now') but it
        • Maybe I should clarify. From what I have read I think that the Red Team will do better than any other group. They have probably put more money and time into their effort than any other team (even though they started later than some) and they deserve to do well.

          That said, in a dynamic enviroment you won't always have the luxury of "the best map in the world". While this works well for convoys there are other situations where the ability to deal with a changed landscape (due to war or natural disaster) o

    • I'm not sure that it is a loophole. It's not as challenging as doing it the other way, but let's face it, this is being done for the military, and you're extremely naive to think that the military doesn't have precise topography maps of the entire world, or that they can't obtain such maps in short order. Remember, a key component to cruise missile technology is topography. Remember in GWI, the cruise missiles took hours and hours to program before launch. Now, they can be reprogrammed in minutes.

      So,
      • you're extremely naive to think that the military doesn't have precise topography maps of the entire world

        My thoughts exactly. I'm also figuring that OP and others probably haven't seen the training that our fighter pilots go through when preparing for missions. Radar is used to build precise 3D models of the target area. The pilots are able to fly their exact missions in simulators dozens of times before actually heading out for the real thing. I've seen many pilots saying that they can't believe how lif
    • by fizban (58094)
      This is no different from you getting in your car, looking at a map to find out the best route to get from point A to point B and memorizing what turns you have to take at certain key points. But the map doesn't show every little bend in the road, every little obstacle, elevation changes, etc. You have to do all that while you're driving the roads. The autonomous vehicle has to do the same things. You don't think that's impressive?

      The point of the competition is not to come up with a route. It's to simulat
    • No imagery I know of can "see" all things large enough to stop a vehicle, such as meter-size rocks and bushes. The vehicle will still have to execute local intelligence (or brute force).
      Furthermore, you assume that all military robots would be programmed with similar maps, so this is not an advantage.
    • I'm all for innovation, but exploiting poorly-worded rules just to win for winning's sake is an empty victory at best.

      You don't play AD&D 3rd Edition, do you?

  • QID (Score:4, Funny)

    by j0hnfr0g (652153) on Wednesday March 10, 2004 @10:23AM (#8520606)
    The Qualification Inspection and Demonstration was rumored to be the state's Driver's License Test.

    The vehicles had been fretting about the dreaded parallel parking portion of the test.
  • Bah! (Score:2, Funny)

    by JustinXB (756624)
    Nice to know 3 million dollars buys you a roll over and placement. What the hell did they do to the HUMVEE that made it roll over? I know HUMVEEs and HUMMERS, they don't roll easily.
    • Re:Bah! (Score:4, Informative)

      by def (87618) on Wednesday March 10, 2004 @10:37AM (#8520721) Homepage
      Basicly, it took a turn too fast.

      a picture [redteamracing.org].

      this page [redteamracing.org] is the running log put out by the group, and includes a description of the accident.
      • Best quote from the log page:

        Sandstorm had been driving with new code for reducing speed in the corners.

        /me makes Jon Stewart "Duh!" face :)
    • Apparently you don't know them as well as you think. A friend of mine rolled one in the national guard by going crossways on an embankment that a less durable but more entertaining 4WD vehicle (like a really pissed off CJ-7) would have handled ok. It was only on its side, though, he was lucky.
  • by PieEye (667629) * on Wednesday March 10, 2004 @10:38AM (#8520726)
    Popular Science has a great article in the March 2004 edition (online here at PopSci.com [popsci.com]) called "Clash of the Headless Humvees".

    Weird title, seeing how they showcase the CMU entry, a high-school entry running in an Acura (donated by a parent who works for Honda) and a single-member "team" trying to do a motorcycle entry.

  • I feel kinda priveleged to be part of this. DARPA is working with SCORE International Off-Road Racing (http://www.score-international.com) to do the "checkpoints" and road crossings for this event, of which I am a part of.

    Basically it means sitting around all day waiting for these things to show up, but it will be fun nonetheless.

    I have a feeling that this event will not have a finisher, but from what I have heard DARPA plans on carrying out this challenge for about five years anyway.
  • One of my friends works with them (I'm a student at cmu), and recently he told me that they flipped the thing and crushed a bunch of shit. Lots of the roof-mounted equipment had to be replaced. Apparently it took a turn too fast. I'm glad they were able to have it ready, and a bit surprised they were the first. They certainly seem to be striving to do their best. Anyway, knowing the red team's capabilities, we won't see that problem again. Here's to hoping and their success.
  • I'm somewhat surprised that so many young people would work on a project that will help our military develop unmanned hunter-killer vehicles. Isn't this why DARPA's funding this project? I'm not against the project, just curious if there are any conscience issues involved here.
  • with this is simply how cheap the US military is getting away with this. Instead of setting forth a proposal, taking bids, working in tandem with one of the big development houses, they offer up a rediculously small prize. If they had gone through someone like Lockheed Martin, they project would have easily cost them into the 100 million dollar range. Oh well. Hopefully the military will get what they paid for.
    • which method is likely to come up with the more innovative solution?

      you think this is a bad idea? they have how many engineers and people working on the problem? and if they used a 100 million and a team of lockheed martin?
      and you think this is WRONG?

    • by Zathrus (232140) on Wednesday March 10, 2004 @12:24PM (#8521727) Homepage
      with this is simply how cheap the US military is getting away with this

      Getting away with what? Basic R&D?

      So you'd rather have them spend a few billion on a single supplier, who may not be able to deliver anything, and then keep all the technology as classified for an unknown period of time? Yeah, that's a great use of taxpayer money.

      Instead, they put out a challenge that allows both public and private industry to participate. Any useful technology could be immediately spun off for commercial use, and considerably less taxpayer funds are used (yes, public universities will use some taxpayer money as well, but it pales in comparison to the alternative).

      Oh, and they're still not "getting away" with anything. DARPA doesn't automatically get the technology. If they get a winner then they'll have to negotiate licensing terms.
  • Anyone know if there are plans to televize or broadcast the race in any form?
    • Re:Broadcast? (Score:4, Informative)

      by qedigital (545151) on Wednesday March 10, 2004 @11:40AM (#8521307) Homepage
      You can check out DARPA's satellite feed on Saturday:

      From http://www.darpa.mil/grandchallenge/media_feeds.ht m [darpa.mil]

      On Saturday, March 13, DARPA will provide same-day coverage via satellite of the Grand Challenge start and highlights at the following times:

      Live coverage of the start: 6:30 - 8:30 Pacific/9:30 - 11:30 a.m. Eastern
      Video news release: 11:00 - 11:30 a.m. Pacific/2:00 - 2:30 p.m. Eastern

      Coordinates for both feeds:
      Satellite: AMC 9, Ku, Transponder 03
      Space is: 36 MHz
      Downlink Frequency: 11760.000
      Downlink Polarity: Vertical

      Hopefully someone will record these feeds and make them available online for all of us without satellite

  • Field Report, Day 2 (Score:2, Informative)

    by EvilXenu (706326)
    Here's the second day field report sent to me by a friend who is out attending the DARPA Grand Challenge. Posted with his permission:

    Attendance was about the same today except it didn't appear that there was as many media representatives present. Again temperatures were in the 90's. I acquired a media pass today and was allowed access to almost every area of the speedway including the pits and the start line. This will allow me to film each entry up close and interview members of the teams. DARPA is

  • Hopefully, this is just the first step towards that goal.

    Given the 40 or so years between the DoD's ARPA net experiments and what we have now, it isn't that far fetched.
  • by loac (585499) on Wednesday March 10, 2004 @12:51PM (#8522017)
    I could have saved them $250,000 in sensors by installing a $100 roll bar!
  • DNT(DO NOT TEST)
  • I was there (Score:4, Insightful)

    by Kallahar (227430) <kallahar@quickwired.com> on Wednesday March 10, 2004 @01:12PM (#8522178) Homepage
    I went by the event yesterday as a spectator and got to see Red Team do their run. Of the 23 teams who made it this far, they're the only one that has completed the qualification course so far. People complain that they have a more accurate map and that they're not doing real AI, but based on their performance on this surprise course, they have a real obstacle avoidance system.

    In one section there was a minivan parked in the center of the GPS path. Of the eight vehicles I saw run, only three made it past the car. Three hit it, and the rest failed before making it that far.

    It seemed that the biggest problems teams had were getting GPS right. Several drifted off course or turned the wrong way, going off course. One got the next GPS coord inside of its turning radius so it kept circling a spot until they turned it off.

    Lots of great designs though, and some really impressive engineering.
  • by citanon (579906) on Wednesday March 10, 2004 @01:25PM (#8522351)
    You can look at the latest pictures, the teams' relative positions, and status charts.

    http://www.grandchallenge.org/
  • The New Scientist has a nice writeup of the qualifying round as it now stands. The last paragraph is particularly interesting.
    DARPA says it will do everything it can to make sure all vehicles capable of stopping safely qualify, which includes allowing them multiple chances to qualify and perhaps ignoring rare crashes. The finalists will be announced on Friday morning.
    http://www.newscientist.com/news/news.jsp?id=ns999 94757
  • From the Red Team log [redteamracing.org]:

    I withheld midterm grades of our course, pending the outcome of QID, since this is a third of the grade. Since QID went well, grades will be good, and it will be a pleasure to assign these.

    Withold the grades, and students will do anything. (Note to Theory profs out there: withhold grades until someone proves P != NP )

  • Is it too late for me to enter my Roomba?
  • by citanon (579906) on Wednesday March 10, 2004 @02:13PM (#8522979)
    Towards the end of this year, PCI-Express and next generation graphics cards using them will come to market.

    How is this significant for the DARPA race?

    Well, newer generation graphics cards with highly programmable graphics pipelines can act as very powerful SIMD processors. Up until now, their capability has not seen much use outside of graphics because the AGP bus allows data to travel at full bandwidth in only one direction at a time. This meant that every time you need to download data from the video card, you had to flush the AGP bus, loosing or delaying the uploaded data.

    With PCI-Express, data could travel both ways concurrently at full bandwidth, so there's the potential for using the graphics card as a specialized SIMD processor.

    I bet much of the processing for the vision and obstacle avoidance could be done on a GPU. If that's the case, instead of having a 1.5 gigaflops CPU per pc, you could have 10 or 20 gigaflops (IIRC) of processing power at your disposal for little over $1000, thus making the necessary computing hardware much cheaper.

    Currently, the CMU team, for example, has multi-itanium servers aboard their Hummer, which is NOT something doable on a shoe string budget.
  • by Upright Joe (658035) <uprightjoeNO@SPAMgmail.com> on Wednesday March 10, 2004 @03:23PM (#8523801) Homepage
    Man, these teams are using the wrong military vehicles. Humvees? Supply trucks? What the hell is that? Seriously man, strap a GPS system onto an M1 Abrams and open that baby up.

    I say screw collision avoidance. Go for collision dominance. Any obstacle capable of stopping a 65 ton tank travelling at 45mph is gonna show up on the mother f**king map.
  • by big_ara (760977) on Wednesday March 10, 2004 @03:26PM (#8523838)
    I am at the DARPA grand challenge right now.

    Here are some photos:

    DARPA Grand Challenge Photos [mit.edu]

    Enjoy!

"Card readers? We don't need no stinking card readers." -- Peter da Silva (at the National Academy of Sciencies, 1965, in a particularly vivid fantasy)

Working...