Slashdot Mirror

← Back to Stories (view on slashdot.org)

DARPA Announces Grand Challenge 2005

Posted by michael on from the calling-all-cars-calling-all-cars dept.

An anonymous reader writes "The Grand Challenge 2005 Date has been announced for October 8, 2005. Check out DARPA's official webpage for details. Already several teams from last year are gearing up: Carnegie Mellon Red Team, D.A.D., and Cal Tech. Also, several new teams are entering, among them Stanford, and Florida Tech. Should be a very interesting Challenge next year!"

10 of 164 comments (clear)

  1. We'll see... by darth_MALL · · Score: 5, Funny

    "Should be a very interesting Challenge next year!" ...more so if anyone finishes

    1. Re:We'll see... by GuyMannDude · · Score: 5, Insightful

      "Should be a very interesting Challenge next year!" ...more so if anyone finishes

      More interesting for who? The crowd or the researchers? Hey, if you want an exciting race, go watch NASCAR (or not). As far as the researchers are concerned, it's probably more interesting when these things fail to finish the race than if they all completed the course without difficulty. Each failure teachs the researchers something about AI. These "lessons learned" are then used for a variety of applications and theoretical extensions, not just building a better autonomous car.

      DARPA is not putting on these contests because they expect someone to win. They are trying to give researchers a difficult problem to work on. Don't be looking at the fact that none of the vehicles came close to finishing the race as some sort of failure or "boring". The problem is quite exciting for the researchers and for anyone interested in AI. The fact that they are making it an annual thing is icing on the cake.

      GMD

      --
      watch this
  2. Based on the 'successes' of 2004... by YodaToo · · Score: 4, Funny

    ...the 2005 challenge will involve creating autonomous vehicles that can navigate one mile along a flat, empty highway with a clearly marked, solid center strip. The vehicles will have one week to navigate the course

    --
    This way to the egress...
  3. what if... by teknokracy · · Score: 4, Funny

    This year: Make a robot that will successfully find a parking spot at the mall!

  4. I wish I had... by Cyclotron_Boy · · Score: 5, Funny

    a big garage, a spare '67 IH Scout 800, a laptop I could trash, assorted robotics parts, and a month or two paid time off (or better yet- sponsored by my work)... I just *know* I could get out of the parking lot...

  5. I still don't understand why they don't by Marxist+Hacker+42 · · Score: 4, Funny

    just build the machine itself to be relatively indestructable- handling any terrain. Say with four wheels large enough to be completely invertable and floatable. Then just add a GPS unit and skid steering, and some simple logic to try 4 times, then rotate 90 degrees, run for 100 feet, rotate back 90 degrees, and try again, recursively, plus seek out pregrogrammed destination co-ordinates. Make it go up to 60 MPH to make up time when it doesn't have any barriers to get around, and let it go. It might not take the straightest route, but it will get there eventually- kind of like my 1-year-old's bumble ball robot that has no brains at all, just a gyroscope and bumpers to keep it moving in random directions.

    Even better yet- a huge bumble ball with GPS locator to tell us where it is- just drop it into ANY terrain, and it will bounce around until it gets where it wants to be.

    --
    SJW: a person who perceives an injustice, and while correcting it, commits a greater injustice.
  6. Florida Tech? by TXGB324 · · Score: 5, Informative

    As a proud dropout of Florida Tech, I'd just like to point out that the "Florida Tech" link goes to an article about the University of Florida. If Florida Tech is competting, I wish them all the best luck. Here's the correct link to their website: www.fit.edu

  7. Re:DARPA. Aren't they... by GuyMannDude · · Score: 5, Insightful

    the same spooks that want to identify terrorists by how they walk?

    No, they're the ones who created the Internet. You know, that thing you're using right now. Plus, they happen to be a huge supporter of scientific research and development. Given the fact that industry has slashed R&D in favor of raising the quarterly reports by a half a percentage point or giving the members of the Board an ivory backscratcher as an annual bonus, let's not be too quick to insult one of the few remaining patrons of science.

    GMD

    --
    watch this
  8. Should be good by nizo · · Score: 5, Funny
    The DARPA Grand Challenge is a field test designed to accelerate research and development in autonomous ground vehicles that will help save lives on the future battlefield.

    I can't wait to see all the new automated field medic designs. Wait, why does that one have a big gun sticking out of the top....

    --
    I Am My Own Worst Enemy
  9. Lessons Learned by texbot · · Score: 5, Interesting
    As a member of Team Caltech I can say that next year's race going to be much more exciting for a couple of reasons.

    First off, returning teams already have a foundation to build upon, both in existing hardware and in technical experience. Writing software for a race like this is almost impossible to do without testing it on a working vehicle (i.e. testing in simulation only works out major problems, but does not translate well to desert racing). For example, Caltech spent 6 months getting actuators and drivers to work well enough to hand over the vehicle to the software team. As soon as that happened, we noticed several problems interfacing the actuators to the software (e.g. updating actuator positions too fast locked them up and made them stop responding). Ultimately our vehicle was not even waypoint following accurately until late February. Most teams were in the same state we were in - racing the clock, plagued by bad hardware (sensors and actuators) and inexperience. BUT we were very close to being very good. If they re-ran the race mid-summer this year the results from all of the teams would be very different. Looking to next year, teams have working vehicles which means 1 full year of onsite testing instead of 2 months.

    Another thing that is interesting about the next race is the timing relative to academic calendars. A lot of teams are university driven and it was very difficult for students to devote enough time to the project while still handling their school requirements (definitely true with a Caltech workload). The next race is at the very end of the summer which means that a crew can work on the vehicle full time for three months before the next race.

    Whether or not someone wins the next race is entirely up to DARPA. By next year there will be 5+ teams that could navegate last-race's course in

    Anyway, good luck to all teams...especially new teams - you have quite a hurdle in front of you. See you in 1 year.