Stories
Slash Boxes
Comments
Search

News for nerds, stuff that matters

Slashdot Log In

Log In

Create Account  |  Retrieve Password

DARPA Files Patent On Predictive Simulation

Posted by Zonk on Wed Aug 22, 2007 02:37 AM
from the looking-to-the-past-for-the-future dept.
Patents Privacy Science Technology
An anonymous reader writes "New Scientist has a post on a patent filed by the Defense Advanced Research Projects Agency (DARPA), seeking to control a new potent predictive simulation. The patent outlines the process, which may someday allow researchers to accurately predict the behavior of observed subjects. They're not there yet, but not for lack of trying. It already works in some military war game scenarios, says the patent. 'Parunak says his model can successfully detect players' emotions, and then predict future actions accordingly. He believes the technique could one day be applied to predict the behavior of adversaries in military combat situations, competitive business tactics, and even multiplayer computer games. The patent application gives an interesting insight into DARPA's goals. The agency has pumped a lot of money into AI in recent years without reaping major rewards. One day computers may find a way to accurately second-guess humans, but I suspect we may have to wait a little longer yet.'"
+ -
story

Related Stories

Submission: Can DARPA predict what you'll do next? by Anonymous Coward
This discussion has been archived. No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.

DARPA Files Patent On Predictive Simulation 50 Comments More /

 Full
 Abbreviated
 Hidden
More
Loading... please wait.
  • have these scientists not watched a single sci-fi movie. Military machines that can predict human behavior always lead to human enslavement. and the only way to stop them is by sending those machines back in time to stop us from building the machines in the first place.

    • Re: (Score:3, Interesting)

      by Znork (31774)
      "have these scientists not watched a single sci-fi movie."

      Apparently they havent watched history movies either.

      The appropriate response to someone attempting to predict your behaviour is to feed their prediction algorithm false data (aka, feints, lying, etc). That way _you_ can predict _their_ behaviour, and not only that, you can even _control_ their behaviour.

      This isnt something particularly new. This is the same old thing 'but on a computer'. I expect to momentarily see another patent application for the
        • "What you really need is a random strategy generator."

          Would a recursive strategy make it go boom? Would a "mexican stand off" freeze the input device?

          The only strategy here is "raise the signal to noise ratio", aka "FUD". I'm sure their mates who plant stories in the media can get some coverage for a bullshit (but not worthless) patent. It may be that it ends up bringing in royalties from their favoured game maker's public releases.

          I hope not, I love shoot-em-ups and think using them to train troop

        • Re:are you sure this is a good idea? (Score:5, Insightful)

          by Dragonslicer (991472) on Wednesday August 22 2007, @06:28AM (#20316371)

          What you really need is a random strategy generator.
          "Professionals are predictable; amateurs are dangerous."

  • Obligatory... (Score:4, Funny)

    by ZombieRoboNinja (905329) on Wednesday August 22 2007, @03:02AM (#20315549)
    Step 1: Patented behavior-prediction computer
    Step 2: Beowulf cluster
    Step 3: ???
    Step 4: Psychohistory! [wikipedia.org]
    • I thought you were going to say...

      Step 4. Scientology, (with oblig. Tom Cruise & Precog ref.)
      Step 5. Prophet!

  • Prior art (Score:4, Funny)

    by MillionthMonkey (240664) on Wednesday August 22 2007, @03:02AM (#20315551)
    I have already predicted with 100% precision that this patent will be granted.

    • Re: (Score:3, Insightful)

      by ebonum (830686)
      Interesting point. In someway you have "reproduced" invention.

      For a patent to be granted, someone skilled in the art should be able to take the patent and build it.

      "The patent statute requires that the application describe the invention in its "best mode" to enable an individual skilled in the art relevant to the invention to be able to repeat the invention."

      If they can't actually build it, this SHOULD be a mute point.

  • Meh (Score:3, Interesting)

    by SamP2 (1097897) on Wednesday August 22 2007, @03:07AM (#20315575)
    When a genuinely new way of doing something is patented, I don't see much of a problem. Even if you don't agree with software patents in principle, patents that introduce a new technology tend to expire before the technology matures enough to become profitable. In that case, the patent filer gets the honestly deserved upper hand of having better in-house knowledge about the technology by the time it gets to production stage, instead of having the unfair advantage of forced monopoly over its production.

    Some patents are harmful - such as those which either patent a well known technology they didn't really invent, or patentsquatting (patenting something with the only reason of preventing others from using this technology, even if you have no intention of using it yourself either), but it doesn't seem this was one of these cases.

    If the copyright system worked like the patent system (requires novelty and expires in a reasonable amount of time (~5 years)) then we'd be living in a much better world.

    • Re: (Score:3, Interesting)

      by StringBlade (557322)
      I agree with your statements on patents in general, but we're talking about DARPA here...a government agency. The government is not supposed to be able to patent technologies or if they did, that would (should?) effectively make it unpatentable by private parties because the patent is collectively owned by all the taxpayers.

      As for copyrights, I don't think the same rules should apply as patents but I do think that the copyright lengths should reflect those of patents (or be even shorter since copyrights ar

  • Interesting idea (Score:3, Funny)

    by Splab (574204) on Wednesday August 22 2007, @03:25AM (#20315649)
    This is not as far fetched as one might think - if you have ever played a game like counter strike and observed the players on a public server, you can see the follow a very predictive pattern.
  • All video games infringe this patent.

    While senators are desperately seeking ways to outlaw us playing violent video games, DARPA found its way outlawing all video game once and for all.
  • Seems that someone else got this idea earlier.

    Just see that:
    Isaac Asimov's Psychohistory [wikipedia.org]
    Is that patent valid since the prior art [wikipedia.org] arleady exists?

    /Z
  • He believes the technique could one day be applied to predict the behavior of adversaries in military combat situations, competitive business tactics, and even multiplayer computer games.

    We can run this simulation to predict what other players are going to do in a simulation.

  • I knew they were going to do that (Score:3, Funny)

    by niceone (992278) * on Wednesday August 22 2007, @03:50AM (#20315743) Journal
    My prior art told me yesterday.
  • How effective can this really be? What if both sides have said tech? Then they both know what each other thinks that the other is doing and change tactics accordingly.
    • At the very least, it might make for an interesting scene in a movie. [imdb.com]
    • Well, if the other side knows you have it, they can already try to fool it.
      Military history is full of very intersting examples of one side building very complex missions to make the other side believe it managed to collect valuable intelligence.
  • ...a model of the agent's emotional disposition and state, ...
    16. The method of claim 1, wherein the simulation involves urban warfare.

    Well that's a no-brainer, they're pissed off!

    Seriously though this is BDE thing that novel that it can be patented? It seems like a useful algorithm, how come they can patent it?
  • Someday I'm gonna be walking around an apartment in Paris to find a computer program that greets me with a full summary of my file...

  • Psychohistory? (Score:3, Interesting)

    by the_arrow (171557) on Wednesday August 22 2007, @04:57AM (#20315983) Homepage
    Someone should tell Hari Seldon his work is already done!

    • Someone should tell Hari Seldon his work is already done!
      Only as long as the mechanism is good enough to predict the mule and adapt accordingly.
  • Is 42, HA! I'd like to see a machine predict that. Then i googled the answer to everything and it gave me 42. Yea, thats all i got. As I predicted everything insightful i was going to say has already been said.

  • This is where DARPA got the original Idea (Score:3, Informative)

    by Shohat (959481) on Wednesday August 22 2007, @05:29AM (#20316099) Homepage
    DARPA issues a 2 million $ challenge to build a driverless car.
    A brilliant engineer built such a car, that was able to navigate in complex environments at high speeds by predicting the size, shape and behavior of surroundings on its path through simulation, according to the behavior of similar environment and path structures it has already passed. This causes the car to actually gain speed and statistical confidence in its own upcoming actions simply by acquiring enough experience of driving in similar environment.
    Same kind of algorithm can of course be applied to any machine that is expected to operate for a long time in a complex semi-predictable environment - such as forex trading, poker, or a battlefield
    This is the story on Wired [wired.com]
  • wonder if a braod patent like this could be applied in some situations to games ... say gta?

  • The patent outlines the process, which may someday allow researchers to accurately predict the behavior of observed subjects.

    Presumably it will only allow some researcher to predict behavior. Researchers who lack the money or clout to license the patent won't have the legal ability to make predictions using this technology.

    I hate government patents.

  • ... and ideal basis for an unbeatable poker bot.

    Vegas here I come!
  • Folks likening this to Harry Seldon's psychohistory in Isaac Asimov's books are missing the point. Psychohistory was predicting the movements of a society as a whole. What DARPA is striving to do is predict the behaviour of individuals faster than those individuals can act.

    An "obvious" method for doing this is to somehow capture the individual's state vector and that of its surrounding environment, and simulate it in faster than realtime. Stuff of science fiction for now, and it is usually referred to as po
  • *spit* on our new behaviour predicting overlord.

    Dang it.

    How did it manage to dodge that?
  • I vaguely recall some Asimov series (one of his better known ones, IIR) that deals with the ability to predict group behavior quite successfully through some sort of psychology. It seemed to evolve into some kind of "future guessing" where he warns of a messianic figure or something. Assuming my memory is anywhere near what I think I'm referring to, it's an interesting case of life imitating art...

  • The prediction of this mechanism is predicated on the fact that the subjects being observed are not aware of the observer. The mere fact of observing may change the outcome of the objects' behaviour. Now, thanks to the slahdot effect, this mechanism & its patent will be rendered useless.
     

  • This is either great or awful (Score:4, Insightful)

    by melted (227442) on Wednesday August 22 2007, @09:50AM (#20318353) Homepage
    Depending on the legal interpretation. On one hand as a government agency all work done by DARPA should be public domain. On the other hand they somehow managed to patent this. Does this mean that this is an anti-patent, i.e. no one else can patent this anymore and everyone can use it? Or did they find a legal loophole which could prevent everyone else from using the tech? If it's the latter, it's pretty horrible. DARPA pays for a heck of a lot of fundamental innovation each year (with taxpayer money, of course). If they start patenting it a lot of things will come to a grinding halt.

    Any lawyers on the thread?

    • Re:Riiiight... (Score:4, Funny)

      by Mr2cents (323101) on Wednesday August 22 2007, @03:26AM (#20315659)
      That's what I didn't get: if you want to use something like that for war games, why patent it? Then you have to disclose how you did it, no? Betting that your enemy will not use this because of patent laws, is quite optimistic thinking.

      USA: Please stop using our wargame simulation technology, you're only making it worse.
      Enemy: Making it worse? How can it possibly get any worse? Coca-Cola! Coca-Cola!
      USA: And don't abuse our trademarks!

      • Re: (Score:3, Interesting)

        by QuickFox (311231)

        Then you have to disclose how you did it, no?

        They want to disclose this.

        The military people can already make predictions. They need others to make predictions too. They're sick and tired of propagandists and politicians who can't make even the simplest and most evident predictions.

        The military people know, for example, that adventures like the invasion of Iraq only serve to fuel terrorism and make everything a hundred times worse. That's simple common sense. But since the propaganda machinery and the politicians lack all common sense, the military pe

        • Maybe it's for the people that would happily ignore "opinions" of high ranking military personnel, but would pray at the results from a computer...

                Calin
        • Isn't it because the 'enemy' doesn't do its own predictions by algorithms and therefore unpredictable?

        • The military people know, for example, that adventures like the invasion of Iraq only serve to fuel terrorism and make everything a hundred times worse. That's simple common sense. But since the propaganda machinery and the politicians lack all common sense...

          It's quite right that the way USA dealt with Iraq and terror suspects just creates more problems.

          I don't subscribe to the assertion that politicians do it for stupidity.

          IMHO Bush has powerful support that go beyond the two party system. Else he'd not h

        • The military people can already make predictions. They need others to make predictions too.

          Exactly. Coincidentally, this was the reasoning behind DARPA's proposed prediction market [wikipedia.org], which would harness the "wisdom of crowds" to quantify probabilities of events. It got canceled, like all good ideas, because it offended the wrong people.

      • Re: (Score:3, Funny)

        by jamesh (87723)
        But because of the patent, if the enemy wins the war then the USA can take them to court and seek a good amount of the spoils of war in compensation. Now that lawyer would be one earning his commission!

    • Re: (Score:2, Informative)

      by tgv (254536)
      I would like to see your solution for these equations for normal human behaviour. For some reason, I think you cannot even formulate the objective, let alone solve it. This model might be suboptimal, but that doesn't make it worse than random guessing.

        • Re: (Score:3, Interesting)

          by tgv (254536)
          First: I doubt the alternatives have equal probabilities. In a real world setting, there are hundreds if not thousands of different options at any moment, most of which are highly unlikely. Second, you're not playing against a single person, but against a whole bunch of them, which changes behaviour significantly. Third, you have to take the possible actions of your allies (also a large number of individual agents) into account. That makes computing the probabilities of the joint actions and the joint distr

        • Re: (Score:3, Insightful)

          by rtb61 (674572)
          More specifically predictive simulation can be very effective but it is completely subject to the quality of information that is used for the prediction of behaviour. Any errors in the information input, and the predication fails, which in turn can lead to a very bad strategy choice ie. instead of making a sound tactical choice, an opportunistic choice is made based upon the optimal solution to the prediction not matter how unsound tactically that choice might be.

          Just another magic box solution, for when

    • Re:Solution: Randomize human behaviour (Score:5, Interesting)

      by bentcd (690786) <bcd@pvv.org> on Wednesday August 22 2007, @04:46AM (#20315939) Homepage

      Even if they could predict human behavior reliably, a counter would be simply to use a dice or random number generator to determine a range of actions that one may perform.
      This would presumably cause you to pursue a strategy that is worse than what you otherwise would have (unless you're a really crappy strategist so that random choice outperforms conscious planning). If so, then mark that down as a victory for the prediction system.

      It becomes a bit like land mines: it forces you to use a less optimal route to your target than what you would have preferred. There must be a term waiting to be coined here. Idea space denial?
      • problem is that EVERY simulation system has it's saturation point. if you have it predicting one outcome, then let the leaders believe that outcome is what is happening and they will do stupid things that leave your second and third teams wide open to attack from behind, or they will focus on what looks like a small platoon coming in to attack the front gate while one lone bomber set's off his bomb on the secondary target.

        No computer simulation can figure out everything that will happen, embrace that and a

        • It's not like there's one perfect strategy. The worst strategy of all is the one the enemy is expecting and prepared for.

          Of course. But if this is a tool that will enable your enemy to consistently expect and prepare for what would /otherwise/ have been your best strategy, then this is to your detriment.

          (Of course, the tool should develop into expecting that you will avoid what would theoretically be the best strategy since you anticipate that the tool will predict this strategy, and so on and so forth. In the end, it will most likely be an expert system for helping you determine where to put your various countermeasures in

    • populace can be easily manipulated by fear

      to fabricate the illusion of security

      These goals seem contradictory. Perhaps these are used in a repeating cycle of fear, manipulation, false security?

All trademarks and copyrights on this page are owned by their respective owners. Comments are owned by the Poster. The Rest © 1997-2009 Geeknet, Inc.