Follow Slashdot stories on Twitter


Forgot your password?
Software Technology

Using AI To Train Firefighters 67

Roland Piquepaille writes "Computer scientists at the University of Southern California (USC) have developed DEFACTO, a training program which uses artificial intelligence (AI) to help firefighters practice simulated emergency situations. The system is currently used by the Los Angeles Fire Department. DEFACTO has committees of AI 'agents' which can create disaster scenarios with images and maps seen in 3-D by the trainees. The software agents also evaluate the trainees' answers and help them to take better decisions. As one LAFD captain said, 'You can see if you're heading toward a mistake much more quickly.' Read more for additional details about this AI project and a photo of a LAFD Fire Captain using the system."
This discussion has been archived. No new comments can be posted.

Using AI To Train Firefighters

Comments Filter:
  • by RuBLed ( 995686 ) on Thursday June 07, 2007 @02:48AM (#19420873)
    I believe the fire captain is playing.. errr.. beta testing Sim City Societies, I swear I could see the Firefighter dispatch tool...
  • "America's Firemen"? (Score:5, Interesting)

    by weighn ( 578357 ) <weighn&gmail,com> on Thursday June 07, 2007 @02:49AM (#19420877) Homepage
    so can the USC use some of this code as the basis for a game? This could be used as both a recruiting tool and an aid to help recovering pyrophobics.

    I'm not suggesting that it would be a shame for all this hard work to go into just training guys to save lives and property :) but the screenshots suggest that there could be elements of strategy (which block to approach from, consideration of wind conditions) and some cool FPS with the water cannon. Possibly some riot quelling action too ... are there any firefighting sims out there? Perhaps a multi-player which pits firefighters against arsonists?

    • >recovering pyrophobics

      Is *getting over* a fear of fire really a good thing? I think my fear of fire is a pretty healthy attribute, alongside my fear of lions, cyanide and axe-wielding nutjobs.
      • by Aladrin ( 926209 )
        Phobias aren't 'fear', they're 'irrational fear'. The kind of fear that makes you lock up and do -nothing- or do the wrong thing, instead of keeping a level head and dealing with the situation.

        Personally, I don't think it's possible to 'get over' a phobia. I think you can control it, and learn to make yourself control the situation instead of letting the situation control you, but a pyrophobe will -never- stop being afraid of fire.
        • Re: (Score:1, Informative)

          by Anonymous Coward

          Personally, I don't think it's possible to 'get over' a phobia.

          Read up on the Emotional Freedom Technique. [] (Although it's difficult to prove it works, as wiki mentions, there is a lot of anecdotal evidence that it helps people.)

    • Burning Rangers was a firefighting game. A scifi firefighting game. Ticks all the boxes, that one.
    • Funny you should ask. I wrote the 3D visualization tool for this while I was a grad student at USC. I used Torque game engine to use an existing model (aquired using LiDAR) and layered on an arial photograph on it for the textures - that's how much fancy I could have gotten given the time we had. I left in 2005 and am not sure if they are still using it though. But, the pictures you see on TFA are screenshots from the tool I developed. As to why I'm not listed on the list of grad students who participated o
  • The AI program should be able to cook up a four-alarm chili that puts the best firehouse cook to shame.
  • Questionable Results (Score:5, Informative)

    by Vskye ( 9079 ) on Thursday June 07, 2007 @03:32AM (#19420997)
    First off, it's a AI program. This will not give you that much practical experience compared to being in a more traditional controlled test environment. I used to run ship fire simulations, with actual fire and smoke in a building setup for this type of deal when I was in the Navy. We actually trained a group of Iranians back in the day, and I remember several trying to get out of the port holes on the building, because they freaked out. (ever see a 2 1/2" hose flying around? this will put a serious hurt on your team if nailed.) I guess my whole point is that actually going into a test environment on a moments notice, donning your equipment and getting a first hand view of smoke/fire is a better experience, IMHO.
    • I see your point if this were to replace traditional methods of training, but do not see how you reached the conclusion, that this will replace not supplement traditional training methods. I draw the conclusion that training (physical) and training(mental) would yield better results, neither being as significant if used separately.
    • Re: (Score:3, Interesting)

      by utnapistim ( 931738 )

      guess my whole point is that actually going into a test environment on a moments notice, donning your equipment and getting a first hand view of smoke/fire is a better experience, IMHO.

      I don't think there is any theoretical training that can replace the hands-on experience. When I did the SCUBA Rescue diver course, we had to - first - get over the theoretical part (check for dangers, approach, evaluate, check for breathing etc.), and - second - go through with actual exercises.

      I think all courses (shoul

    • by hcdejong ( 561314 ) <hobbes&xmsnet,nl> on Thursday June 07, 2007 @04:55AM (#19421299)
      As others have said, this simulator isn't meant to replace basic training. It's about planning how to attack a major fire.
      ...a more traditional controlled test environment.

      The problem with such an environment is that it's limited in size, and has a fixed layout. This is no problem for initial training, but experienced firefighters will go in knowing what to expect, which skews the results.

      With the simulator, you can present scenarios that are guaranteed to be unfamiliar to the trainee, and on a much larger scope than physically feasible.

      Similar systems are used in the army: they have lots of hands-on weapons training for the soldiers, but also "command post exercises" where the trainee commanders just shuffle paper, issue radio orders etc. and no bullets are involved. In such an exercise the commander can learn how to manage his division, in scenarios that can't be played out in real life (e.g. because there's no training ground big enough to do battles with an entire division, plus there's the cost factor).
    • Different Approach (Score:3, Informative)

      by Raptoer ( 984438 )
      This is not to replace real training at all, I totally agree that this type of training can and never will be able to (in the foreseeable future) match a real training simulator. This is more of management type training, where a firefighter learns how to make decisions with disaster type situations.

      The real advantage of this system of the previous version is it no longer ties up an entire fire team in order to run the simulation, it comes up with truly random situations (a person is more likely to train peo
    • This will not give you that much practical experience compared to being in a more traditional controlled test environment.

      The advantages of simulated training environments extend into the metaphysical realm by enabling capabilities unavailable to us in the real world: Repeatable scenarios with zero reset time and zero physical impact, multi-variable scenario configurations, visually replayable and multi-angle post motum analysis, time dialation and multiplication, etc.

      Simulators give trainees a chance to work on specific skills without having to go to the time, expense, and danger (in this case) of dealing with the real t

    • also i have a couple of questions

      1 will they use this to make a few AI firemen?? (some of the current ones need upgrades)
      2 how well does it train on the Trivial > interesting > Fun > Break out the marshmellows > RUN LIKE HXXX! part of the exercise?
  • Since when were laptop batteries referred to as AI?

  • Is it something like this one? []
  • Remember this gem of the Sega Saturn ?
    Better prep for the future of FireFighting :) []
  • by mazzanet ( 804816 ) on Thursday June 07, 2007 @04:52AM (#19421279) Homepage
    Over here in the lovable land of .au, we (CFA []) and other fire agencies around the country already use a training simulator made by VectorCommand in the UK (link []) which is very similar to this package in the OP. Career staff particularly, as well as volunteers, are readily ran through various exercises and drills on it. One of the most useful features is that it a scenario can be run individually or with a team of users (with networked computers).
    • Something I forgot to add is that as well as the occasional AI training, physical practical (including hot drills in structures - 'fire houses') and theory training is pushed heavily with a very comprehensive training program that includes Australian Standards and nationally recognised qualifications.
  • A company called vectorcommand have been doing this for years, check out there site []
  • I've gone thru actual fire fighting training, from structure to fuel storage/well head suppression to forest fire fighting in remote areas, and until you've had a chance to choke on real smoke and smell real burning flesh, you're not quite capable of grasping the gravity of what you may have gotten yourself into when things are no longer being simulated.

    That said, simulations could help to weed out the ones that sign on as a result of the 'fever' and excitement that attracts a certain type looking only f
    • I know you couldn't pass up the opportunity to mention "burning flesh", but it should be pretty clear to anyone in the fire service (or anyone who RTFA for that matter), that this is designed for training command officers, not line firefighters or engineers.

      And by the way djupedal... nowadays we wear this nifty new-fangle technology call "SCBA" which helps prevent that whole choking on smoke thing.
      • the problem is what happens when

        A you land up in an area that went from trivial to interesting (could you last long enough to mask up?)
        B what happens if that nifty tech breaks on you (chunk of wall manages to smash your airpack or you time out because you managed to get trapped)?
        • Which is why you train hands on... I never denied that, was just pointing out that with modern technology choking on smoke is not generally necessary.

          Filter breathing, wall breeching, bailouts, RIT, all sorts of things you should be training on regularly if you are on the line. How many chiefs need those hands-on skills? They need to have an understanding of their team's capabilities, and how to best utilize the resources they provide.
  • I'm a Lieutenant on a small department, and have been part of many "simulator" drills using not so artificial intelligence. We use an overhead project, software that allows drag and drop visual and audio changes to simulate the progression of a fire against a background image, and the real intelligence of a senior officer running the drill. The purpose of the drill is to give experience to the firefighters and officers making decision on how to attack the fire and when to take certain actions.

    It is NOT about the individual firefighter on the line doing his job -- he's not meant to be focused on the big picture. He's got to focus on his local task as assigned -- search, vent, attack, etc.

    The important thing, is that the person running the drill has a situation in his head about what caused the fire and how it will progress through the building, and can adjust the progression as a result of the decisions made by the officer making decisions. Once done, a great benefit of the experience is the discussion. Another huge benefit is the practice at simply making best use of radio traffic and keeping the situation in mind all at once.

    The only advantage I see to this software they're showing is that it requires less people so you could have more people being in charge of the scenario and learning. They lose the experience coordinating the radio traffic, and the discussion at the end of how their tactics impacted the results would not benefit as many people.
  • Who is... (Score:1, Offtopic)

    by ehaggis ( 879721 )
    Al? Ohhhh... AI!
  • ... but what if the fire isn't near a train route!??!

    You'll forgive me for not caring to read the article, but it's a Roland Piquepaille job. Is that wrong of me?

  • by Marvin01 ( 909379 )
    I would have thought he would be kept pretty busy with the Nuggets... I guess he needs something to do during the playoffs.
  • Fight fire with AI.
  • What kind of AI is it? Is it rule-based AI, neural nets? You don't really need AI for physical simulations, and victim simulation may be able to be done with some basic probability rules. Rule-based AI is somethings not considered AI, harkening back to the 80's statement "Man, people are calling anything with IF statements 'Expert Systems'". I sense some possible hype here.
    • The AI is actually based on a Multi-Agent solution. I saw a presentation of this firefighting system at an AI/Multi Agent conference last year (AMAAS). At a simple level, agents use BDI theory -- Beliefs, Desires, & Intents. The agents in this scenario not only create the and run the disaster scenario, but they also represent the resources in use. Each agent has a set of goals that it is trying to achieve and the system generates a set of plans for achieving those goals. Mix all these agents together a
  • In Soviet America, AI programs you!

"The number of Unix installations has grown to 10, with more expected." -- The Unix Programmer's Manual, 2nd Edition, June, 1972