Forgot your password?
typodupeerror
Robotics Science

Another Step Towards the Driverless Car 224

Posted by CowboyNeal
from the optical-sensors-said-the-light-was-yellow dept.
jtogel writes "At Essex, we have for some time been working on automatically learning how to race cars in simulation. It turns out that a combination of evolutionary algorithms and neural networks can learn how to beat all humans in racing games, and also come up with some quite interesting, novel behaviours, which might one day make their way into commercial racing games. While this is simulation, the race is now on for the real thing — we are setting up a competition for AI developers, where the goal is to win a race between model cars on real tracks. As the cars will be around half a meter long, the cost of participating will be a fraction of that for the famous DARPA Grand Challenge, whereas the challenges will be similar in terms of computer vision and AI."
This discussion has been archived. No new comments can be posted.

Another Step Towards the Driverless Car

Comments Filter:
  • In case of rapture (Score:5, Insightful)

    by Harmonious Botch (921977) * on Thursday March 22, 2007 @08:22PM (#18452357) Homepage Journal
    At least now they won't cause accidents.

    Seriously, this is a technology whose time has come. Persuading elderly drivers to give up their cars is difficult, and the baby boom generation is putting a lot of people in that situation in the next decade or two.
    • by Adambomb (118938) * on Thursday March 22, 2007 @08:31PM (#18452473) Journal
      I must say, I was envisioning disaster when contemplating a world with driving controlled by systems created by humans who arent there to react to unaccounted conditions. You make a bloody excellent point though. The fact that a significant enough percentage of drivers really should NOT be driving would make this a great opportunity. Make it either Opt-In or by Court Order to have to use such automation, and it looks better and better.

      I still would have to be VERY VERY sure of the system and see it tested out the wazoo before I would ever consider getting in one. I don't trust a team of EE and SE specialists to think of all the possible reactions they would need coded in for outlier situations. Even an autopilot for an airplane doesnt have to worry about falling trees, landslides, or elk...unless its a REALLY REALLY bad day at least...
      • by Original Replica (908688) on Thursday March 22, 2007 @09:05PM (#18452855) Journal
        Make it either Opt-In or by Court Order

        Now this, to me, is a very important distiction. What if for this to work well, all the cars have to be computer controlled? What if computer control is then mandated? This is a whole new exciting level of "nanny government". Sure this might be safer in that there would be fewer auto accidents, but do you really want all transportation to be centrally controlled? Sure each car might be autonomous at first, but emergency workers need the ability to remotely turn on off, right? It's for everyone's safety.
        • by codemachine (245871) on Thursday March 22, 2007 @09:31PM (#18453113)
          There are certainly control and privacy issues in automation, as well who is liability in case of an error (which is probably the one thing that won't be overcome - lawyers will never allow it).

          But on the other hand, getting killed in an automobile is much too common, especially given that almost everyone has to travel in one at some point, if not very frequently. Getting around shouldn't be so bloody dangerous considering how ubiquitous it is. Imagine not every having to let drunks choose between being responsible vs driving home drunk. And imagine not ever having to be on the road where some random drunk or incompetent driver, can end your life at any instant, where it is just bad luck that puts you in this spot.

          Automobiles are an outdated and obsolete technology, or at least should be. The problem is coming up with and implementing the "next step" when the current technology is so ingrained into our society and city planning. It is a very non-trivial problem to come up with something better, and another non-trivial problem to "upgrade" to that something better on a live production world.
          • by 56ker (566853)
            Science fiction becomes science fact. The American armed forces already have vehicles that can drive themselves - I remember at least one story by Asimov of a world where cars drove themselves. In that - technology got to the stage where the manufacturers insisted the government legislate compulsory AI driving and accidents disappeared overnight.

            The other posters fears about unaccounted for circumstances are unfounded. If there was some problem with the program it would default to safe mode (eg car would st
            • Re: (Score:3, Interesting)

              by sumdumass (711423)

              The other posters fears about unaccounted for circumstances are unfounded. If there was some problem with the program it would default to safe mode (eg car would stop)

              That would be great if there was a way to make sure every other car would stop too.

              We have autopilot on planes (in fact even planes that can land and take off by themselves), we have satellite navigation, we have remote driving of cars - so why not go the whole way and allow an artificial intelligence to do it?

              There are some differences

          • by inviolet (797804) <slashdotNO@SPAMideasmatter.org> on Thursday March 22, 2007 @11:27PM (#18454153) Journal

            Getting around shouldn't be so bloody dangerous considering how ubiquitous it is. Imagine not every having to let drunks choose between being responsible vs driving home drunk. And imagine not ever having to be on the road where some random drunk or incompetent driver, can end your life at any instant, where it is just bad luck that puts you in this spot.

            The safety aspect is definitely a selling point. But that's not the killer app.

            The killer app for AI cars is: traffic throughput. Right now, traffic throughput is limited by our need to leave lots of space in front of our car so that we don't hit the guy in front of us. This creates low throughput through traffic lights because everyone must wait for the person in front of them to move away, before starting to move too. AI would need none of that.

            Ditto for freeway merges and weaves. AI could weave two lanes of cars together with ease... even without central automation or inter-car communication. All that is needed is a sufficiently standardized algorithm or a sufficiently clever computer. Our brains already do the same, even when the "DriveCar.exe" process is set to low priority in favor of a ringing cellphone.

            Can you imagine how fast traffic could move if (to name just one benefit) everyone rolled forward instantly when the light turned green? And if nobody slowed down to rubberneck a roadside accident?

            The implementation problem might solve itself too. Once AI cars prove their mettle, I can imagine that cities will designate more and more lanes as "AI only", with attendant increases in speed limit and throughput. Sort of like how HOV lanes work today. Soon we'll all be clamoring for an AI car in order to get the same benefits.

            • by Snart Barfunz (526615) on Friday March 23, 2007 @06:19AM (#18456149)
              Just a small point - marketing driverless car software as a 'killer app' - probably a bad idea.
            • The killer app for AI cars is: traffic throughput. Right now, traffic throughput is limited by our need to leave lots of space in front of our car so that we don't hit the guy in front of us.

              Um, no it aint.

              Traffic throughput is limited by how quickly you can get cars off a particular road. i.e. Parking. You can have cars 1/10th of a second apart, but if it takes 10 seconds to park the thing, or even 5 seconds to turn onto another road, that is the limiting factor.

              If everyone has their own car, road performance is limited by parking bandwidth. Now, if everyone used a taxi...

              • by Eccles (932)
                If everyone has their own car, road performance is limited by parking bandwidth. Now, if everyone used a taxi...

                In some situations, this might actually be the solution. You don't own a vehicle, you have taxi service with an autonomous taxi. It drops you off at work, and then drives on to its next pickup. Smart algorithms mean it moves on to the nearest person with autonomous taxi needs. Smarter algorithms might allow the taxi to share taxi service, perhaps with isolated compartments for each person.

                You
                • by Colin Smith (2679)

                  You run into the problem, though, of commuter patterns, as you have a large group of people moving from the 'burbs to the city in the morning, and then all moving back in the afternoon.

                  You just need a cache of taxis at the burb/city end large enough to keep the service time down to within acceptable limits, say a 120 second wait. Bearing in mind that the taxis re-circulate once dropping off their passengers the cache doesn't have to be anything like as large as you might think.

                  And it can be done today without requiring A.I. ...
                  http://faculty.washington.edu/jbs/itrans/prtquick. htm [washington.edu]
                  http://www.atsltd.co.uk/ [atsltd.co.uk]
                  http://www.personalrapidtransit.com/ [personalrapidtransit.com]

                  The performance of a PRT system, like roads, is d

            • by drinkypoo (153816) <martin.espinoza@gmail.com> on Friday March 23, 2007 @10:55AM (#18458665) Homepage Journal

              The killer app for AI cars is: traffic throughput. Right now, traffic throughput is limited by our need to leave lots of space in front of our car so that we don't hit the guy in front of us.

              Yes, and later, traffic throughput will be limited by the need to leave lots of space in front of the car so that if the car in front of us suffers an equipment failure (not necessarily computer-related; a blowout qualifies) the computers have time to work out a solution that doesn't involve collision.

              Certain realities of physics make it a good idea (or even a necessity) to not have cars tailgating one another, even if they are automated and much better drivers than humans are.

              It would make far more sense just to replace the highways with rail lines, load cars onto trains, and ship them places. Then the cars can be loaded literally on top of one another.

          • by zCyl (14362)

            Automobiles are an outdated and obsolete technology, or at least should be. The problem is coming up with and implementing the "next step" when the current technology is so ingrained into our society and city planning.

            Not to mention the fact that half of the people on the planet do not live in cities, and these are the people who usually have to travel farthest. City planning does not universally solve the problem of transportation.
        • by droopycom (470921) on Thursday March 22, 2007 @09:46PM (#18453219)
          You are free to walk. (for the time being).
      • by stratjakt (596332) on Thursday March 22, 2007 @09:23PM (#18453033) Journal
        I bet you can't wait to be stuck in a state run home, either.

        You're probably young, so the ageism can be explained.

        I know people in their 80s, perfectly capable of driving, and renewing their license.

        We don't need dorks mandating new technologies to use. We just need the DMV to do it's job, which is to make sure only qualified drivers are qualified to drive.

      • If the issue is the Rapture, I think most of the people left behind will have tougher aspects of their lives than whether their cars will function safely.

        As far as testing goes, when we were working on the jeep two years ago, we had a nice, big, back yard to play, courtesy of as he [www.scottajones] has considerable acreage (20? 30? 40?). It cuts down additional neighbors and there's a lot of nature preserve. You can't hear the traffic a few blocks east of it from the major thoroughfare coming it's like a nature preserve
        • by Dun Malg (230075)

          Something which most people don't think about is: if the front end crumples too much, the engine has to go somewhere. It certainly doesn't jump out from under the hood and clear itself from the car. It's not going to deflate into a small piece of rubber.

          Nor does it necessarily have to move straight back into the passenger compartment. BMW has made it a selling point to illustrate how their cars are designed such that the forward drive train (engine + transmission) breaks free of the body and is deflected down, so that the passenger compartment rides up over the top of it. Many other high end luxury cars are similarly designed.

          • by drinkypoo (153816)

            BMW has made it a selling point to illustrate how their cars are designed such that the forward drive train (engine + transmission) breaks free of the body and is deflected down, so that the passenger compartment rides up over the top of it. Many other high end luxury cars are similarly designed.

            Practically all cars are designed to do this. The engine and transmission mounts break (nearly all of them consist of two metal plates connected to one another only by a piece of rubber vulcanized between them) and

        • by damiam (409504)
          Something which most people don't think about is: if the front end crumples too much, the engine has to go somewhere. It certainly doesn't jump out from under the hood and clear itself from the car. It's not going to deflate into a small piece of rubber. Imagine parking an engine in your passenger area at a pretty good speed and (people) trying to survive. Did you watch Twister and see the tower fly into the truck's front window? That's minor.

          Safety. Yet another compelling reason to drive a mid-engined car [wikipedia.org]

      • by NonSequor (230139)
        You also have to consider how resilient such a system could be to tampering. If it relies on GPS (and I don't see how it wouldn't), then what will it do if I jam the GPS signal? Will the car know how to get off the road safely with the GPS data jammed? Can it still get to safety if I jam the signal near a busy highway and there are hundreds of cars trying to pull over at the same time?
        • by Dun Malg (230075)

          You also have to consider how resilient such a system could be to tampering. If it relies on GPS (and I don't see how it wouldn't), then what will it do if I jam the GPS signal? Will the car know how to get off the road safely with the GPS data jammed? Can it still get to safety if I jam the signal near a busy highway and there are hundreds of cars trying to pull over at the same time?

          Don't be daft. You're overthinking it. It certainly wouldn't use GPS for anything more than coarse navigation, as even an optimistic 2 meter accuracy is insufficient to keep you in your own lane. Maneuver will likely be managed with optical sensors. Is there a problem with people shining spotlights in each others eyes on the road today? Unlikely it will be a problem when it's robots driving either.

      • by Don_dumb (927108)

        The fact that a significant enough percentage of drivers really should NOT be driving would make this a great opportunity.
        For those who aren't aware Essex in the UK is synonymous with terrible drivers (it is the home of 'boy racers') so it is just a little ironic that their Uni is the one trying to find a replacement for human drivers.
        • by Dog-Cow (21281)
          You have no real idea what ironic means, do you? If Essex is the home of bad driving, it makes perfect sense for a nearby University to do research in replacing the drivers. It's not ironic in the least.
    • by binarybum (468664) on Thursday March 22, 2007 @08:33PM (#18452491) Homepage
      Persuading elderly drivers to give up their cars is difficult

          Have you ever really tried? Sure they get ornery and wave their canes around a bit, but most of them are fairly frail and the task can be completed with ease. Sometimes they're confused and just think you're a valet - these ones will hand you the keys with a smile!
    • by WillAffleckUW (858324) on Thursday March 22, 2007 @08:39PM (#18452553) Homepage Journal
      Persuading elderly drivers to give up their cars is difficult, and the baby boom generation is putting a lot of people in that situation in the next decade or two.

      I find backing over them works fairly well.
    • I would love to have a driverless car: let me get some work or reading done while lounging in the back seat (safer) of my car while it is driving me through the daily rush hour. Because I can get work done, I can either drive off later or am in less of a rush to get where I'm going. No more tedious trips of hours upon hours of driving.

      Lower insurance premiums - and if the car has an fender bender, I can point to the manufacturer and hopefully won't be branded as an unsafe driver for life if I didn't do th
      • Re: (Score:3, Insightful)

        by Ford Prefect (8777)

        I would love to have a driverless car: let me get some work or reading done while lounging in the back seat (safer) of my car while it is driving me through the daily rush hour. Because I can get work done, I can either drive off later or am in less of a rush to get where I'm going. No more tedious trips of hours upon hours of driving.

        Why not catch a train or bus to work?
        • Re: (Score:3, Insightful)

          by rolfwind (528248)
          Time to my daily grind: 40 minutes one way. Parking 3 minutes walk to destination. 43 minutes total.

          Bus: Have a stop locally - 5 minutes walk. Take bus to a central station - 1 hour 5 minutes. Take second bus, unknown wait, to destination - 40 more minutes. 10 minutes walk to destination. 1h55m minimum.

          No thanks.

          Train? None here. I don't live in the city.
          • by drinkypoo (153816)
            When I lived in San Francisco I had to take a bus, the muni train, and a bus to get to work if I didn't want to drive. Time to work in the car: twenty minutes or less including parking at the foot of Potrero Hill where there are far less spaces than cars in the neighborhood. Time to get there on public transit: At least an hour and a half. Usually more because the bus would rarely meet up with the MUNI in a timely fashion. I estimated at the time that it cost me about 25% more money in bus fare than it did
      • by mrbluze (1034940) on Thursday March 22, 2007 @09:18PM (#18452999) Journal

        Sitting in a car with my missus driving is much the same as being in a driverless car:

        1. Still get claw marks on all the passenger-side interior handles and the dashboard
        2. Still likely to hit every bird, squash every small furry animal on the road and drive over every cardboard box and bit of metal.
        3. Still get no response or admission of guilt when the car crashes

        Biggest difference is that the thing is more likely to know the way to someplace.

      • by drsquare (530038)

        No traffic tickets - the AI can go closer to the speed limit than I have the patience to
        So if you're forced to go at the speed limit, it would take much longer to get to your destination than with a normal car. I don't see how this is an advantage.
    • Persuading elderly drivers to give up their cars is difficult

      Just tell them how easy it will be to find the farmers market...
    • by suv4x4 (956391) on Thursday March 22, 2007 @08:43PM (#18452617)
      Seriously, this is a technology whose time has come. Persuading elderly drivers to give up their cars is difficult, and the baby boom generation is putting a lot of people in that situation in the next decade or two.

      Not just, consider accident caused by drunk drivers, by drivers fell asleep, careless drivers...

      But don't expect a smooth transition. An "AI" driver could silently save thousands of lives, but the first cases where the AI was the reason for an accident will cause major outcries.

      It's the nature of human beings to react like that.
      • by timeOday (582209)
        I don't think it's insurmountable. Air bags cause unnecessary death sometimes, but they're a big net gain and we keep them.

        I do think we'll see unmanned transport planes first, though. Flying is easy. There's less to crash into, you only land at a pre-set number of known locations, and planes can be much more expensive than cars to cover the costs of new technology.

        • by suv4x4 (956391)
          I don't think it's insurmountable. Air bags cause unnecessary death sometimes, but they're a big net gain and we keep them.

          I do think we'll see unmanned transport planes first, though. Flying is easy. There's less to crash into, you only land at a pre-set number of known locations, and planes can be much more expensive than cars to cover the costs of new technology.


          That's insightful, although I wonder if they will want to shift so much responsibilities for a so expensive machine onto AI for a plane. A pilot
    • The links go to an AI presentation of virtual cars and a news release saying there will be a competition without any details about the competition. Did I miss something? Is the only news that they have developed neural nets to drive a virtual car?

      The competition sounds like a manageable project for academics (versus the DARPA event).

      Is the competition still in the vapor-ware or maybe-someday stage?

      Anyone have a link (perhaps IEEE) that has details?
    • by 70Bang (805280)


      The issue of DARPA is still to be decided. There's a Grand Challenge 3 this fall, two years after #2 completed the desert challenge; i.e., they figured people would need two years for preparation. And that is for realistic traffic. Six hours, six miles...in Europe. There's a demo to be met by April 13. I'd be comfortable saying I've received 200 messages so far. They've been coming in pretty regularly since the May 1, '6 News Release (a two page PDF).


    • I don't think we're even remotely close to having vehicles that can be autonomous in all situations. There's certainly a solid case to be made for automatic driving on freeways and interstates. For one thing, widespread use of dynamic cruise control can significantly reduce traffic congestion by stopping the ripple effect caused by over braking.

      But urban settings with a lot of pedestrian traffic are a complete technical and legal nightmare. Then there's the issue of very poor quality roads or severe weather
    • Re: (Score:3, Funny)

      by NerveGas (168686)
      I just want it so I can sit in the rear seat and watch a movie, play video games, work, whatever. Hey, put some "limo-black" tint on the rear windows, recline the seats, and get jiggy while your car cruises down the highway. You can't beat that.
    • by CastrTroy (595695)
      I've always thought the whole driverless car idea was crazy due to the liability issues. Right now when somebody gets in a car crash, most of the time it's blamed on human error, and the car company is not at fault. When the car company is found at fault (Firestone tires?) they end up paying through the nose and lose a lot of money. Once you start making driverless cars, every accident becomes the fault of the car company. Not just fatal crashes, but all the other little bumps and bangs that happen. Wh
  • Oblig (Score:2, Funny)

    by commisaro (1007549)
    I for one welcome our new automated race-car overlords.
  • I recall the Forza 2 team commenting just recently that their AI drivers were being powered by neural networks which they'd managed to train to the point that they were actually using some extremely cool braking and steering behaviors that they had never been taught. This seems quite similar.
    • Re:Forza 2 (Score:5, Interesting)

      by jtogel (840879) <julian@togelius.com> on Thursday March 22, 2007 @08:55PM (#18452753) Homepage Journal
      I don't know much about the techniques underlying Forza 2, but I went over and talked to the guys who worked on Forza 1, and we compared our approaches. At least for the first game, what they are actually using is recorded trajectories on different track segments which are then spliced together at the junctions of segments, so as to create similar-looking behaviours on unseen tracks. The problem here is of course that the new tracks are constrained to being constructed out of the same segments as the driver has already been tested on - there is no generalization. The track designers for Forza simply had to live with this constraint.

      We have ourselves gotten player modelling working fine with evolutionary neural networks, which can generalize, but the Forza team didn't consider these techniques reliable and fast enough in time for the release of the original game. Maybe things have changed with Forza 2.

      There is some information on the Forza AI on http://research.microsoft.com/mlp/forza/ [microsoft.com], and our approach to modelling is described in http://julian.togelius.com/Togelius2006Making.pdf [togelius.com].

      Note that all this is about modelling behaviour, not about creating new behaviour from scratch; there are some papers on this on my website [togelius.com] as well.
  • http://rars.sourceforge.net/ [sourceforge.net]
    Anyone have first-hand experience of how that is coming along? Can you program these with neural nets also, or still "just" hand-coded? (My own experience is nigh on a decade old.)
    • Surpassed by TORCS (Score:2, Informative)

      by novocastrian (653554)
      TORCS [sf.net] is a more advanced racing simulation than Rars. Its held robot-programming contests for the last 3 years, with another about to start soon.

      There have been several robots that use various learning techniques, though none to my knowledge have been full-blown AI/neural net solutions. To be honest, I query the advantages of doing it that way. A robot that has code to plan a smooth & optimal path around the track & calculates braking and steering accordingly will do much better (initially at lea
  • Thats great and all, but will the AI-enabled cars also come with an afro wig and a black leather jacket? Oh, and they should probably be bulletproof.
  • The courses he uses remind me of courses from Super Off Road [wikipedia.org].
  • Traffic (Score:3, Interesting)

    by et764 (837202) on Thursday March 22, 2007 @08:58PM (#18452785)
    A few months ago I was thinking about doing something like this, but in heavy traffic situations. What if the course had way more cars than should ever actually fit, and the cars independently tried to minimize their travel time around the course. I wonder if the computer could get a better overall throughput than people seem to do on the crowded highways of, say, Seattle.
    • by Nethead (1563)
      I know that a computer could do better VOTING for traffic solutions than Seattle does. Can we say Monorail, and Viaduct? Maybe New Evergreen Point Floating Bridge?
  • by jtogel (840879) <julian@togelius.com> on Thursday March 22, 2007 @09:08PM (#18452883) Homepage Journal
    If anyone actually is interested in reading the papers discussing the experiments we did (many more than you see in the videos!), most of them are available on my website [togelius.com].

    Some of them are of course better than others. I can recommend this one [togelius.com], about evolving general and specific driving skills, this one [togelius.com] about co-evolution, this one [togelius.com] about different learning techniques, and this one [togelius.com] about modelling human driving and evolving tracks. There are several new ones, including one on physical cars, which are not on the website yet - mail me if you want a preprint!

    All this assuming that anyone actually reads academic papers... sometimes it seems that not even the guy who writes the paper actually reads it. (Not true in my case, of course!)
    • by bmajik (96670)
      I read the modeling human driving paper as race-driver instruction with real tracks and real human drivers is an interest of mine. I was expecting to see a discussion of the information processing problem, the acting-on-incomplete data, and so on, that must happen with a real human in a real car on a real course.

      The paper seems very game focused and the extrapolation to real driving seems a bit distant, but I concede not reading the other papers.

      One comment I have about your track modelling: all your track
  • If we start using driverless cars, the Blue Screen of Death will suddenly have a whole new meaning!
  • by RandomWordGenerator (813207) on Thursday March 22, 2007 @09:27PM (#18453073)
    The problem with driverless cars isn't the technology but insurance.
    Many manufacturers have been dissuaded from pursuing the technology and installing in their vehicles because in the case of any accident the corporation would be liable. Obviously the 'driver' wouldn't be at fault because they wouldn't be driving.
    No large corporation is going to put itself in line to pay out on every bump, scrape and minor slaying caused when their killer robo-cars Attack!
    • On the contrary, the problem is the technology. We simply cannot make complex, correct, software without huge expense. Even something as simple as automatic speed control can get screwed up. Example: The BMW's which spontaneously accelerated due to a software bug.
    • Re: (Score:3, Insightful)

      by Foerstner (931398)
      By that logic, automakers wouldn't ever introduce new technology.

      Power steering? What if the pump fails during a hard turn?
      Air bags? What if some idiot doesn't buckle up and gets killed by the bag?
      Seat belts? What if the latch weakens with age and breaks during the impact?
      Windshield wipers? What if they crap out in the middle of a heavy rainstorm?!

      Sooner or later the technology becomes mature enough that the benefits outweigh the risk of liability. At that point, the manufacturer slaps another disclaimer in
  • Oh great! (Score:5, Funny)

    by codemachine (245871) on Thursday March 22, 2007 @09:33PM (#18453129)
    It is bad enough seeing a steady stream of cars and SUVs with only one person in them streaming out of the downtown at rush hour. Now we're going to have cars out there that aren't even taking anyone anywhere.

    The environmentalists will not be happy with this development!
  • on a real track, and these algorithms wouldn't stand a chance. Racers know subtle moves and blatent moves that these systems will never be able to learn. Add the fact that real cheating and bending the rules has to occur under the nose of race officials, and that team cars run by algorithms would be banned from any racing venue for being dangerous morons within one or two races, and this would disappear faster than most vaporware.

    Implying that these cars could "drive themselves" in any meaningful or safe
    • by jtogel (840879)
      Hmm... why? Why would a machine learning systems never be able to learn such moves? And why wouldn't they be able to stick to the rules? Just curious.
    • Actually I think it would fascinating to pit humans against machines for racing. I suspect on a known track that you could make a machine very competitive indeed. Particularly on those stupifyingly boring oval tracks that Americans seems so fond of. Much higher tolerances to G Forces, no fatigue, and the ability to analyse every part of the previous lap would have to help.
      • Re: (Score:2, Interesting)

        by tarball (34682)
        Yeah, except the boring oval tracks, which I probably dislike more than you, would be the easiest place to kick the butt of a program controlled car. Because the program doesn't feel the dynamics of the air or the track like a human does.

        A boringly smooth road track with an entirely predictable car, like most F1 tracks and cars are becoming, would be the ideal combination for these algorithms. No one passes anyway, so maintaining position until a perfect pit stop occurs is the way to get ahead. Good pit
  • there are some things that i really would not want to have to write into the code for a driver less car, but that would need to be addressed. What happens if you are driving along a road and someone jumps out in front of you while you are passing a car going the opposite direction? Does the car swerve to the right to attempt to miss the person, and risk running itself into an object that could kill it's driver? Does it swerve to the left and hit the other car? Does it drive into the person? What about
    • by hazem (472289)
      It could be that every such scenario does not have to be programmed... but rather, a complex decision like that is programmed through some kind of decision logic that uses other smaller logic modules to handle the sub-parts of the decision.

      But if you give these cars the ability to communicate with each other and "smart roads", you might be able to end up with behaviors that are just not possible with current cars.

      Given your scenario, it maybe possible the car can slam to a complete stop - while communicatin
  • The article mentioned the cars getting stuck in the corner. This is a problem with the NN architecture used. Backing up requires a very different sort of behavior than normal driving, so you require a way for your architecture to keep track of a particular state, and change behavior as you progress through that state (you need to back up for a set amount of time, then go forward and change direction). This problem is made clearer when imagining the absurdity of trying to get a simple NN like this one to lea
  • Better Yet (Score:2, Informative)

    by Dean Hougen (970749)

    I'm all in favor of robot contests and all but more important, from my point of view, is the ability to share resources (such as test environments, robot chassis, sensors, vision-processing code, etc.) outside of the competition itself.

    The biggest unnecessary impediment to robotic research right now, as I see it, is the difficulty researchers have in making comparisons between systems. You demonstrate your racing code on your robot in your test environment. I demo my code on my bot on my test track. Th

    • by jtogel (840879)
      Thanks for the nice comments! It's all very free and open source, though I haven't gotten around to spelling it out explicitly or attaching any particular license to it. I too would really like to have a more sophisticated simulator to work with, but I have two really important requirements which all the alternatives I looked at so far have run afoul of:

      * The simulator should be 100% cross platform (I regulary use Ubuntu, Mac and Windows, and researchers who want to participate in the competition can well b
  • I thought this would be time based trials, but read this "while outwitting the opponent cars but to do so it needs to be smart, it needs adapt to the behaviour of the other cars as it drives." Great, I get to spend my time developing a driving robot just to have another robot freak out and slam my car into the wall. Haven't they heard of baby steps? Hopefully, they'll use time trials and a run with a remote controlled car to weed out the obviously not ready ones. Seriously, if they just race then a quick st
  • by Animats (122034) on Friday March 23, 2007 @12:08AM (#18454477) Homepage

    Notice that in all the examples, the road is much wider than the car. That's not by accident.

    Driving using reactive behaviors is easy if you have plenty of room. On narrow roads, though, those approaches fail. You have to look ahead. In fact, to drive in the real world, you need a controller that plots at least an S-curve ahead. Otherwise, you'll end up in a tight spot pointed in a direction that won't get you through.

    You don't necessarily have to "plan", in the AI sense, but you need a fairly good dynamics prediction capability, after which you can run a reactive controller on the prediction.

    We went through this with our DARPA Grand Challenge vehicle. We started out with a reactive planner, but it just couldn't deal with tight spots. Most of the other teams ended up with S-curve planners, too. The reason you need S-curves is that you need to be able to achieve both a desired position and direction at a point ahead of the vehicle. So you need a curve with at least two degrees of freedom.

    The predictor needs to know enough about the vehicle dynamics to make reasonable predictions. For example, predicted S-curves have to be built knowing how fast you can change the steering angle and how tightly you can turn given the current speed and ground bank.

    If you need to do this stuff, read up on adaptive model-based feedforward control. The idea is that you have a system that learns how the system behaves as the inputs change and builds a model. Inverting the model gives you a predictor. Given a predictor, you can control.

    A useful feature of that approach is that, while you're using one predictor, you can be training a better one safely. Predictors are trained by watching; they don't have to be in control. So you can start out with some dumb controller and work your way up to better ones, without crashing. This is probably how mammals learn motor skills.

    • by jtogel (840879) <julian@togelius.com> on Friday March 23, 2007 @01:03AM (#18454833) Homepage Journal
      This is an interesting argument, and yes, we are experimenting with predictive control and internal models as well (experiments running as we speak). But I think that the real power of predictive models only show when you have multiple agents involved. People often underestimate the power of reactive control just because they assume that humans can't tune them well enough. But evolution is not limited in that way, and can sometimes do things with reactive controllers you just wouldn't think possible. (Stefano Nolfi has done some thinking and experimenting on this, see for example his paper "Power and limits of reactive agents".)

      In the case of our (admittedly simple) model, we have a limited line of sight, and I think a good reactive controller can perform optimally (however you define that, often optimality is just another buzzword) given the limited sensor data. We did try evolving reactive control on much narrower tracks with good results - see for example our papers on track evolution. What the controller learns is often just to slow down when coming up to a narrow passage.
      • by Animats (122034)

        I read the paper and made a copy of the most difficult map, track #8. I'll try to convert that into a form the Overbot software can handle, and run it.

        That map, assuming the vehicle is 2m wide and 3m long, has a narrowest width of 4 meters, which is not all that tight. The simulated vehicles in the article seem to have a rather tight minimum turning radius. They do skid in turns; unclear if the controller is exploiting that behavior to tighten turns. What is the minimum turning radius of those vehicle

        • by jtogel (840879)
          That's interesting. I have to get back to you about the minimum turning radius once I get to my "work" computer (just woke up). I'd like to know about the results!
  • Those cars are definitely drifting! [wikipedia.org] In that first video, all four "wheels" are clearly going sideways at the same time.
  • Some posters have posited the "what if every car were an AI car" scenario. But the transformations all talk about changing our current cars into AI cars.

    But I'd like to propose a different slant. If every car is an AI car, then how will this differ significantly from a distributed form of public transportation? If you break it down, the daily commute is filled with SUVs and a lone driver, with the SUV remaining parked (taking up space) for the whole day. So what about "transportion as a service" here (A

  • This is great news for road safety - now we just need to eliminate passengers as well as pedestrians and other road users so we can finally avoid people getting hurt in traffic.
  • by 955301 (209856) on Friday March 23, 2007 @05:46AM (#18455965) Journal
    Does anyone else feel like automating our current transportation is insanity compared to building a new transportation system that actually lends itself to automation?

    Why are we trying so hard to make something designed to be operated by a human computerized so it stays on the road when we can make a road with rails on it?
  • Is justs loves hows peoples pluralizes thes words towards.

    --Richards
  • In the late 70s, I read a very good SF book, Man Plus [amazon.com], by Frederik Pohl. The story was situated in the late 1990s, and everyone commuted to work by getting into the car, telling the system where to go, and settling back to read the news or watch the Today show.

    Sigh.

Never put off till run-time what you can do at compile-time. -- D. Gries

Working...