Traffic Control of the Future

petra13 writes "A high point of the Autonomous Agents and Multi Agent Systems conference this past week was Kurt Dresner and Peter Stone's paper 'Multiagent Traffic Management: A Reservation-Based Intersection Control Mechanism.' They designed an automated system where cars reserve a time to pass through an intersection as they approach it and are then sped up or slowed down to ensure their arrival at exactly the right time. This allows traffic to enter the intersection from all directions simultaneously, eliminating the need for traffic lights and considerably reducing delays caused by stopping traffic. On their website, you can find Java applet simulations to illustrate the system. Especially impressive looking is the six lanes of heavy traffic in all directions simulation. I would love to see this in real life (from a safe distance of course)."

Comments

What about.....

[BWJones]

I have to wonder if these simulations or plans account for bicycles or pedestrians?

Re:What about.....

[transient]

Doesn't look like it. Nor do they account for, as someone else pointed out, turning. Even more importantly, at no point during the simulation does a dog run out into the street, a hubcap fall off, or a tire blow out. At the end of their report, the authors mention that humans probably aren't capable of driving within the tolerances required by their system, but they never consider distress/emergency situations.

But, in spite of its limitations, this is an impressive technique and I'm sure that someone will be able to build on it.

Re:What about.....

[pHatidic]

You're taking this too literally. It's really just a metaphor. Let's say to the north of the intersection is the United States. To the south is Iraq. To the west is our ally Great Britain and to the right is terrorist Michael Moore. Does this make any sense to you? Of course it doesn't.

Now these cars are like diplomats all trying to make peace with eachother. If this doesn't make sense it's because it's complete nonsense.

Next we have the pedestrians and bicycles as mentioned in your post. Let these represent terrorists and weapons of mass destruction. If you're confused then clearly its because this entire situation makes no sense.

To conclude while you may think this simple simulation is designed to control cars, it's really something much larger designed to make the world a more friendly place. And if this doesn't make sense to you, you must buy the product.

In all seriousness though, this has applications far beyond cars, such as increasing the efficiency at factories with conveyor belts and robots, routing data over the internet, more efficient combustion engines, etc. While it would be ideal to evolve the perfect solutions using genetic algorithms, this is a good fix in a less than perfect world.

Re:What about.....

[bizpile]

I would assume that they would use off-ramp type of turn lane and just adjust the traffic the same way for the cars entering the new direction of travel as they do for the intersections. No one says you have to make only 90deg. turns at the intersection (unless of course you plan on installing this system at existing intersections with no road modification). Howev,er there is still the problem of dogs, stalls, breakdowns and the like.

Scary!

[Sgs-Cruz]

That six-lane each way simulation is awesome, but they had better modify the thing before actually rolling it out so that the cars don't go so damn close to each other. Computer control or not, I don't want another guy's car 7" from my bumper at 70 km/h...

Um

[Apreche]

That simulation was pretty impressive when I looked at it. Until I realized something. None of the cars are turning left or right. Theories and math and simulations work great and are often impressive. But real world factors will almost always mess them up.

So one day when there is a way to get from everywhere on earth to every other place on earth without turning left or right give me a call. Until then, let's stop and let people turn left.

Re:Um

[big tex]

The rotary, in it's big-ass Massachusetts form, is one of the most interesting traffic control devices - part fun, part terror, with all of the lane changing and bluffing that Massachusetts is famous for, WITHOUT LINES.

The rotary is a last choice for traffic engineers without the sack to design a 8-way free for all (like Kelly Square in Worcester).

Great!!

[SeaDour]

Now all we have to do is convince the general population that their cars are safe in the autonomous control of computers rather than their own two hands. Sure, *I* know that having automobiles controlled by a sophisticated traffic network would be safer and more efficient -- I read Slashdot, after all -- but I doubt very many people in this country would be so thrilled about the idea of giving up their grip on the steering wheel.

Security

[Stile 65]

I know people have already commented on the cars not changing lanes or turning, and the possibility of breakdown, but this system would be easy to exploit maliciously. If an agent didn't slow down the car, or misreported its speed/location, that could make for a lot of... er... amusement?

Standard vehicles in controlled areas

[kindofblue]

This may not be practical for general traffic, but I could see it being very useful for places where one can control a fleet of individual cooperative vehicles. This could be on a factory floor with robotic delivery vehicles (e.g. in an Amazon-type warehouse), baggage haulers on airport runways, at airports with the airplanes themselves to get to runways, construction sites with heavy machinery, companies with fleets of similar vehicles like at UPS, FedEx, Walmart, military sites with tanks and humvees (using encrypted channels of course), etc.

There are lots of places where you have a need for traffic control with big or many vehicles, in tight spaces. Such resource allocation is a huge part of many problems. That's where they should market this first, I think.

Chicken and egg...

[Faies]

Insurance companies will want real proof that such a system will be stable and as secure as today's intersections before even half-considering it.

Such proof for this system will require that ALL cars in the area be equipped with such systems and an equally large number of intersections handled.

This roadblock to development was what happened to a demo for a system in which cars controlled by computers would follow magnets in a road and drive within 1m of other cars. That was a couple of years back in San Diego.

If cars are going to be automated someday, we'll need to find some compromise which does not require implementation for all vehicles on a road- i.e. a lane for truckers on long stretches of highway.

That's just my 2 cents. Something like this would be really cool should we ever get to this point....or we could just get flying cars and fly over :)

Custom sim shows it better

[t_allardyce]

Stick the granularity on 3 and try:
N: 2 - .04
E: 4 - 1
S: 2 - .06
W: 4 - 0.1

you can see the system cue the cars on the east -> west road up and create little 'gaps' in the flow across all lanes that sync up with the north/south cars as they cross, nice to look at but it really needs turning and lane crossing, on the low granularity the cars get more clearence which is abit more realistic :P

The 6 lane version as a great theme park ride

[sprior]

Imagine a theme park doing the 6 lane version as a futuristic thrill ride. You'd have to hose off the seats after every run...

Car AI of the future, to driver:

[SpotBug]

"Approaching intersection, please close eyes."

This was solved centuries ago

[Stubby]

if they are not going to consider turning lanes, there is a Much simpiler solution. A Bridge. If every vehicle is only going straight, an elevated bridge is the solution.

the other problem with this solution is average car length. An accepted Average car length is 19 ft. But the first semi truck that goes through this intersection gets t-boned.

This is barely a concept techonology. Every one thinks they are a Transportation Engineer because they drive cars, the problem is always much more complex.

Network management is not a solution to transportion problems.

Hey

[mukund]

So where's the Frog?

Re:An alternative mechanism

[s7uar7]

The problem with roundabouts (and I'm from the UK by the way), is that there has to be a roughly equal traffic flow from each entry point, otherwise the system falls down. If the majority of traffic is following a particular route, say going straight across, and there is very little traffic they have to give way to (as happens during rush hour), then it's almost impossible to join if they have right of way. The only solution is to start putting traffic lights up on them, and that defeats the whole object.

Bad Science

[ccoakley]

Have you ever tried to program a traffic simulation? There are few simulations more trivial, so don't be impressed.

Second, traffic simulations based on human behavior are always post hoc analysis. Twiddle the parameters until it looks right, then make up the behavior that fits the parameters. If you've ever had a chance to play with one, they are a lot of fun. Often the whole simulation falls apart with less than a 5 percent change in some parameters.

Actually, this is true of almost all behavioral modelling. If you've ever done any reading in modelling of software systems, you know how hard that can be (try proving the safety of critical sections in a multithreaded system). Behavioral modelling has all of the great concurrency of software modelling with less determinism (or at least it should...). What makes anyone trust behavioral modelling is beyond me.

As a side note, many things in the real world are based on this kind of crappy science all the time. Check out the San Diego freeway system. The I5 805 merge was just recently redone to improve traffic flow. It failed miserably. Staffing levels on military vessels are done by models. The ships are always understaffed initially until trial and error fixes them.

Unfortunately, people think that computer simulations can solve all problems, even when there is no theoretical reason to believe that the model will even approximate reality.

Two Phases

[DumbSwede]

I've given this some thought over the years, for instance when sitting at an intersection when a light is red and no other traffic. I think what is needed is a 2 phase implementation. First mandate that all cars will be equipped with some sort of transponder that traffic control systems can read (robustly). In phase one, new cars would be mandated to have such equipment by say 2008, used cars by 2010. The benefit during the transition period, traffic lights that optimize for transponder cars, and decrease their average wait time. Phase 2 mandate new cars be drivable by a combination of remote and autonomous control by 2015, used cars to be upgraded by 2020. Advantage: several highways allow hands off driving for upgraded cars in transition period. Mandated transponders on older cars alert remote controlled cars to a hazard in the area.

Starting 2020 driving on a highway or in most city-centers without being on autonomous control would be a crime. Starting 2010 driving a vehicle not sending valid transponder signals would be a crime.

Of course the transponder signal will drive privacy advocates nuts, but I don't think you can get to a robust autonomous driving system without it. I suspect transponders are coming anyway for other reasons, so best to make lemonade out of lemons. Yes you will be taxed for in city driving -- sorry, it's coming anyway. Yes cops will know where your car was in any 48-hour period -- get over it. Yes you will no longer be able to speed - who cares as long as I can blog /. while I ride, and my average arrival time is lower due to everyone optimizing the available traffic ways.

As to unexpected hazards like pedestrians, cars will have built in radar (already practical) that reacts much quicker than even the most alert driver. Drivers will have to be insulated legally from any liability for hitting a pedestrian when said pedestrian jaywalks in an autonomous driving zone, as will the autonomous driving system manufactures.

Will children and pets be hit by robot cars? Yes, but congress will have to mandate legal protections as long as aggregate fatalities fall. Gross negligence in equipment manufacture could still be prosecuted, but any system certified by government for use should be immune from legal persecution as long as the accident falls outside of the parameters the government mandates it be able to handle. The legal challenges are the true roadblock, even if aggregate safety is improved.

While we're at it, lets lower the sound level of emergency vehicles, but have a signal override your loud radio to inform you that there is an emergency vehicle approaching. Same for trains. This could lead to some additional pedestrian accidents, but not if pedestrians are trained to use existing traffic systems better. Children could (should?) be equipped with transponders to alert the system to increase safety margins (i.e. slowdown). Of course transponders on children is another hot button topic, but I'm not referring to some 24/7 implant, but a device they carry when in downtown areas, same for the handicapped and the elderly, even your average citizen if they wish to enhance their own safety.

Transponder abuse must be a severely prosecuted crime for obvious reasons, both for sending false signals or for stalking individuals by tracking their signals.

You can fight these changes, which I believe will come, or you can live in a less technologically advanced nation. Other countries come to mind: "autonomous driving mandated ... in Japan" (ongoing /. joke). We will not have robot servants, we will not have autonomous highways, we will not have other unthought of applications of technology if we are not willing to allow our physical presence to be tracked in real space (and this means everybody). How that information is used and stored is where we must concentrate or efforts in the privacy fight.

Granted sufficiently intelligent systems would not need transponders and