Computer Will Take On Formula 1 Champion 299
Jacky Baltes writes: "Thought that Deep Thought vs. Kasparov was a big deal. I am part of a research group that attempts to beat the world champion in Formula 1.
The goal of the Man v. Machine Challenge is to design and implement a
robotic system that can drive a F1 car faster than the current world champion.
You can have a look at the progress at the Man v. Machine Challenge Web site . We will had some more technical details about our control system design, data fusion, and car model to the site later.
So Michael, hold on to your head.
Jacky Baltes"
Nice! (Score:1)
I am joe american
This whole saga kinda reminds us all of the whole Hyperion thing (Jim Clark's 200 foot sailboat, sailed by 25 sgi workstations) - now that's a project.
but will it.. (Score:5)
Is this to be *in* a race? (Score:3)
It's not clear from the web site if this robotic car is to actually compete in real race conditions, or if they plan some farce where it's just doing speed laps solo? The first is a real challange, while the latter is a farce. It's a factory robot following a white line - only faster.
Pretty cool... (Score:3)
Ciao.
PhatKat
Challenge? (Score:2)
mostly a test of agility and quick thinking isn't it? A computer with a good understanding of physics should be able to determine the perfect speeds and angles as well as determine when the tires are too bald and extrapolate when more gas is needed etc...
Deep blue actually had to outhink a human(If you can call Kasparov human:) ) without just simply being faster. Even deep blue couldn't know all the possible chess moves. Although quick thinking was certainly a part of it, it seems more than that.
Not to knock what you're doing. The technology just in the robotics to controll the car must be amazing, but it might be better to compare the test to the first cars that could outrun a horse rather than Deep blue.
Deep Blue (Score:1)
Good. (Score:2)
Death (Score:2)
Re:Deep Blue (Score:1)
Imagine... (Score:2)
Sorry had to say it, Imagine a Beowulf Cluster of those...
This seems to me like the first steps of an AI which could be dangerous. Don't get me wrong, while creating an AI is a great leap for mankind could it also be the downfall of mankind? Also Will this "robot" be driving against one person or will it be driving in a larger race? I think for it to be a true test of man vs. machine it should be in a real race, having to deal with multiple opponents, as men are forced to do.
When a man sits with a pretty girl for an hour, it seems like a minute. But let him sit on a hot stove for a minute-- and it's longer than any hour. That's relativity.
-- Albert Einstein
Deep Thought (Score:1)
RARS (Score:2)
Re:Is this to be *in* a race? (Score:5)
one advantage, that would be difficult to resolve,
and that would be that it'd be simply unafraid
of death. And, that if you could send a computer
car, barreling through a race, slightly clueless,
but unconcerned about it's own mortality, then
I think the human racers would just have to get
out of the way.
With live drivers, isn't there a slight matter
of 'how much do you want to win' versus, 'how
close are you willing to go to the edge' that
doesn't quite translate when machines are involved.
Re:Challenge? (Score:1)
For this to be truly impressive, it needs to be ran under actual racing conditions, i.e. other drivers.
I don't want to seem down on it, this is really cool step to having auto-drive cars.
yep, can't wait till I have to liscense my car from Microsoft...
Re:Challenge? (Score:1)
Oh yeah, nothing to it. The rest is all just typing.
Except of course for the teensy little problem of figuring out where the other cars are and what they're doing.
Pete
Re:Deep Thought (Score:1)
http://www -pe rsonal.umd.umich.edu/~nhughes/htmldocs/deepthough
J
Time race or head-to-head? (Score:2)
Is the race for the best time or is it a head-to-head race? Can't tell since the web site isn't responding.
If the later, I wouldn't want to be the human racer. The current state of autonomous computer controlled driving is pretty lousy. One miscalculation could result in an accident. Also, human drivers are a little more cautious with risky moves since the consequences could mean death or injury. Will this computer controlled driver be cautious about the human life of the other driver when considering grazing the other car in passing?
Great (Score:1)
Re:Challenge? (Score:2)
Moreover, Deep Blue had time to overcome any mistakes he might have made.
On the other hand, this computer will need to integrate so many different data feeds in real time that producing a coherent model of a what's going on would be difficult enough. Being able to analyze that data and in *milliseconds* decide on a course of action
Well, I'm doubtful. Plus the result of any mistake would likely be severe.
Want to make $$$$ really quick? It's easy:
1. Hold down the Shift key.
code (Score:2)
I'm surprised... (Score:5)
c'mon, people.
J
Uhh Race condition? (Score:3)
Really though F1 cars are fast and dangerous, I really hope they do a good job in the design.
For instance what is going to happen if a tire blows out, sensor/circuit fails.
They might do okay, but I would be worried about low cost implementations coming onto the road too soon.
Re:Challenge? (Score:3)
It's one thing to design a computer that can outthink an opponent by brute force and given a reasonable amount of time. It's quite another that can adapt to the immensely varying conditions of a racecar/track and make split-second decisions - any of which can send you careening off the course in a nasty fireball.
Oh, and fit in an F1 racecar. Have you seen the size of these things? They're go-karts!
OTOH, have you seen the size of Deep Blue?
Methinks this is a publicity stunt. It really makes you wonder when on the first page they're talking about the publicity generated by Deep Blue and subsequent profits. And then they go on to recruit investors.
--
Re:Is this to be *in* a race? (Score:2)
I very much doubt whether any driver would be prepared to compete with a robotic car under race conditions. Would you?
Merchandising... (Score:2)
I can see it now, AI-Andi the T-Shirt, AI-Andi the matched luggage, AI-Andi the toilet paper, and finally AI-Andi the flame thrower.
We all know what is going to happen... (Score:4)
The human driver is going to win, but after he wins he is going to stumble out of his car, sweating, and die of exhaustion.
Ah the computer (Score:1)
Deep BLUE (not "Deep Thought") (Score:5)
They fed the program Kasparov's entire game history while keeping its game history secret from Kasparov. Normally in competitive chess you are allowed to study your opponents past games in order to learn what tactics they are likely to use. In this case, Kasparov wasn't allowed to do that. The fact that he went ahead with the game anyway was probably due to overconfidence on his part.
The folks at IBM seemed to realize that they won merely because of the setup, and thus when challenged for a rematch by Kasparov, they said they weren't interested, because they had "done everything they set out to do". (Personally, I think they were scared they would loose in a fair match.)
Kasparov has stated publicly that if the "Deep Blue" team actually abided by the rules of competitive chess, he will "tear [Deep Blue] to pieces". They have so far declined.
That said, even if the machine were able to beat the best human player in a fair match, it still would not be that remarkable, because computer chess programs are still limited to the "brute force" approach, where they pick their next move by simply searching as big an area of the total possible game tree as possible. The human mind does it differently, only examining at most a dozen or so possible moves before deciding. Ho the brain can pick such strategic moves without searching a significant portion of the total possible game tree is still one of the great mysteries of cognitive science.
A Beowulf cluster of Pandora's Boxen (Score:1)
Either they don't know the meaning of "Pandora's Box", or the reports I read about WinCE to be used in cars were true. Oh, the humanity!
.-.
Not a hope (Score:5)
Consider chess: you have a vast archive of previous games, a relatively simple domain, the ability to test millions of boards a second, almost free live testing, and almost no financial penalty for mistakes. Contrast F1 racing: no archive, complex domain, almost no simulation ability, real testing costs $1000/hr, the mistake penalty is $100,000.
This is either hopelessly naive or a scam: after three years, you might get an AI around the track at 100MPH. Judging from the website, it's a scam: they talk about all the great value of the webhits and PR, ask for sponsors, etc. There is almost no info on the AI approach, etc.
Looks like nothing but a money sink to me.
Re:Deep BLUE (not "Deep Thought") (Score:1)
Oops, I meant "how" not "ho".
Re:Challenge? (Score:1)
It's FAR from just plotting the best-speed line around the course. A racetrack is a VERY dynamic environment. Sounds like a worthy challenge indeed!
suggestion (Score:5)
The research team should contact the Knight Industries or the Foundation for Law and Government, and hire Bonnie as soon as possible.
(Yes, I read this post and thought, "Jesus Christ, make a Knight Rider reference as soon as possible." May others come and do it better.)
I could see this happening... (Score:3)
We may never see a robot piloted race car on the same track as the human driven cars, but I could see competing robots racing against each other. Then, it becomes more a matter of which team has the best programmers, as well as the best pit crew, etc.
Re:code (Score:2)
A good control system might even be able to beat a good portion of the field in NASCAR and yet it stands no chance in Formula 1.
It's one thing to calculate the ideal trajectory through a racetrack, it's quite another to account for MacLaren's pit strategy and the slight drizzle that's beginning to fall while you're on used-up grooved tires and running the fastest laps of the race. (Which, incidentally is what Michael Schumacher did about two weeks ago in Japan to clinch the F1 World Championship).
--
cool (Score:5)
Re:Not a hope (Score:3)
Deep Blue, not Deep Thought (Score:2)
Deep Blue is the name of the IBM machine that beat Kasparov the second time they played.
Solid state gyroscopes (Score:3)
On a semi-related subject...
Does anyone know anything about solid state gyroscopes? I read about a gyro once that worked using a length of fiber optic cable wound into a loop. You passed a laser through a splitter, one beam down the cable, and then both beams hitting a light sensor. When you spun the loop, it would cause the interference pattern to change, thus measuring rotation. The dynamic range of its operation was astounding, like from 1000RPM down to .0001 RPM or something crazy.
From a project like this to succeed, I would imagine you would need something like this that could withstand the G forces while giving you extremely accurate results.
It seemed so simple that I figured they would have taken over the world by now with a million uses, but I haven't heard anything since. Anyone know anything?
--
FOOSBALL Playing Robot!!! (Score:2)
I'd pay good money if some robotics genius could invent a machine that I could hook up to a standard Tornado foosball table that could beat me in Foosball. I'll pitch in some starter money if anyone cares to help on starting a challenge for a FOOSBALL ROBOT vs MAN contest.
Re:Not a hope (Score:2)
I don't agree with you there.
While I don't have any links handy, there have been computers capable of driving cars in controlled environments for decades. Relatively recently, I have even seen demonstrated (on tv) a computer controlled car navigating through traffic (there was of course a human driver ready to take over in case of any mishaps).
So, computers operating cars, especially in controlled environments, isn't that big of deal. There are teams today, I'm sure, capable of hooking up a computer to an F1 car and making it drive around a track. No big deal.
I don't think anyone has had a computer drive a car hundreds of MPH. But I don't think there is that much of a difference between having a computer drive a car at 20 MPH or 200 MPH, as long as you have fast enough processors.
These kinds of challenges are silly... (Score:3)
It's not really about beating the human opponent - it's about making a bigger, nastier computer. The human is just a benchmark, and not a very good one at that because we tent to be pretty inconsistent.
The Deep Blue-Kasparov fight was lost to begin with because Deep Blue could see a dozen or so moves ahead for any given board configuration, elimiate the ones that it was programmed to think unlikely and then pick the one that left it in the best situation given a set of rules. People don't do that, at least not on the scale that a computer can, not to mention the mistakes we make, so Kasparov was doomed to loose eventually, if not to Deep Blue then to Really Deep Blue. It was all about how quickly and how well the computer could "solve" the given board configuration.
This race is no different. It will be a lot more challenging because the inputs are infinitely more complex than in chess, and the proper course of action is sometimes not clearly defined, but it will just be a horribly complex formula of some sort that tells the car how fast to go. With other opponents on the track, the level of complexity goes up, but it's still just a formula.
Me.Speed = NewSpeed ( frTireTemp(), flTireTemp(), rrTireTemp(), rlTireTemp(), frTirePSI(),... )
What I'd like to see is Deep Blue explain why the chicken crossed the road or what's the ultimate question to the ultimate answer, or to just drink 4 pints of beer and try to pick up...
----------
Re:Racing the bot (Score:2)
No, but perhaps against Schumacher, Häkkinen or Villeneuve?
This is simple... (Score:2)
How? By teaming up. They are better equipped to handle the tiny calibrations in track condition in order to maintain a constant speed.
All the robots would have to do is to get 3 or 4 robot cars to surround a human driver on 3 sides, then slowly force him into the wall. Repeat x # of human drivers.
Of course, it would be more amusing if the robots just followed a hive mentality. Then they could just assign one robot car as the "Queen" and have all of the "workers" suicide into human cars. At a cost of 1 robot per 1 human, the machines would see that as a positive math situation. And they could probably also engineer situations to take out multiple humans with just one robot car.
Now THAT would be good entertainment...
Re:Not a hope (Score:2)
Driving at 30 mph (e.g. in a Hans Moravec vehicle) allows you to ignore the real issues of F1 racing: skids and slides, engine overpressure, overheated brake response, body torque effects, lift and drag forces, etc. Races are won and lost because the drivers are pushing to the very edge of performance.
The interactions of these non-linear effects is what makes simulation hard... you really can't train an AI to optimize times unless you have gigantic datasets from which to produce good models. Watch tapes of Indy 500 races: cars break traction and do 360 spins AND RECOVER! If your AI hasn't done that 20 times (in the real world, with a 180mph effective wind,) it probably wouldn't recover.
Re:Is this to be *in* a race? (Score:2)
I agree that driving a race car fast is a complex and difficult skill (a couple of laps in a go-kart can show you that), but it doesn't mean that computers can't be programmed to do most of them, particularly those that don't involve other drivers.
What if the car kills someone? (Score:5)
But a computer has no such fear. It makes decisions based on programming. So let's say that it cuts too close to another car for whatever reason, and in the collision the driver of the other car dies. Is the programmer liable? After all, he is the one who effectively made the decision to cut that close to the other car. But it doesn't affect him negatively because he was never at risk. So someone is going to sue him, saying that he was careless because he was never at risk.
I wouldn't touch this project with a 10-foot pole. If this car ever drives on a real track, it's going to end badly.
--
What *are* the proposed rules, anyway. (Score:5)
Same FIA Formula 1 car for both operators
Computer must mechanically operate the same controls used by the human;
Computer must fit in the same space as the human, including power source.
Computer can have no electrical connection to vehicle for power or sensors; all its sensors must be self contained, and have no physical extension beyond what is allowed the human (no camera through the floor to follow the line :-)
Computer can have as many hands, legs, arms and eyes as it likes
Computer gets human equivalent sensors only - visible light vision and accelerometers; no radar, sonar, or active illumination allowed.
Computer controlled car must meet same weight requirements as the human/car combination
I won't demand race/traffic interactions. Solo qualification laps will suffice. Even under these conditions, I'll take the human for ten years easily, and probably twenty years.
I don't think it's an "AI" problem as much as a robotics, sensor, and machine vision problem. I don't think there's been so much progress in the last 20 years that it's feasible.
Though I sure Frank Williams and Patrick Head would sign it up as soon as it was available.
-dB
Re:Solid state gyroscopes (Score:3)
You're referring to fiber optic gyros. My understanding is that they look at the interference pattern of light beems traveling in opposite directions arround a ring and you can easily figure out how fast it's rotating.
Ring laser gyros are a similar technology. These may be based on dopler shift. I'm not too sure about how these work.
There are also quartz oscilating gyroscopes. I believe Cadilac uses these as yaw rate sensors in thier traction control systems. Baically, you use the piezoelectric effect to drive oscilations in one direction. The coreolis effect will cause oscilations in a second deirection if the device is rotated.
I worked with silicon oscilating gyroscopes last Summer. They are similar to quartz olscilating gyros, except that electical attraction is used in driving the oscilations. There are a lot of really cool details that go into designing these things. Unfortunately, my NDA keeps me from saying much more. Work with this stuff if you get the chance. A lot of really cool engineering goes into them, IMHO.
Pendular integrating gyroscopic accelerometers are another very interesting sensor. The Germans used them in thier V2 rockets in order to kill the engine at a specified velocity (this is where the integrating characteristic of the acceleromiter pays off). AFAIK, all US strategic missles use PIGAs.
Karl
I'm a slacker? You're the one who waited until now to just sit arround.
Re:Is this to be *in* a race? (Score:5)
It's a measure of how far we've come that we can actually approach discussing the real-world application of Asimov's "Three Laws of Robotics".
Isaac Asimov's "Three Laws of Robotics"
Clearly, this is a case of the First Law overriding the Third Law. The reasonable thing would be to not try to win the race. (OK, so sue me. I was a SF geek long before I ever touched a computer.)
Will the computer need to take a piss? (Score:2)
Computers don't get tired, they don't get thirsty, and they don't have to urinate so it's hardly a fair challenge.
And as soon as cars stopped crashing... (Score:2)
On a side note, remote controlled cars, without the fear of the driver losing his life, might be something else entirely. I'd love to see an Indy car throw a piston on the straightaway because the driver was trying to push it to 250mph!
What about the human driver? (Score:2)
Second thought, I wonder why they chose F1? It wasn't that long ago that the governing body of F1 started being more strict on what kinds of electronics could be in the cars. Someone said (can't recall who) something about the cars almost being smart enough to drive themselves. If they were truly out to show that the computer can do it better, they should put it in a World of Outlaws car (struggle to go straight, let go to go around the turn, sideways). Or how about Motorcross (the old kind, where you weren't allowed to put your feet down)? Anybody watched "On Any Sunday"? Let's see a robot try to put a motorcycle over a 30-ish inch log laying across the trail, and then make the 90 degree turn right after the log... Most people can't do that..
Del
Re:What if the car kills someone? (Score:3)
There are always worse case scenarios for things...computers will fail somewhere, and people can die because of it. It's part of life. The only difference here is that it is part of a (somewhat) frivolous pursuit.
The best analogy would be to bull fighting or the rodeo. Does an animals handler blame himself when an animal kills someone? Well, he might, but he knows that feeding an animal doesn't make him responsible for the animal killing a person in a game where death is a risk inherent in the game.
Re:Is this to be *in* a race? (Score:2)
Just think of the way our lives will be lived when we DO have computers and robots that are up to par with Asimov's!!!
Too late... (Score:2)
Pick a less expensive class first (Score:3)
The nice thing about Formula ford is that there are large numbers of near-identical cars available off-the-shelf for a realistic pricetag, yet the skills required to drive a formula ford well are very, very similar to an F1 car.
This smells fishy... (Score:2)
- Note that the first items in their menu, and a large portion of the site, are about sponsorship, how big of an opportunity for advertising this is, etc. etc. I've never heard of a research project with a "Supporters' club".
- As has been mentioned, it wasn't Deep Thought that "beat" Kasparov (it's argued that it was hardly a fair fight), it was Deep Blue. Methinks someone who was studying AI techniques and relevant prior AI work would know that.
- The few technical parts read like a sophomore year computer engineering project proposal. high on fluff, low on details.
- Nowhere does it give any details of what this challenge really is. Is it just negotiating a car around an oval track at high speed? Is it a real race with other drivers? The real goal is unclear.
I think it's a neat idea and if it's for real, hey, I applaud them. Personally, I take it with a grain of salt the size of Texas. Sounds like someone trying to grab attention, maybe go IPO, get-rich-quick. The whole thing sounds like a sales pitch, and I'm not buying.Re:What *are* the proposed rules, anyway. (Score:2)
Personally, the task of "driving an F1 car" is so much down to definitions of "driving" to make the problem not very appealing.
And I'm sure Bernie Eccelstone would be trying to figure out how to get a cut of the robot's salary :)
Re:Deep BLUE (not "Deep Thought") (Score:5)
As for Kasparov... you mean Kasparov had to publish all of his private practice sessions and give them to IBM? Nope... let's put it this way... all of Kasparov's public games were known. All of Deep Blue's public games were known. What they did to practice for the event was unknown. Where is the problem? If I have a game with Kasparov and I am unrated, just joined FIDE and have no public games... and win (it's possible!!!) does that mean I didn't deserve to win? Personally I think Kasparov did not win because he tried to out think Deep Blue and its programmers... kind of like reverse-reverse psychology. He did not play like he would with a human opponent (but then most people realize you often have to play differently with a computer).
Now I absolutely agree that Deep Blue is a nearly worthless effort if their only goal was to beat Kasparov. It has no tact and is a brute force approach to a elegant game. The human mind such as Kasparov's is tuned to such precision that research into how the brain learns I believe is many times more important than trying to find the best way to brute force a game. Uh... but then I supposed the brain is itself a sort of brute-force mechanism with 100 billions neurons. Who knows if the development of large scale parallel computation systems like Deep Blue will eventually lead to developments as inredible as the brain.
Re:Is this to be *in* a race? (Score:2)
You, presumably, are also aware that road car ABS and traction control devices are going to be biased towards "safety" rather than getting the absolute most out of the car.
You should also know that this kind of gear was allowed in F1 up until about 1991 - the Lotus and Williams of that era had traction control, ABS, active suspension - frankly, from a technical point of view, those cars were far more interesting than the F1 cars of today. Why was it banned? For sure it wasn't banned because it made the cars slower. . . BTW, rumours persist that Ferrari has figured out a way to make the engine management system act as a traction control device on their current F1 car. I wonder why they'd do that?
For the record, the 500cc GP bikes also use a traction control system on wet days.
Re:Zero slippage != fastest lap. (Score:2)
Re:What if the car kills someone? (Score:2)
Sure races are dangerous and this is a silly competition because somehow, somewhere someone let out the man vs. machine meme and it isn't going away. I'd much rather see more socially-friendly projects like ARGO than publicity-friendly crap like this.
Oh man who takes this page seriously its starts off with the words, "The Vision..." Not to mention this quote:
Formula One alone has 40-billion-plus television viewers annually.
That must include all the extraterrestial fans in our system. Could be worse they could be watching the 700 club.
Re:Deep BLUE (not "Deep Thought") (Score:4)
Deep Blue was a machine optimised for graph searches. Now, given this, Kasperov claims that there may have been a human component in his match with Deep Blue. According to him, he claims that if a decent human pruned some of the search trees for Deep Blue first, then DB would have no problems performing like a world-class chess player. Something to think about....
--
Re:Challenge? (Score:2)
Start with racing simulator computer games. How much computing power actually is used to run the physics engine? How much goes to the graphics. Now remove graphics. Now consider what the engine is modeling. Probably the game was designed to calculate 10, 20 cars all using the same physics model. Now remove all but two cars. Now consider the hardware its running on. PC games simply never come close to the limits of the system with opimal code because the game has to function on so many configurations that many optimizations get left out. This program can run to the limit.
Consider the calculations per second necessary in a game. I'll say 30 to 60. Lets say this system will do 1000. Remember however that the X-29, the first forward-sweeping winged plane to exceed Mach 1 had to be flown with a computer interpreting and actualizing the pilots commands due to the inherent instability of a forward-sweeping wing. Now how many time a second did the wonder adjust? The computer adjusted the plane only 40 times per second. How many times per second is really necessary for this race? 1000 perhaps since its a nice big round number with no real logic behind its choosing. I dare say there will be negligible difference at 500 adjustments per second.
Obviously the physics model of a racing sim isn't as good as it need to be. Already modeled however are the most of the car and its connection to the road. Gravity and most of the laws of physics exist. What is missing? Probably the effects of wind, random uneveness in pavement, fault tolerances in general, AI to deal with real loss of traction, tire wear, road conditions...I know I'm forgetting some other things.
My conclusion is: If three years ago the best computer available ran 333MHz, three years from now 4GHz may well be reality. If the computer doesn't have to worry about graphics and 18 other cars, while the code has been written down to the metal, there is an excellent chance an AI car can handle 200 Mph with more aplomb than any of us can at 60.
Re:This smells fishy... (Score:4)
I can't believe nobody else is really seeing this. Read through their site (don't worry, there isn't much actual information
They have a flow chart for the project, and the biggest component is a bit *thick* arrow pointing at themselves labeled as '$', for crying out loud! Included in that flow chart is a *separate* company that will be doing the actual technical work.
Oh, and what's that company again? "RDD is a research, design and development company." I wonder, did they already have a company by that name, or did they have to think about it for a whole 30 seconds to come up with it? Oh wait, I forgot, these are management types, they probably spent a few weeks in meetings just to determine the consulting company to hire for suggestions.
And as Lish points out, even the semi technical parts are all fluff. If you'll notice, all of the pages where you might find technical information on this are the shortest pages on their site.
What about all of the other R&D going towards self driving cars? It's been going on for years. Every now & then you'll see some more about it in a Popular Science/Mechanics, Discover, and/or Scientific American. Self driving cars have been done countless times, they usually need something special in the road to keep track of and/or a human driver to follow. They mention they've already got positioning equipment all around the track, allowing them to position the car to within 1cm. Okay, that's a huge advantage over other self driving car projects, feasible only because it's in a closed track environment. But what about that other driver, that's still a huge feat to overcome, not to mention driving conditions and other "non-linear" elements. They don't address any of that. All they say is "this is what we want to do, imagine how much money it could bring in."
This site wasn't written for those interested in R&D, the advancement of robotics, or AI, or even F1 racing, this site was written to garner investor interest for a project that I don't think even they expect to be finished.
Until I see real evidence of ground breaking, well funded R&D, I consider this nothing more than a hoax, a deceptive ploy for money.
Don't get too excited, guys.
WHATS YOUR BUDGET LIKE! (Score:2)
Re:Is this to be *in* a race? (Score:3)
and not the only one, buddy...
But you got your analysis wrong. The third law would never come into effect here, since the robot/car is ordered to race as quickly as possible.
Thus, the second law will override the third and the robot/car will indeed take chances that a (normal) human wouldn't. (well it would slow down sometimes because a crash would mean that it failed to achieve it's objective, not to protect itself)
Fortunately for Shumacher, in every situation involving other cars with human drivers it would *have* to slow down. "cannot risk to fight for positions in this curve, someone might get hurt."
Then again, it might argue that a robot beating the F1 champ somehow would be good for humanity...
Re:I'm surprised... (Score:2)
--
A bit to strict? (Score:4)
Of course.
Computer must mechanically operate the same controls used by the human;
Why? The extra mechanics involved adds no real difficulty to the computers task. I agree that the computer should not have any extra control over the car, but what advantage does the computer get by issuing the set_brake_level(50); command insted of extend_left_foot(50); ?
Computer must fit in the same space as the human, including power source.
Yes, we want identical cars, but I'd rather state "Computer must be contained in the car. No remote control." That said I'd be equally impressed by a remote control setup as long as all sensors were in the car
Computer can have no electrical connection to vehicle for power or sensors; all its sensors must be self contained, and have no physical extension beyond what is allowed the human (no camera through the floor to follow the line :-)
Same as for the controls. Wether the computer has a direct feed from the cars sensors or points a camera at the dials and does some image processing is not important. What matters is that the computer must not have access to more information about vehicle status than the human.
Computer can have as many hands, legs, arms and eyes as it likes
Yes, but as I said: I prefer a display of AI not robitics.
Computer gets human equivalent sensors only - visible light vision and accelerometers; no radar, sonar, or active illumination allowed.
Hart to tell what is equivalent. A human has stereoscopic vision to measure distances. I think that would be a hard task to match.
Computer controlled car must meet same weight requirements as the human/car combination
Definitely. The question will rather be: Should the human car add ballast to make up for a heavy computer? I don't think it will be very lightweight...
*IF* this ever comes to be, I'd like to scale it down to an AI problem as much as possible, not a robotics/sensor contest. "Can a computer drive a car at 300 km/h?" is a much more interesting question than "Can a robot controlled by that computer operate the car?"
Vapourware (Score:2)
This was done back in the '70's (Score:2)
Re:Imagine... (Score:2)
Imagine a Beowulf Cluster of those
IMAGINE? - Don't have to! I drive to work trying to avoid them every morning!
Re:What if the car kills someone? (Score:3)
If you wrote the car racing systems using the risk assumptions of airline control it would stand absolutely NO chance of winning a race. It would be pottering around the corners on the outside to avoid risk of impacts with the human drivers zooming through on the inside.
No, if this thing is to have any chance of winning then it'll have to take risks. Take that corner a little faster than last time, leave the braking a little bit later, get an intimidatingly little bit closer to the guy in front.
And when it goes wrong, the programmer has no risk of death and injury like the human drivers ... only of litigation, big time litigation.
I'm 100% with LordNimon on this - as a software engineer - I wouldn't touch this project with a 10-foot pole. (However, I'd watch it on TV at a safe distance!) [slashdot.org]
Regards, Ralph.
Re:Pick a less expensive class first (Score:2)
This is a very interesting problem, and not one that I think can be solved in the near future provided that you exclude such technological advancements such as ABS. Newer ABS systems work by sensing lockup in one wheel (not just one axle) and adjusting the brakeing on each individual wheel. I assume the F1 robot wouldn't be afforded the luxury of a sensor on each wheel.
And how about the track itself? I suppose there would have to be something in/around the track that the robot could base its path on. But how would it deal with changing track conditions? Every racer knows that the track (not to mention the car) drives differently as the race progresses. What if oil or gravel is spilled on the track? If the robot comes in "thinking" that turn 4 is the same turn 4 that he entered last lap at 70 miles per hour, there's going to be trouble if that turn has changed drastically. There's no margin for error like that in F1 because the traction budget is already at 100%.
Re:What if the car kills someone? (Score:2)
I can see it, just. I can't speak about CART but F1 in my opinion is looking as fixed as professional wrestling. The championship is nearly always decided at the last race, the home boy too often wins at the home race, result changes, dubious stop-go decisions, etc.
However, humans being human, there's always the risk that the drivers, no matter how well paid and controlled they are, might not take the fall when they've been told to.
So, I don't think it so unlikely that the governing bodies might not choose to employ a group of healthy, attractive, pliant young actors (of a national diversity to optimise advertising revenues) to pretend to be the drivers off-race.
During the race, however, the robots are in control, speeding up, slowing down, crashing, exactly as planned - to optimize the excitement, thrill and spectacle (and advertsing revenues) expected of the F1 soap opera.
It might not be so bad actually ... they might even be able to program in some overtaking. :-)
Regards, Ralph.
How are they defining "beat a human driver"? (Score:2)
But suppose the projects definition of "beating a human driver" were to mean only "getting a car around a race track faster than the wetware controller can." If the "race" were separate time trials (i.e. on an empty track), then this prject is not as totally insane as it would appear at first glance.
Re:Is this to be *in* a race? (Score:2)
Re:Is this to be *in* a race? (Score:2)
You can't put those rules in a program though. Bumping wheels is not against the rules. Doing it intentionally is. The line between them is subtle and subjective.
Even if it weren't, this car would either be disqualified
Unfortunately you can only make that decision after you've sent your possibly-psychopathic car to the track.
*I* sure wouldn't be the guy trying to run the beast off the road. It's not necessarily going to do the "smart" thing and hit the ditch when there's no more room on the track for both of you. It'll expect *you* to give way right up until the moment both cars go up in flames.
They don't have to run *together* do they? (Score:2)
-Ben
Re:Is this to be *in* a race? (Score:2)
The teams are alowed to have different engine mappings for different rpms/engine conditions. The mappings must be consistent but not necessarily linear. What they do is measure the air pressure in the intake plenum/air box of the car, this gives them a rough idea of the car's speed (they aren't alowed measure wheel spin directly) with the air pressure and engine rpm known, they can essentialy determine when the conditions match that of the standing start and use the engine mapping to essentialy reduce engine power and therefore wheel spin at the start of the race.
Re:Is this to be *in* a race? (Score:2)
Re:This isn't F1 (Score:2)
Re:Is this to be *in* a race? (Score:2)
F1 cars were driven by computers (Score:2)
A computer should be able to get a better lap time than a human, but that's not the same as winning in F1. The technology of the cars has a lot to do with winning. (Look at what happened to Irvine when he left Ferrari for Ford!) Driving in traffic would probably be beyond the computer.
A question that I would have is: who would do better in an unusual situation? Say the car starts spinning, or something on the car isn't working 100%?
Re:Is this to be *in* a race? (Score:2)
I think robots will be manufactured and used for many commercial tasks LONG before they figure "higher concepts" like that out.
Re:Is this to be *in* a race? (Score:2)
This gets into sensing and computing complex spacial relationships, which I believe is FAR FAR beyond robotics at this point, especially in the time-frames we're talking about, with the input and sensing technologies we have today. IOW, I don't believe we have the technology currently to allow a robot-car to compete on a circuit at the same time as human-driven cars, without the humans quickly figuring out how to jocky into better positions, and force the car to either collide illegally, or back-off.
It's a very subjective decision that the driver has to make, and it's based more on gut instinct than logic, whether to attempt to get in the groove, or let the other driver go ahead and drop behind, or attempt to keep up alongside in the outer lane.
Re:Pretty cool... (Score:2)
I am not being sexist. I simply have never known a woman who could parallel park. Or juggle three objects.
Re:FOOSBALL Playing Robot!!! (Score:2)
Re:as far as size is concerned (Score:2)
--
Re:Asimov doesn't enter into it (Score:2)
Sadly that's not going to happen, mainly because he died in 1992 [asimov.com]. But his stories and books probably did inspire a lot of the people working in robotics to enter the field in the first place.
Maybe some Knight Rider fans can help me out... (Score:2)
Re:We all know what is going to happen... (Score:2)
Re:What *are* the proposed rules, anyway. (Score:2)
I'm starting to think the "robots" would really be a bunch of little Bernie androids, which would replace not only the drivers, but the engineers, designers, crew chiefs, pit crew, etc. This would finally give Bernie the absolutely total control he's wanted over F1 all along...
Motorheads on /. - yeah! (Score:2)
As someone who originally trained as a robotics engineer and has spent enough time on the track to judge the difficulty of the problem, my money is on the "meat puppets" for the next 50 years or so... (That's 30 years for procedural AI to finally die and 20 years to actually solve the problem.) But no computer will ever be likely to drive like Nuvolari, Fangio, or Foyt, as that kind of performance is beyond technical and requires soul.
Re:Challenge? (Score:2)
Why Not Robot Cops? (Score:2)
Re:A bit to strict? (Score:2)
How? A human applies a certain pressure to the brake pedal. A skilled driver knows by practice just about how much to apply to begin with. A skilled driver also quickly adjusts that pressure judging by sensory input. A robot would face exactly the same challenge. Granted, a mechanical system would introduce a delay, but then you could just as well make a rule "Computer must not think faster than a human" or more general "Computer must imitate all human shortcomings"
I don't really think this will come to an actual contest, but I for one would prefer a contest where one participant is not predestined to lose.
Re:Not a hope (Score:2)
Y'see, F1 banned most computer control in '94. Before then, ABS braking and traction control (to name to two biggies) were very common - now both are banned. They still have semi-auto gearboxes.
Now, absolutely seriously, some of the F1 teams were researching this just before the ban, and reckoned they were at most a year from making a car which could lap the circuit at a competitive speed autonomously.
In some ways, this may be an easier challenge than road car driving. By requiring them to drive flat out, you don't have to assess the speed as hard, just distance from the next corner and whether the car is sliding for speed. Traction control sorts out a lot of the speeds, line isn't a difficult challenge at most tracks. I wouldn't like to try Monaco, but Sepang (GP tomorrow) should be doable. ABS brakes are easy enough, too, and they're a big part of the skill. Remember, too, that judging braking power and distances are _easier_ for a computer. It just goes as hard as it can and lets the ABS deal with it, for the time dictated by its start and finish speeds - both of which it can work out pretty easily. A racing auto gearbox? Easy, especially when you've got semi-auto already. Program it to shift up at the rev limiter for acceleration. Downshifts are easy, too - the existing boxes already have programmed downshifts and all you need to add to that is the knowledge of corner entry speeds - not a big job to calculate. Also, it's a qualifying shootout - so an otherwise empty track and no need for collison avoidance at speed.
If they can train the system by prigramming it with data from a live driver, it becomes _far_ easier. I can't tell from the website whether this is permissible or not, but if it is then they're laughing. Even if the driver concerned isn't that fast.
This really isn't as hard a challenge as it sounds. Whether they can beat Michael Schumacher or not, I wouldn't like to bet. But I'd certainly bet that they could build an AI which would lap fast enough to qualify.
Re:Challenge? (Score:2)
This is a much harder problem than anyone here seems to realize. God is one awesome engineer, and our best efforts at mimickry are pitiful subsitutes for what we see in nature...