Slashdot Mirror
Stanley and the Conquest of the DARPA Challenge
geekboy_x writes "Wired has a great in-depth piece on the Stanford team that won the $2 million DARPA prize. If you remember last year's disaster - with most vehicles falling off the road in the first kilometer or so - this victory becomes all the more amazing. The fact that the Stanford team used a 'tailgating' strategy is the best surprise in the article."
Also interesting to note is the fact that the major leaders of the Stanford team came from the Carnegie Mellon AI department 2-3 years ago.
http://www.asti-usa.com
In order to run, one must first learn to walk...
FTA: "He liked to point out that planes had been flying themselves since the 1970s. The public was clearly willing to accept being flown by autopilot, but nobody had tried the same on the ground."
Just give us our flying cars then already, damnit!
These are the first real steps towards completely autonomous vehicles that have any sense about them. You're not going to see these things out on roads like we have today for a long time, if ever, because of how unpredictable the real world is. However, imagine if you build roads that are only used by autonomous vehicles. It could be similar to an airplane - when you reach altitude, you program your heading and let it go at it, but when you're close to your destination, off it goes and you're back in full control. That, in my opinion, is where this technology is eventually going to go.
From TFA on 7 ways cars are already robots:
"4. Lane-Departure Prevention
Nissan has a prototype that uses cameras and software to detect white lines and reflective markers. If the system determines the vehicle is drifting, it will steer the car back into the proper lane."
I've driven enough roads under construction that I would be seriously afraid that my car would steer me into oncoming traffic because road workers haven't bothered to paint over lines that were previously there.
Personally, I'd be interested in how these vehicles do:
1. On regular highways.
2. At speeds other than the 5 to 25 MPH tested.
I realize they're not built for that. I would just like to see how they do applying what they "learned" in the desert to real traffic situations.
But does it run linux?
Seriously though, they don't seem to go into much detail about the programming aspects of the robot. Of course they give some small details on what it ends up doing, but nothing about what language they used, etc., i.e. the interesting part.
The teams did well this year, but what disappoints me is that this year, many of the teams had relied entirely on laser range finders and GPS to navigate the course.
There was one entry, a motorcycle, which still ran completely on a vision system (cameras instead of sensors). Unfortunately, it did not do too well.
While the military can still use technology developed by the teams that completed the DARPA Grand Challenge, I think they could benefit even more from a vision system capable of doing the same thing. What use is a robot that can navigate a desert if it can't actually see anything?
... is that the CMU team relied heavily on extensive pre-analysis of the environment, and failed (at least in the sense that it didn't come in first). Stanford instead relied on a probability analysis of the incoming data, along with multiple technologies for different goals (lasers for short range data, video for long range data).
It seems that the DARPA grand challenge not only showed off the first realistically autonomous vehicles, but also laid to rest the idea that expert systems were the way forward. The way forward instead is self-teaching computers. Hooray for self-teaching AI overlords!
Those who can, do. Those who can't, sue.
I still think it will be a long time before we trust a computer to drive us around. Intersting that it used a 'tailgating' strategy...what happens if all the cars around it are also doing the same!
I was never that impressed with the CMU approach. All that manual preplanning was an obvious dead end. And the giant mechanically stablized gimbal was just too clunky. It didn't help them in 2004, when they hit an obstacle placed by DARPA, and it didn't help them in 2005, when DARPA moved the racecourse from California to Nevada to prevent preplanning. The Air Force colonel in charge for 2005 said preplanning wouldn't work, and he meant it.
Computer vision of the natural world is finally about to take off, after three decades of frustration. It's probably possible to do much of the early vision processing in a current-generation GPU, which may make it affordable. Look for new apps that connect to cameras and pick out items of interest. Read that paper linked above.
Basically, after two years of work they have it going at 45MPH over rough uncharted terrain.
That is pretty darn good.
The best thing about it is, the system is capable of second guessing itself, that right there is the fundamental step that lead to success.
The flip side of all of this is, it is based on probability, and while in a desert the opportunities for accidents may be minimized, I wonder how well it will deal with unexpected random events, such as people who don't put on their turn signal when changing lanes.
CPU power and other hardware can always be scaled up to deal with increase speeds (indeed a major topic that the article deals with), the question is can the algorithms deal with truly unexpected input?
Of course one solution to this is to have all cars automated, then you do not have problems with fools not using their turn signal, as the cars would just wirelessly inform each other.
Bleck, then again, I have not yet seen a perfectly working wireless network stack, hopefully who ever they get to program the cars would be of a higher caliber than the idiots who program PCs and wireless routers/switches.
Need help treating your acne? Come here!
From Wired: The resulting liability issues are a major hurdle. If a robotically driven car gets in an accident, who is to blame? If a software bug causes a car to swerve off the road, should the programmer be sued, or the manufacturer? Or is the accident victim at fault for accepting the driving decisions of the onboard computer? Would Ford or GM be to blame for selling a "faulty" product, even if, in the larger view, that product reduced traffic deaths by tens of thousands?
It figures. A technological advance that would cut the number of traffic deaths by about 95% by taking drunks and maniacs out from behind the wheel, and preventing 93 year-old men with dementia from killing people, will be bogged down by liability issues should the robot kill someone. C'mon people! Even the best system will not prevent a fluke accident or yes, even a bit of bad code, from killing someone, but weight that against the number of road-rage infested idiots on the road now, driving at 100+ mph, swerving in and out of traffic, and I think libility needs to be the furthest thing from anyone's mind.
Just don't let Microsoft write the software.
GetOuttaMySpace - The Anti-Social Network
was when Thun explained how the vehicle was taught to drive by following a human driver and adapting its algorithms according to his behavior, gaining much better results than "force feeding" massive amounts of data artificially.
This has immediate implications not only for robotic cars - what if we took a human and strapped some positional sensors, voice recording, etc. and made a humanoid robot follow him throughout the day?
I mean how varied are our lives after all? Given the right processing power and sensors, the results could be interesting...
Again, a great achievement for a 'bottom up' approach to artificial intelligence
The fact that the Stanford team used a 'tailgating' strategy is the best surprise in the article.
Not anymore.
I beleive this complaint is a little early. Based on the early successes shown in the desert, without people stepping off curbs in front of cars, and other urban hazards, I believe it is premature to say robot drivers will reduce automobile deaths by 95%. That prediction maybe true someday, but we're not going to see that next year. Or even in the next decade.
basically due to whatever circumstances (width of the road, start order etc) someone has to be in front and someone has to be behind - the fact that the Stanford vehicle was following another entry had nothing to do with how it was successful, in fact one could argue it put the vehicle in some danger if the lead vehicle messed up, rolled, crashed etc. It later passed the said vehicle to go on to the win - The article makes no mention of a "Tailgating Strategy" it does say that it was tailgating another vehicle for a bit before it passed it - not sure how this is any more strategic then when I drive to work in the morning - how about this winning strategy "Don't hit the car in front of you". Don't know why this bugged me so much, its actually a good read, I just don't know why this non-existent "Fact" was so prominent in the lead in. Sorry.. not enough coffee today....
Right now I think that it may have some issues regarding lane changing, and collision avoidance, but I think that, in the long run, those problems are a lot more solvable than, "Woops there's a giant ditch in the way, what do I do?".
Collision avoidance is pretty simple...Just stay X distance away from everybody around you, and computers have a huge advantage in that sort of test because, a) they don't get bored and stop paying attention, and b) they have very quick reaction time. It's probably easier to teach it to avoid someone merging into its lane than it is to teach it how to tell what a turn signal means.
Still a long way to go, but this is a big step.
ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.
Now all we need is a superstrong protective layer, a pursuit mode, and cool red lights on the front!
Accident opportunities in the desert are minimized? "The desert" isn't just rolling sand dunes, or a dirt road through scrubby brush. It's rocky, angled, steep, unpredictable terrain. Dealing with something as easily identifiable and predictable as road traffic (cars never leap into the air, or instantly hop sideways 6 feet) is a snap compared to off-road driving. What do you do that's so complicated when you see a car changing lanes suddenly, putting it too close to you? Apply brakes? Change lanes? A computer can do those things pretty easily-- probably safer and more attentively than a person.
If a job's not worth doing, it's not worth doing right.
That's actually not true. There was no "tailgating". During the Grand Challenge, no vehicle was allowed to approach another while both vehicles were active. DARPA had the ability to remotely pause any vehicle. When vehicles got anywhere near each other, the trailing vehicle was paused to maintain separation. If the trailing vehicle was clearly faster, a pass was scheduled. All passing took place with one vehicle stationary and at a wide place in the road. Wired has this wrong.
As a participant of another DARPA team (Cornell -- our site is down), I am skeptical as to whether the winners of the challenge would be able to drive in a real world environment. In many ways the Grand Challenge was a toy problem, but this is not usually emphasized because they want to make it seem more dramatic.
First of all, no other moving objects on the course. When a vehicle was about to pass another, the one in front was paused so that the passing vehicle could overtake it. At no time did the vehicles have to deal with changing conditions.
Secondly, to my knowledge, there were no obstacles (which were promised) on the course. If someone knows differently, I'd like to hear about it. So we don't know to what extent obstacle avoidance is effective on those vehicles.
Thirdly, daylight and clear weather is one thing, but nighttime, rain, snow, etc. would significantly degrade the data.
Essentially the problem that the current vehicles solved was this:
Given a set of waypoints and a "corridor" outside which you will never have to go (so far the problem can be solved only by 10cm-accuracy DGPS), use your other sensors to avoid obstacles by moving left or right within the corridor.
Not very much like real world driving at all. And I'm not saying Stanford, CMU and the others didn't accomplish something big -- I'm just saying it's not what the Wired piece makes it out to be.
... and they really did an amazing job, however this is sponsored by the military.
So what is it going to be used for? Suicide bomber cars?
I wish more competitions (like F1 racing for ex.) were government sponsored but for discovering certain new advantages that are directly appliable in the public sector.
Sort of like community service, offering prizes to those who prove their technology and donate it as "public patent" for everyone to use.
Exactly. If this is truly a military project then the vehicles must be able to blind-reckon once the satellite information is blocked. What's more annoying is that the tailgating idea for Stanley means that someone else is truly paving the way. While a good strategy for the race, it's does not help an "auto"-nomous vehicle, for Pete's sake.
I think they should make the requirements harder next time and give more money.
Isn't Skynet finished yet? :)
One result from the second Grand Challenge that lots of people harped about was the fact that Stanley, the winning (and hence, fastest) entry, completed the course with an average speed of only about 19 mph. "19 mph?" quoted some of the the nay-sayers, "we're supposed to get excited about that?"
One thing that TFA points out, which wasn't mentioned many other places, was that the course rules stated a maximum vehicle velocity of 25 mph. Ideally, then, the fastest possible average speed for any entrant would likewise have been 25 mph. Stanley, at times, wanted and could have gone faster than that, and held back due to the rule-imposed speed limit. In that context, 19 mph is actually quite good, considering the terrain would have forced it to slow down over bumps and turns.
I'm sure that with sufficient AI, it'll know that other driver is about to change lanes even before he does. I know I can do that just by noticing the "body english" of other vehicles on the road, so I figure a properly trained AI can do it, too.
--
"Open source is good." - Steve Jobs
"Open source is evil." - Microsoft
One could be sent to collect a downed pilot.
Not necessarily.
What do you do when someone jams their way over into your lane, pushing you out, and you are already up against the edge? Under what conditions do you accelerate, decelerate?
On ice, there is suddenly a collision 50ft ahead, do you try to steer around it, slam on the breaks, coast to a stop? If you have to change lanes, to which lane?
Here comes the key question: How would the appropriate reaction vary based upon the distance of the accident in front of you and upon different road conditions?
Codifying human experience into a computer is a complex task, and at some point a huge switch statement just becomes too unwieldy. If the appropriate reaction is to swerve into the neighboring lane, but there happens to be a child running across a crosswalk there, what then?
You get to a point where a sacrifice must be made, and then how do you program the computer?
Need help treating your acne? Come here!
The article presents the history of Stanley is presented as a series of intellectual breakthroughs that I can understand, just like a lot of the pop science I read when I was a kid (and continue to read). I'm pretty sure each of these breakthroughs (such as learning from humans and assessing sensor data critically) are ideas that have been around in AI for a long time. The true story of Stanley is no doubt just as dramatic but much harder for a layperson to appreciate.
I think the first practical non-military application of autonomous cars will involve a ton of infrastructure. It won't be achieved solely by making the cars as advanced as possible, but by providing a lot of supplemental data from an array of stationary sensors (and processors) installed by a city or theme park that wants to be the first to have autonomous cars.
Eventually human drivers will be banned, and the cars will communicate and cooperate with each other (much better than human drivers!). Traffic engineers will maneuver cars manually in rare instances, and computer-controlled cars will give them a wide berth. Safety will be improved, but so will traffic efficiency. Cars will become less personal, hence smaller and more efficient; crashes will become rarer and safer, hence cars will be smaller; computers will be better drivers, so cars will run faster and closer together. We can look forward to a period of ten to thirty years in which freeways don't get any wider.
Continuing my utopian fantasy, if cars become autonomous and have less personal significance, many city dwellers will choose to use taxi services instead of owning their own cars. That means that most of the cars on the road at a given time can have a sensible capacity, rather than the maximum capacity the owner imagines that he or she might need. Per-capita energy use for personal transportation in the U.S. will drop to a fraction of the current level.
It will happen someday, but maybe not in the next hundred years, depending on how stubborn we are. It would certainly be easier and more rewarding to start with helpful, high-infrastructure environments, but the military has such a massive capacity for funding research that we will probably solve the harder problem of hostile environments first. I.e., we'll have autonomous robot sharks with frickin' laser beams on their heads long before we have Johnny Cab.
Anyway, congratulations to the Stanford team on a great achievement.
Note to self: get a sig.
Embedded.com has this interesting article on Stanley: http://www.embedded.com/showArticle.jhtml?articleI D=174904699
I D=174400407
They had another article on 11/18/05, that suggested that the biggest problem faced by the Stanley team was not designing the software but keeping the bugs out of the software: http://www.embedded.com/showArticle.jhtml?article
It seems that engineers face an uphill challenge in getting this technology into our cars. The problem is more one of reliability and safety than artificial intelligence.
your retarded
sarchasm
You make it sound like there is nothing to it. The problem is that there are consequences to every choice the "driver" could make. For example the another lane free of other cars? Does that lane end in 50 ft explaining why the other driver jumped over? Is there someone right on my tail that hitting the breaks to suddenly would cause an accedent? Then there are the truely simple yet important questions like. Is the car too close. Programmed wrong and you could have computer controlled cars causing massive accedents because people are merging on an expressway.
But officer, the computer made the car swerved into the other cars because that old lady merged infront of me without signalling.
Its lasers are constantly teaching its video cameras how to identify drivable terrain, and it knows that it could accelerate more.
Maybe one day it can use its lasers to eliminate obstacles, creating drivable terrain and enabling to accelerate more.
He who knows best knows how little he knows. - Thomas Jefferson
Try the Scientific American article on the DARPA challenge: Innovations from a Robot Rally
It covers all the teams a bit and talks about some of the innovations that were used by the competing teams. It is a little light but worth a minute or your time.
Architectural plans are like computer source code with a couple of differences: You only compile once.
Everything aside from the possibility of hitting a living thing is easily solvable. We already have cars with computerized traction control, so they could calculate the amount of time it would take to stop given conditions if there was an accident ahead, and you'd always try to stop because that's what the drivers ed textbook says.
Car swerves into your lane, you'd always slow down and try to evade, and you'd never speed up. Even if speeding up might zip you out of the accident, the first time it failed, the auto company would get sued into a smoking hole because the computer hit the gas and increased the energy of the situation.
The solution to the problem is always going to be the same with a computer in control. Slow down, and evade. There will never be a situation where the computer decides to floor it and weave through the obstacles, that will never be allowed in the programming.
The problem with living things is the computers ability to categorize them in advance. Person or dog? You'd need some sophisticated sensors to tell the difference, and some sophisticated software to make the call. But again, it's going to come down to the programming. If a person walks out into the road, and the computer is driving, the computer will ALWAYS try to slow down and evade. It may have a more vigorous response programmed for certain situations (unlikely), but that's what it's going to do.
You act like the goal is to have a computer that can drive a racecar, and make the sort ethical descisions that people are notoriously bad at. It's not going to happen. If they get a functional computer driver, it's going to take the most conservative response in every situation. It is not going to take a huge swerve in a pedestrian area to avoid a fender bender.
ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.
Since 1969, according to the Wiki. I tell no lie here, I can never stop laughing when I realise we already have a Skynet. And it's for our Armed forces.
It was not programmed to tail-gate, it just happened to be so good at what it was doing that it caught up to the CMU vehicle and eventually passed it.
And it was using laser sensors and video cameras to visualize it's enviroment. It's a pretty remarkable system. Makes me wish I'd stayed in school for A.I. programming.
Coding reports in a factory cannot be as much fun as coding a toureg to drive through the desert.
Sean D.
"Hmm. I am to metaphor cheese as metaphor cheese is to transitive verb crackers!"
>What use is a robot that can navigate a desert if it can't actually see anything? It can drive in total darkness, for starters... I'd think that's a big advantage in a warzone. Not sure how rangefinders would cope with sandstorms, mist etc, but then you could maybe switch to another set of non-visual sensors (acoustic? Only when it's 'cam' out there, probably... Why only limit a vehicule's sensors to the visual light spectrum? Our eyes and brains are so good at the task, because it's all we have to orient ourselves, while computers have other alternatives that may prove better suited to a situation. Add the fact that computer-vision is not too good, to put it mildly, in low-light situations, mist, dust etc...
The computer should be able to react to a sudden unexpected situation as well as a human because it is capable of responding faster. The challenge seems to be identifying the situations in the first place moreso than being surprised by them.
Every deer, cow, buffalo, etc... has a GPS unit strapped to its back.
Especially when you consider those drivers who keep their turn signals blinking for 20 miles. One can imagine the motion sickness of the passengers as their computerized car continuously speeds up & slows down for the lane change that never comes.
-Kurt
"We can categorically state we have not released man-eating badgers into the area." - UK military spokesman, July 2007
how do you program the computer? it's been said that this would not work on our current system of roads, streets, and highways. methinks it would only work in a closed system where all the vehicles on said system are computer controlled. in which case, swerving into a lane which would cause the current occupants of that lane to swerve out of the way, etc, would be avoided to begin with, as the initial swerver's computer wouldn't allow them to squeeze into/cut off the other drivers.
The desert is essentially a static environment over a short time frame. You can avoid nearly 100 percent of potential accidents by merely arresting your own movement. Compare to a busy highway, where dozens if not hundreds of independently moving actors can impact you regardless of how flawlessly you negotiate the roads.
Planes fly from city to city on autopilot, but jet fighters do not dogfight or land on carriers on autopilot. Same reason--it's a huge jump to go from single actor in static environment to the physical negotiations of multiple independent actors.
Build a man a fire, he's warm for one night. Set him on fire, and he's warm for the rest of his life.
Slowing down can at times be the worst response though, and slamming on the breaks even more so (though I would assume they would program computers to not do that!)
Most likely you are right, computers will be programmed as conservatively as possible to avoid lawsuits.
How depressing, legal council resolves a technical dilemma, there likely is a better solution.
Need help treating your acne? Come here!
It really helps if you RTFA before you comment. Stanley tailgated for a while, then decided that the hummer was going too slow and passed it. Kinda hard to win a race by tailgating the whole way, no? ;)
Also, the hummer from CMU was using all the GPS data and some data that the team gathered about the route beforehand. Kinda cheating if you ask me. Stan uses a combination of lidar(for under 30 meters) and visual recognizion via camera to extend its viewable range to 80 meters. But on page 4 of the fine article, you can read a more detailed explanation.
Wort Wort Wort!
Naturally, the entire problem is compounded by the fact that the computers need to interface with humans, which has never really been their strong point.
Then again, a lot of problems are made almost trivial if the human element is removed. A simple example: network security is a cinch if you can count on there never being dishonest or malicious users!
Indeed, personal rapid transit is mathematically very simple to implement, and the network topology for it, while not exactly simple, is still far easier on a conceptual level than any of these DARPA entries!
Need help treating your acne? Come here!
i for one would not program my automated car to trust what the other drivers are "trying" to tell me, such as honking and blinking and flashing high-beams.
Instead I will trust what they are in fact doing, such as veering to the left/right, slowing down, picking up speed, or driving like they're drunken dicks.
Maybe what you are describing is how you think humans drive when they see someone with a perpetual blink. Think again. Get outside. Go to a country where nobody use blinkers at all. People slow down to let the guy turn right if the guy is already slowing down. And a computer will be a much better judge at changes in velocity and changes in distances between the two cars.
Oh I'm sorry I didn't realise you were agreeing with the point that cars should not be programmed to read blinking lights. Gotcha. yes boo to the grandparent for thinking that in the first place then.
See page 11 of their DARPA Grand Challenge entry document (http://www.darpa.mil/grandchallenge05/TechPapers/ Stanford.pdf). It runs Linux, the software is written in C/C++, and it uses IPC for communication between the various components.
(This was pointed out by an AC elsewhere in this thread),
His retarded?
Im not here now... Im out KILLING pepperoni
>imagine if you build roads that are only used by autonomous vehicles
Wouldn't that be, like, "train tracks?"
Cheers!
I'm no expert, but it seems to me you're way better off waiting until the squirrel has left the roadway. Even then your thighs must get really scratched up...
My hangup is that with the Robots on this BIG course, why would they be right next to one another? But I guess it's because engineers always think in optimal ways, so the two robots must have been along the same optimal path at the max speed allowed. That's possible, but there's room for doubt.
It must have been exciting to see!
Cheers!The goal of this program is to be able to naviage through an unpaved desert (which is not an easy task). Seperate teams have worked on cars that can navigate highways (I believe CMU has one that can run by itself 99% of the time). No, they are not perfected, but no one ever said they were. We still will have to wait a bit more for robot chauffeurs. But whining about this particular development isn't yet practical is like telling the Wright brothers that their plane isn't good enough to carry business travelers across the country.
Mathematics is made of 50 percent formulas, 50 percent proofs, and 50 percent imagination.
Would a robot controlled car try to straddle a squirrel running across the road like I do?
Yeah, but only to get a better shot with its mounted machine gun.
"I am the king of the Romans, and am superior to rules of grammar!"
-Sigismund, Holy Roman Emperor (1368-1437)
Everything aside from the possibility of hitting a living thing is easily solvable.
Agreed. It's implementing it that is the problem.
you'd always try to stop because that's what the drivers ed textbook says.
Now it may have been about 10 years since I took Drivers Ed, but my text book didn't always say the correct answer was to stop. It stated that you have to do what you thought was right to avoid an accident, which sometimes meant moving onto the shoulder or speeding up.
the first time it failed, the auto company would get sued into a smoking hole because the computer hit the gas and increased the energy of the situation.
The first time the computer fails, the company will be sued into a smoking hole regardless of the choice the computer makes.
The solution to the problem is always going to be the same with a computer in control. Slow down, and evade. There will never be a situation where the computer decides to floor it and weave through the obstacles, that will never be allowed in the programming.
I think that line of thought sells this type of system short. While I don't see a system like this being capable of weaving through traffic on an Interstate highway, it should be more than capable of picking a solution based on the current conditions. This type of system will, undoubtably, have so many inputs and sensors that it will know the traffic conditions in each lane around it, as well as how far away the nearest cars are in your lane.
My Sysadmin Blog
You have no idea what you are talking about do you?
Tesla was a genius. Edison however was a overrated hack who liked to torture puppies.
I read about 5 comments on lane changes and people stepping out in front of it.. lets not forget this is funded by a military research organization, and that is the end goal, not alllowing you to catch some zzz's on your commute to work.
Journal of the trip: NHAA journal and information on the software, RALPH
NHAA showed that it's possible to do at highway speeds (60+ mph), using 1995 technology. The construction issues are a challenge. From the journal, it sounds like RALPH handled construction reasonably well, but there certainly are construction sites that even many humans can't successfully navigate...
Is it just me, or was the second "article" just a marketing pitch?
Whose on first?
If all of the vehicles in your immediate vicinity are traveling at the same speed in the same direction their velocity relative to eachother is 0. You dont have to swerve to avoid a chair across the desk from you, do you? The same will apply to groups of vehicles traveling the highways under computer control.
True as postulated, but nowhere near real world conditions. For starters cars need to accelerate/decelerate along the axis of the road to merge, exit, and find openings to change lanes. Plus they have to accel/decel laterally to accomplish any of those. In addition, there are still going to be points of congestion which will force decel and accel. Computer control doesn't solve the basic problem of too many cars and not enough lanes.
Sociologically it's even more ridiculous...are people really going to be ok with having no control over their speed? Some people are in a hurry and want to go faster. Others like to drive conservatively at low speed. To achieve your assumed conditions there must 100% participation in a controlled traffic system--a classic command-and-control approach. The whole reason the car/road system put the railroads out of business was the personal relevance of full control over your journey.
In addition it would have to be switched over instantaneously, so as not to have computer-controlled and (unpredictable) human-controlled systems sharing the same road. There is no half-way state...if both are on the road the system devolves to the chaotic state of driving today.
Last time I drove down the freeway the only obstacles were other cars.
Not sure where you live, but around here (Mid-Atlantic U.S.) we have traffic jams, slow-moving trucks, random debris (fell off truck, car, etc), broken-down vehicles, various wildlife (up to deer size), puddles, snow patches, ice patches, and occassionally pedestrians on or along our highways at various times. In addition there are occassionally poorly-marked (or unmarked) lane changes around construction areas.
The "corridor" is like the highway and the obstacles simulate other vehicles.
Yet they didn't even allow moving vehicles around each other in the corridor...one had to stop while the other was near. They simply converted any multi-party system to a static system for one of the parties.
I definitely agree that you have to start somewhere and that the Grand Challenge is a great step forward. But let's not trivialize the challenge inherent in driving around other drivers...and in changing sociological expectations.
Build a man a fire, he's warm for one night. Set him on fire, and he's warm for the rest of his life.
So you are saying Stanley didn't use GPS?
I believe all of the competitors used GPS in some form or another, I was just trying to point out the extensive preprocessing done by humans on the CMU team(and they still lost by 11 minutes). Doesn't seem like an autonomus vehicle should need all that help, kinda defeats the purpose of being autonomus.
But since you're an expert in the field, I'm sure you know why that's the case.
I never claimed to be an expert, I only claimed to have RTFA.
By the way, on that link, the Odometry is a joke. It is absolutely useless in this application.
I agree that the Odometry is a joke on Stanley, especially on sand and other surfaces where the wheel may be spinning, but not going anywhere. I like the solution that a bunch of high school kids came up with for their "Doom Buggy", but I don't see any mention of them finishing the race. They used the same technique that is used for optical mice. I don't know how effective it really was, but it seems like it would be a much better idea than seeing how far the tire rotated over a certain period. That article is here. They talk about the "Doom Buggy" on page 2.
Wort Wort Wort!
"Woops there's a giant ditch in the way, what do I do?"
Would it be good or bad if it responded with, "Yeeehaw, let's JUMP it!" ?
Their [CMU's] mission: create a digital map of the race area's topography. The team logged 2,000 miles and built a detailed model of the desolate sagebrush expanses of the Mojave. That was only the beginning. The Red Team purchased high-resolution satellite imagery of the desert and, when Darpa revealed the course on race day, Whittaker had 12 analysts in a tent beside the start line scrutinize the terrain. The analysts identified boulders, fence posts, and ditches so that the two vehicles would not have to wonder whether a fence was a fence. Humans would have already coded it into the map.
Does anyone else think that this makes a mockery of the term "autonomous"? All the route planning (the hardest part of having an autonomous vehicle) is done by humans with the CMU vehicle. It's not autonomous at all.
If I were putting on a competition like this, I wouldn't reveal the location or route beforehand. Instead, I would have all the contestants bring their vehicles to a warehouse, then I would put them in a truck, and drive it to the race start. The race organizers would place them in random order at the starting line, then at 2-hour intervals the officials would press a prominent "Start" button that each vehicle would be required to have.
That would be a true test of autonomy. The current race is clearly biased to favor projects that already receive massive DARPA support.
his retarded and your retarded to and the mods need to get they're act right!
sarchasm
What do you do when someone jams their way over into your lane, pushing you out, and you are already up against the edge? Under what conditions do you accelerate, decelerate?
First you guess at the path of the other vehicle relative to yours for the next few seconds based on your recent measurements of its heading, speed, and size. Then you compare the outcomes of the fairly limited number of control options you have: slow straight, slow right, slow left, fast straight, fast right, fast left. Plug your current speed and approximate mass along with the predicated path of the other vehicle into each of the 6 scenarios and pick the best outcome in terms of energy remaining at time of impact (if any). Admittedly there are more than 6 options for course corrections, but you can make a first choice given the vehicle's width, mass, speed, heading, maximum steering angle and maximum acceleration/deceleration, and then calculate the exact control sequence to produce a course along the requried path while minimizing passenger discomfort. It's really not that complicated (and I actually have written obstacle avoidance algroithms for moving machines) and the computer has a *huge* advantage in quickly measuring and calculating the path of nearby objects.
On ice, there is suddenly a collision 50ft ahead, do you try to steer around it, slam on the breaks, coast to a stop? If you have to change lanes, to which lane?
If there's suddenly an obstacle 50 ft ahead of you you start braking immediately. If you slip, you reduce your breaking to stop the slipping and re-calculate your stopping distance given the new braking power and your approximate mass. If the remaining distance is insufficient, you compare the outcomes of moving left, continuing straight and moving right and choose the best outcome in terms of energy remaining at time of impact (if any). It's also worth noting that emergency steering is rarely if ever more effective than braking if you're really on ice, as it's still a huge change in momentum, and that a straight-on impact is more survivable than a sideways impact, all else being equal. And again, the computer has a *huge* advantage in determing your stopping distance and measuring or calculating your maximum non-slipping braking power and maximum non-slipping steering angle.
Following the road (or in the general case, picking a path) is much more complicated than simple physics exercises like you've described. What part of the situations you described do you see as challenging for a computer?
Yes but no - rail isn't quite the same as a paved surface. I would assume that asphalt is cheaper than rail, foot per foot. You're limited with regard to terrain with rail, as well. You can't put a twisty in laid rail and you can't have great elevation gains without substantial space.
To some 17-year-old who loses 10 cents on every typo he makes (somewhere in an obscure German town), though, this could be a wakeup call for coding more AI into spell-checking. ;-)
"The solution to the problem is always going to be the same with a computer in control. Slow down, and evade. There will never be a situation where the computer decides to floor it and weave through the obstacles, that will never be allowed in the programming."
Using the approach in TFA, the solution to any partcular situation is generated statistically, the programmer cannot know what the outcome will be. Therefore testing to attain government approval of such sytems will also be statistical.
I would imagine that if this technology takes off, manafcturers will limit their liability for tecnological cock-ups the way they do now, ie: by conforming to mandated standards. When an accident occurs and the company can show it has followed all the rules, the company is off the hook. It then becomes the standards that are scutinised and changed, much the same way as the aviation industry is forced to constantly explain it's incident figures.
Things will go wrong and people will die (just ask any medico), people can only learn by their own or other people's mistakes, those who can't must be prevented from using "sharp objects". If regulations are used to broadcast methods of avoiding those mistakes and dish out punishment to those who willfully ignore the lessons, the industry as a whole will steadily improve. This approach is vividly demonstrated by the costs of large product recalls, not the least of which is loss of public trust. If the company doesn't fess up and do everything they can to rectify the situation then they face both an outraged public and some serious jail time.
Note: The above is a description of a transparent engineering ideal that is more often than not perverted by politics and ethically blind accounting practices. Science is about refining and expanding knowlage, ENGINEERING is about refining and expanding methods for the safe utilisation of that knowlage. In the end the public will determine what is "safe", witness Chernobal's impact on reactor investment and the continuing public reluctance to revist reactors as an alternative to fossil fuels.
Software practices often seem to be part science, part engineering, but mainly goat entrails. Software is not "nuts and bolts", the industry is something brand new to civil engineering but it will eventually be absorbed by the "procedure".
Like electricity 100yrs before, the software industry has and will continue to make mistakes with fatal consequences. The question is, can it learn from them or are we creating anthother "threat to the public" such as some of those involved in the oil, tabbacco, pharmecutical, chemical, minning, agricultural,,,, in fact ALL other industries that have otherwise significant benifits to the public.
And did you exchange a walk on part in the war for a lead role in a cage? - Pink Floyd.
actualy you can, but their far less useful for anything since the turning radius is much wider, and the alternative uses of a turntable/roundhouse arangement thing at each end or a push pull engine and switchbacks restricts the length of the train that can be brought up the track. but generaly switchbacking is very good at this allowing quite steep grades to be traversed efficiently with the same ease as a road twisty :P
XML - A clever joke would be here if
Frankly, having worked on three of the teams (the three teams based in Palos Verdes), i know that collision avoidance is much harder that it might seem.
When you're driving, you can see an oncoming car and avoid it. However, you had a couple million brain cells to pick out the points of light, identify them as a car, make the decision to turn, decide which way to turn, figure out how far the steering wheel needs to move to make the turn, then actually send the commands to your muscles to do that.
With a computer though, the first two steps are (currently) near impossible to do in realtime.
Computer vision is SLOW (and inaccurate, to boot). WHen I was working on a computer vision algorithm, I got excited when, in the output from two stereo images taken on a black highway with dark brown dirt next to it, I could pick out the center line! In this output, I didn't see the edge of the road or the car in front of me. Plus, it took about 30 seconds to generate this image on a dual processor AMD workstation. Now, consider that the processing loop on a grand challenge vehicle runs anywhere from 100 Hz to 10 Hz (100 Hz for Terra Hawk, 10 Hz for Team Tormenta's entry). We just didn't have the processing time. Plus, we could see about 15 seconds ahead with the cameras; by the time we identified a fence post, it would be embedded in our front bumper.
There's a good reason nearly every team used a LADAR unit (on of those beige or blue SICK boxes) to detect obstacles: LADAR data is very specific and doesn't require much processing beyond polar to cartesian conversion.
These are things that you don't really think about until you need to deal with them.
Now you sir deserve a mod point. Shame i dont have one.
Mod Parent Up. He actualy knows what the real issues are. dynamic Pathfinding over quick physics
XML - A clever joke would be here if
I can say, without a doubt, that all teams uses GPS...
The E-Stop boxes are GPS based.
The reason I know this is that I spent a good amount of time in the garages at the NQE (except from noon to one when I escaped the heat by going the the Internet center to read slashdot), and saw the announcements that "Teams are to keep their E-Stop recievers off in the garage area because, WITHOUT A GPS FIX, they cause interference.
I think steep grades an exceptional situation.
I'm just not convinced that it's that a road that for use by robot cars exclusively is that different from rail. It's probably cheaper to build, but, you're going to have lower fuel efficiency and it's a benefit that's enjoyed only by people with robot cars... and that'll be a very small minority of people.
Maybe it could be sold to the public if they were bus-only busways, and busway-compatible robot cars could use them.
Wrong, you choose the best outcome based upon how it is going to effect others.
If the choice is either a near guaranteed death collision with the car in front, or running over onto a sidewalk and hitting a child, but with an almost guarantee that the passengers in the vehicle live, which do you choose?
What if the child on the sidewalk is a teenager, and there is a baby in the vehicle?
In a perfectly simulated world in which detailed information about all particles is known with absolute certainty, then yes, mathematics works out perfectly.
You throw stupid humans into the mix though, and things get a bit nuts.
Aside from all of this, humans have instincts; they can react really quickly to insanely complicated scenarios. Heck just think of the CPU power that was needed to keep a car on the road, how many tens of millions, if not tens of billions, of operations needed to be performed per second.
All to accomplish a task that the human mind does with ease.
I have seen computer physics simulations, walking robots are a great example, I believe Honda recently got their's to run. As slow as human babies are to develop, they are apparently easier to program! Admittedly, the major hurdle with walking robots was the development of the appropriate mathematics to solve the problem, and developing a truer understanding of the problem itself, once those were conquered, progress has been made quite steadily.
Also, I might add, physics simulations are really slow. And you would also need a computer that could react to events of such complexity, at incredible speeds. Obviously real time systems are capable of even faster reaction times than this, but the overall complexity of coordinating a real time system of this magnitude, this is not just some real time simulation running inside of Pefect Sphere physics land, the algorithms would have to handle the fact that their data is noisy.
You realize that imaging data collecting when the roads are icy would have problems with glare? Even more so, what about black ice? Where is the black ice at exactly? An experienced driver can feel it beneath their wheels, how about a computer?
When it is foggy out, data is even more sketchy. Heavy rain, humidity, wind, can disrupt the accuracy of sensor data. The fact that your data is being collected from an analog source (the real world), and then put into digital form, means that there is already some loss inherit in it, how much data loss can you tolerate?
Now run your physics simulation on that car skidding on the ice. How well does your simulator handle data of an iffy nature?
The human brain is designed to deal with incomplete, fragmented data, can your simulator handle it as well?
Can it handle it well enough to answer moral dilemas with enough certainty to satify the sue happy public?
If you say yes to all of this, now make such a complex system nearly bug proof. If it crashes, or has even a performance hiccup, even once, lives are going to be lost.
This is not a problem of the physics being done, we all know that the physics can be done, this is a problem of getting the physics done with corrupt tangled data.
Need help treating your acne? Come here!
Then let the robots download maps, etc. autonomously (automatically), and as needed, during the race.
And if route planning is so easy, why did CMU need "12 analysts in a tent beside the start line scrutinize the terrain" which "identified boulders, fence posts, and ditches so that the two vehicles would not have to wonder whether a fence was a fence".
That's not "autonomy", it's glorified R/C.
The DOD, major corporations, government, etc. are all concerned with limiting their liablility by limiting what a vehicle can do using AI technology - not about improving the performance of the vehicle. There is an effort to create a truck that can drive itself across the desert at 30 mph, but not an effort to make one that can drive across the desert at 150mph by integrating more seemlessly with the human driver.
Don't get me wrong. I would love to have a car that could drive me to work each day while I read a book or browsed the net. But the current push in vehicle control systems is more toward limiting the performance the driver can expect than improving it. When I stomp down on the accelerator I need to go fast, right then, not have my acceleration limited by the fuel injection control system - and with he cost of gasoline as high as it, I am not going to stomp on the accelerator unless I have a good reason.
So much of our intellectual efforts, engineering and legal expertise is directed toward limiting liability and risk aversion that it will eventually cripple us.
If we lose our will to push the boundaries of what is capable, then we are doomed.
I know what I'm talking about. Maybe you don't know what I'm talking about. The question was, how can a computer react to a sudden change as well as a human? I'm thinking this is a situation in which the computer will excel because fast response times are one of their strong points as opposed to humans. The problem would be recognizing the change for what it is. Not being able to respond to it fast enough. But you don't know what I'm talking about, right?
Computers can calculate faster, no doubt, but we far excel computers as dealing with a changing environment. Especially when that environment is uncontrolled.
There were very few camera based vision systems in DARPA (and the ones that were there performed badly) simply because it is extremely difficult to pick useful information out of an image. It is hard enough trying to extract where the road is and if there are any obstacles on it, let alone detect and deal with unexpected happenings. Laser systems perform better because it simplifies the information into two quantities; an obstacle, or not an obstacle.
Even a robot catching a ball is on the forefront of robotic research. This is simple to any of us over about 5 years of age but to a robot / vision system this is highly complex. Success has only been achieved in highly controlled and restricted scenarios - basically no unknowns.
So yes, computers have fast response times but it is practically irrelevant in this application for dealing with unexpected situations.
Tesla was a genius. Edison however was a overrated hack who liked to torture puppies.
To an extent is does, swerving off the road to hit a low rock might do less damage to the car than hitting deer antlers, even if the rock is technically bigger.
The first time the program chooses to swerve into a School Bus instead of some trucker in a semi, the public outrage would be enormous.
Even if, technically, it WAS the best choice, people would lose all faith in the system immediately.
Of course you could program in certain "must avoid" objects, but how long would your switch statement eventually be? And computers are horrible at context, what happens when some full size fan with "Sunday School Day Car Trasport" on it is involved in an accident, and the computer does not recognize that the van should be identified the same as a school bus?
Then why is it that every single ridgid body physics simulation I have seen, completely and utterly sucks? Seriously, just rolling balls down a hill inevitably breaks.
Well ok ok this is due to the step size, think wall, hey look, ball goes through the wall! Massivly irritating.
You are right, simple ridgid body physics simulators ARE easy to program, anyone who has taken a few quarters of physics could make one, Newtonian physics is rather trival, but I still think that things would not work out perfectly according to the equations, as most of the equations tend to assume a perfect world, you take a small error in the coefficent of friction of rubber against ice, combined with a small error in measuring various vehicular mass, combined with the small error in every other aspect of the simulation, and what happens to the numbers?
You are likely right in that the best solution probebly won't change, but I would seriously question the data after a certain point.
This is prehaps the only way of keeping things even remotely close to reality, have all of the algorithms be dynamic, only try to guess ahead by a little bit and constantly correct internal variables and estimates against real world values.
Need help treating your acne? Come here!