Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Google Wants To Test Driverless Cars In a Simulation

timothy posted about a month ago | from the do-you-want-to-be-a-virtual-pedestrian? dept.

Google 173

An anonymous reader writes Google has been testing its autonomous vehicles on U.S. roads for a while now. In fact, they're required to, by law. "California's regulations stipulate autonomous vehicles must be tested under "controlled conditions" that mimic real-world driving as closely as possible. Usually, that has meant a private test track or temporarily closed public road." It's easy enough to test a few prototypes, but whenever autonomous cars start being produced by manufacturers, it'll become a lot more complicated. Now, Google is lobbying to change that law to allow testing via computer simulation. Safety director Ron Medford said, "Computer simulations are actually more valuable, as they allow manufacturers to test their software under far more conditions and stresses than could possibly be achieved on a test track." Google spokeswoman Katelin Jabbari said, "In a few hours, we can test thousands upon thousands of scenarios which in terms of driving all over again might take decades." Shee adds that simulator data can also easily provide information on how human behavior creeps into driving. "It's not just about the physics of avoiding a crash. It's also about the emotional expectation of passengers and other drivers." For example, when one of Google's computer-controlled cars is cut off, the software brakes harder than it needs to, because this makes the passengers feel safer. Critics say relying heavily on simulation data is flawed because it doesn't take into account how other cars react to the computer's driving.

Sorry! There are no comments related to the filter you selected.

cool...it's so life-like! (3, Insightful)

turkeydance (1266624) | about a month ago | (#47733775)

until it's your life.

Re:cool...it's so life-like! (1)

rmdingler (1955220) | about 2 months ago | (#47734183)

Ironically, when it's your life, the importance of the moment multiplies like rabbits.

so what is the problem? (5, Insightful)

m2shariy (1194621) | about a month ago | (#47733781)

Test in the fscking simulation and then test on the street. Win-win.

Re:so what is the problem? (0)

Anonymous Coward | about a month ago | (#47733839)

certainly the simulation would include real persons driving simulated vehicles?

Re:so what is the problem? (0)

Anonymous Coward | about 2 months ago | (#47734081)

i take you to mean that real persons would drive simulations of real non-autonomous vehicles in the simulation? and the simulation can encompass a large selection of real-world intersection configurations with all the organic glory of partially obstructed sight lines and perhaps even pedestrian and bicyclist avatars controlled by real persons. seems like it would accelerate the production of results needed to reasonably determine if an autonomous vehicle was ready to meet the real-world itself.

Re:so what is the problem? (4, Insightful)

dnavid (2842431) | about 2 months ago | (#47733943)

Test in the fscking simulation and then test on the street. Win-win.

You don't need to ask for permission to test your car with simulations. You only have to ask for permission to replace real world testing with simulations. Personally, I'm not fond of replacing real world testing completely with simulations. The problem is that the point of testing software is to make sure the programmers have properly dealt with as many possible real world situations, and to reduce the likelihood the programmers haven't ignored an unexpected circumstance. Simulations can only test for what the simulation programmers have accounted for. Its substituting the system programmers' judgment for the simulation programmers' judgment. Its useful, but in my opinion insufficient.

Re:so what is the problem? (5, Insightful)

Your.Master (1088569) | about 2 months ago | (#47734237)

I'd flip it around. An automated car should be required to pass both a road test and a bevvy of simulated scenarios.

Re:so what is the problem? (2)

ganjadude (952775) | about 2 months ago | (#47734027)

can i mod this +1 obvious?

something tells me... (0)

Anonymous Coward | about a month ago | (#47733787)

the physics of a simulation aren't going to match-up to the real world quite right.

Re:something tells me... (0)

Anonymous Coward | about 2 months ago | (#47733969)

The physics aren't the problem, the relevant physics necessary to get this done have been well understood for a long time. The computational power isn't an issue either.

The real issue here is that it's impossible to accurately model the way that other cars and animals are going to be interacting with the vehicles. Presumably the cars themselves are going to be just fine running over raccoons and cats, but larger animals like moose and squirrels are a different matter.

Re:something tells me... (1)

ganjadude (952775) | about 2 months ago | (#47734041)

on the other hand, there are only so many possible scenarios no? to simplify it a LOT theres, keep going, speed up, slow down, turn left, turn right, stop. There are variations of all these scenarios but that is all that there could be. simulations could account for quite a bit in that regard.

Re:something tells me... (0)

Anonymous Coward | about 2 months ago | (#47734107)

The real issue here is that it's impossible to accurately model the way that other cars and animals are going to be interacting with the vehicles. Presumably the cars themselves are going to be just fine running over raccoons and cats, but larger animals like moose and squirrels are a different matter.

Which is an issue with physics (partly)

Re:something tells me... (2)

turkeydance (1266624) | about 2 months ago | (#47734157)

moose and squirrel. well played, sir.

Re:something tells me... (0)

Anonymous Coward | about 2 months ago | (#47734163)

But, again, how the fuck are they going to test those scenarios in the physical realm? It seems to me you can test far more moose-and-squirrel scenarios in a simulation than you can in the real world.

Re:something tells me... (1)

DexterIsADog (2954149) | about 2 months ago | (#47734769)

...going to be just fine running over raccoons and cats, but larger animals like moose and squirrels are a different matter.

Don't worry, they'll never manage to run over that pesky moose and squirrel.

Simulations are limited by imagination (3, Insightful)

Carnildo (712617) | about a month ago | (#47733829)

The problem with simulator testing is that you can't test scenarios that you didn't think of. This is particularly important to find problems arising from multiple simultaneous situations. For example, you might test the scenarios "front camera obscured by rain", "car ahead of you performs emergency stop", and "dog runs into street", but that doesn't necessarily tell you how the car will respond to a combination of the three.

Real life is far more creative than any scenario designer.

Re:Simulations are limited by imagination (1)

Shadow of Eternity (795165) | about 2 months ago | (#47733877)

A simulation is also only as good as its simulator. The idea of a simulator that doesn't let errors slip that will only show up in the real world doesn't pass the sanity test.

Re:Simulations are limited by imagination (1)

Noah Haders (3621429) | about 2 months ago | (#47733921)

and the simulator is only as good as the programmer. Google can test in the simulator all they want, I'm sure they do it anyway. But road testing is required regardless. I don't want to be in the beta group for driverless cars when we're going 70MPH on the 101.

Re:Simulations are limited by imagination (1)

un1nsp1red (2503532) | about 2 months ago | (#47734179)

Just test on the 101 in Los Angeles. You'll never hit 70MPH.

Re:Simulations are limited by imagination (0)

Anonymous Coward | about 2 months ago | (#47733947)

A simulation is also only as good as its simulator. The idea of a simulator that doesn't let errors slip that will only show up in the real world doesn't pass the sanity test.

A simulator in this case is only as good as understanding and modeling the true chaos that takes place on US roads every single day.

People seem to forget that stepping inside a car is one of the most dangerous things humans do, and you likely do it every single day.

Sorry, but since texting will soon become the #1 killer behind the wheel thanks to ignorance, Google is going to have to work damn hard to build a better idiot.

Re:Simulations are limited by imagination (1)

rmdingler (1955220) | about 2 months ago | (#47734221)

Agreed. Though driver distraction is a tough nut to crack.

Even if you account for the physical distraction that texting or talking on a cellular phone creates, you have not slayed the Dragon.

It's the mental distraction these tasks create that takes you out of the Driving Game, and you don't get three lives.

Re:Simulations are limited by imagination (2)

fisted (2295862) | about 2 months ago | (#47733881)

For example, you might test the scenarios "front camera obscured by rain", "car ahead of you performs emergency stop", and "dog runs into street", but that doesn't necessarily tell you how the car will respond to a combination of the three.

Now that really leads to a difficult decision for the car. Should it:
- Maintain heading and come to a halt? Or perhaps
- Maintain heading and come to a halt? Or even
- Maintain heading and come to a halt?

Let's wait for strong AI to solve that problem for us.

Re:Simulations are limited by imagination (2)

0123456 (636235) | about 2 months ago | (#47733911)

Decades of aircraft autopilot failures tells us it will immediately hand control back to the driver, then blame 'human error' for the crash.

Re:Simulations are limited by imagination (1)

rmdingler (1955220) | about 2 months ago | (#47734255)

Because saying Our pilot assed up involves a significantly disproportionate settlement amount than an indictment of our entire technological foundation.

Good post.

Re:Simulations are limited by imagination (0)

Anonymous Coward | about 2 months ago | (#47734697)

If you have any clue on aviation, the first thing that happens should anything go wrong is that it gets blamed on pilot error. This because if a company manages to get a scapegoat, it solves the "problem" without actually having to spend money to do really expensive things things like scheduled maintenance or actually responding to issues pilots report in flight.

Re:Simulations are limited by imagination (1)

Carnildo (712617) | about 2 months ago | (#47733933)

Are you sure the car won't spot the dog, mistake it for a child (remember, the quality of information from the front camera is reduced), and perform an emergency turn to the left? Are you sure the presence of the car won't mask the presence of the dog, or vice-versa?

It's easy to say "when in doubt, maintain heading and come to a halt". It's much harder to define "doubt" in a way that's useful to a computer.

Re:Simulations are limited by imagination (1)

kamapuaa (555446) | about 2 months ago | (#47733953)

Are you suggesting simulators can't deal with multiple scenarios at the same time?

Re:Simulations are limited by imagination (1)

rtb61 (674572) | about 2 months ago | (#47734467)

Where are simulator completely and utterly fails should be obvious to everyone, it does not test environmental analysis at all. The environment is not detected, analysed and correlated, it is simply fed into the program and so only half the system is tested, not the whole system.

The system should be tested on the road under normal conditions, from rush hour to night driving with a driver ready to take over and at lest two randomly chosen independent observer. Things that need to be tested, missing or worn line markings, road works, debris on road including plastic bags in the wind, car doors opening into traffic stream, vehicles straddling lanes, emergency vehicle response with regards to other vehicles failing to react appropriately et al.

Re:Simulations are limited by imagination (0)

Anonymous Coward | about 2 months ago | (#47734779)

Where are simulator completely and utterly fails should be obvious to everyone, it does not test environmental analysis at all. The environment is not detected, analysed and correlated, it is simply fed into the program and so only half the system is tested, not the whole system.

I don't think you have a clue about what you're saying. You know nothing about simulations, and particularly the simulations Google would create. Remember, they hire platoons of people *much* smarter than you.

You just pulled this "obvious" error out of your ass.

Re:Simulations are limited by imagination (1)

PopeRatzo (965947) | about 2 months ago | (#47734125)

Maintain heading and come to a halt?

That's going to double travel times right away.

Re:Simulations are limited by imagination (0)

WinterSolstice (223271) | about 2 months ago | (#47734193)

Or just drive the damn car.

I swear, I'm SO sick of this driverless car crap. I don't want one, I don't want to share roads with one, I don't want to even see them.
It's bad enough dealing with humans, the last thing I want is this.

We HAVE a way to get around without you having to drive. It's called public transportation. Get on a damn bus, taxi, or train.

Re:Simulations are limited by imagination (4, Insightful)

ShanghaiBill (739463) | about 2 months ago | (#47733895)

For example, you might test the scenarios "front camera obscured by rain", "car ahead of you performs emergency stop", and "dog runs into street", but that doesn't necessarily tell you how the car will respond to a combination of the three.

This seems backwards to me. Testing combinations of scenarios happening simultaneously would be far easier in a simulator.

Re:Simulations are limited by imagination (1)

Pentium100 (1240090) | about 2 months ago | (#47734621)

But only the combinations you think of, while in real life something might happen that you did not expect.

Simulations are limited by imagination (2, Interesting)

Anonymous Coward | about 2 months ago | (#47734007)

Sure, but the article isn't taking about simulations vs real life. It's talking about simulations vs contrived but legally required tests on manufacturer test tracks. Both are limited by imagination but simulations are more thorough, at least according to Google

Re:Simulations are limited by imagination (4, Interesting)

swillden (191260) | about 2 months ago | (#47734021)

The problem with simulator testing is that you can't test scenarios that you didn't think of. This is particularly important to find problems arising from multiple simultaneous situations. For example, you might test the scenarios "front camera obscured by rain", "car ahead of you performs emergency stop", and "dog runs into street", but that doesn't necessarily tell you how the car will respond to a combination of the three.

Real life is far more creative than any scenario designer.

Which is why you should do both. A simulation can test millions of permutations -- including arbitrary combinations of events, and in far more variety than could be tested in a reasonable amount of time on real roads -- and can verify that software changes don't introduce regressions. Real-world testing introduces an element of randomness which provides additional insights for the simulation test cases.

Ultimately, governments should probably develop their own simulators which run the autonomous car through a large battery of scenarios, including scenarios which include disabling some of the car's sensors. Then autonomous vehicles from different manufacturers could be validated on a standard test suite before being allowed on the roads, and when real-world incidents occur in which an automated car makes a bad decision, those incidents can and should be replicated in the simulator and all certified vehicles tested. They should also do real-world testing, but I suspect that in the long run simulations will provide much greater confidence.

Re:Simulations are limited by imagination (0)

Anonymous Coward | about 2 months ago | (#47734101)

the critics seem to assume a simulation would only include programmatically created test subjects. the simulation arena can include real persons who would drive simulations of real non-autonomous vehicles in the simulation. and the simulation can encompass a large selection of real-world intersection configurations with all the organic glory of partially obstructed sight lines and perhaps even pedestrian and bicyclist avatars controlled by real persons. seems like it would accelerate the production of results needed to reasonably determine if an autonomous vehicle was ready to meet the real-world itself.

Re:Simulations are limited by imagination (1)

PopeRatzo (965947) | about 2 months ago | (#47734119)

Real life is far more creative than any scenario designer.

Ain't that the truth.

This is why I don't see everyone in driverless cars in any of our lifetimes. I'm thinking it's at least 70 years out. And not least because a) who's going to pay for all the necessary infrastructure? and b) shared liability will make it a nightmare.

Maybe first let's see if we can have a driverless NASCAR race without crashes. And then I want to see the CEO of a driverless car company put his kids in the car and send them on a coast-to-coast road trip, including LA at rush hour, Chicago's Dan Ryan Expressway Southbound at 3:30am and on small roads crossing the Appalachians.

Re:Simulations are limited by imagination (2)

D'Sphitz (699604) | about 2 months ago | (#47734153)

You can't test scenarios that weren't thought of on a private test track either.

Re:Simulations are limited by imagination (1)

siphonophore (158996) | about 2 months ago | (#47734195)

You make an excellent argument for simulated testing. A real world test will only give you a few scenarios, simulation will throw millions at each individual unit.

Of course you're right about real life constantly surprising people--that's why the development team is performing continuous algorithm development in the real world. I hope my automated car has a real-world-tuned algorithm in combination with a moslty-simulated per-unit system test.

Re:Simulations are limited by imagination (0)

Anonymous Coward | about 2 months ago | (#47734437)

I'll go a bit further and say that simulations are limited by algorithms. Sorry, there's no way an algorithm is going to be able to deal with all the stupid shit people do on the roads. No way. If all cars were instantly replaced by driverless cars that obeyed every law, you'd still have to deal with bicycles and pedestrians and they do far more stupid shit than just cars. Sorry, no way would I trust an autonomous vehicle tested only in simulation. Hell, the govt doesn't trust drones until they've been tested in the real world.

Reality is limited by probability (+consequences) (1)

penguinoid (724646) | about 2 months ago | (#47734747)

In a simulation you can have people do all kinds of crazy shit you wouldn't see in thousands of on-the-road miles. You can simulate malfunctioning equipment that you wouldn't get without years of wear and tear. You can test modifications to the AI without real-world consequences. You can test the human-ai interaction on average drivers without liability problems. I could totally see a simulation being superior to reality for testing purposes.

But you could also have a broken simulation, which could make the whole thing near worthless.

MIT's Rodney Brooks (0)

Anonymous Coward | about a month ago | (#47733843)

As head of the robotics program at MIT Dr. Rodney Brooks famously said, "Robot simulations are doomed to succeed."

California decriminalizes Need for Speed, Forza (-1)

Anonymous Coward | about a month ago | (#47733849)

News of the huh what

Easy solution (1)

Anonymous Coward | about 2 months ago | (#47733863)

Require that all autonomous vehicles deliver themselves to your driveway. From the factory. If they make it there, they are deemed safe for use.

I'm confused (1)

daniel142005 (906427) | about 2 months ago | (#47733865)

Why is it so hard for the test track to be outside the place where they're manufactured? When a car is done it would drive through a "course" by itself, since it is autonomous... or at least they want us to be believe it is. Can see the job description now: Driver required for autonomous vehicle test course, must be able to maintain the stability of the vehicle with automated cars on the road that may occasionally divert from their intended path. Comes with great benefits.

but seriously, Tests could be simulated with the same kind of course a drivers ed student supposedly goes through, and there's no reason these things shouldn't be able to drive themselves to an offsite storage facility, even if it is controlled roads or roads with caution signs. Simulations don't account for faults in the design or manufacturing.

Re:I'm confused (1)

Noah Haders (3621429) | about 2 months ago | (#47733945)

google has billions and billions and billions. I'm not going to cry if they have to make a test track.

Re:I'm confused (1)

siphonophore (158996) | about 2 months ago | (#47734121)

A test track may break the bank for a start-up with a great new algorithm

Re:I'm confused (3, Insightful)

ShanghaiBill (739463) | about 2 months ago | (#47733991)

Simulations don't account for faults in the design or manufacturing.

You don't have to test every car to find faults in the design. You only have to test one.

Faults in manufacturing are not unique to self-driving-cars. So why should only SDCs require testing of every car?

Bad conditions (1)

Anonymous Coward | about 2 months ago | (#47733867)

I can grasp how they might program a car to drive between lines, avoid other cars, and obey traffic lights. I've always been curious how well they do with ice, emergency vehicles approaching, and drunk drivers. I'm guessing better than us, but I would still love to see it...

test software but not hardware / road conditions (2)

Joe_Dragon (2206452) | about 2 months ago | (#47733871)

may help test software but not the full hardware and how well it works in all kinds of weather / settings. Also what about road conditions / slight lines? odd traffic light layouts / intersections? Just useing google street view as the input likely will not get the full lay out from each lane / all times of day / all cycles.

The problem with simulation is ... (2)

CaptainDork (3678879) | about 2 months ago | (#47733879)

... lack of randomness.

Will they simulate a 3 year old tossing a sandwich out the window into oncoming traffic?

Re:The problem with simulation is ... (1)

turkeydance (1266624) | about 2 months ago | (#47734207)

3-yo? how about everyone throws out all their trash? total discharge at 11 mph over posted speed. all 4 windows open and ejected into traffic? yes, i was doing 11mph over the line. right in front of me. NASCAR skilz.

Re:The problem with simulation is ... (1)

phantomfive (622387) | about 2 months ago | (#47734681)

I've read your post three times and I still have no idea what it's talking about. Sounds interesting, though.

Re:The problem with simulation is ... (0)

Anonymous Coward | about 2 months ago | (#47734247)

Will a closed highway test simulate that?

Re:The problem with simulation is ... (0)

Anonymous Coward | about 2 months ago | (#47734761)

They can probably do just as much in a simulator with respect to randomness as they can on a closed test track or a closed public road. In fact it doesn't seem that difficult to simulate people in the virtual world that has been created.

Reports indicate they've already done quite a bit of real world testing and have probably covered the bases on what you would typically come up with to do in a closed course.

I still feel like it makes sense to do real world testing, but I'm not sure the randomness argument is a good one.

Also, it seems like it is in Google's best interest to make sure their car is completely safe. Even if the people designing and building the cars don't care at all about the lives of their customers, they sure care about their bottom line and if there is an accident it will have a very significant impact on the bottom line and would certainly tarnish the brand.

Adding Politics to Engineering Decisions (3, Insightful)

siphonophore (158996) | about 2 months ago | (#47733887)

Are we really having a public, political, emotional discussion about the relative merits of ATE vs Validation testing? Come on, Slashdot, you're a bunch of engineers, right? Does the CA state legislature have ANYTHING of value to add to your FMEA? What about your production planning? Test plan? V&V protocols?

It's the height of hubris for outsiders (especially lawyers in the state legislature) to come in and dictate low-level engineering details. A responsible legislature (and public) would acknowledge that they have NOTHING of value to add to the discussion.

The only appropriate regulation is "make it X safe." Don't tell us engineers to get there, and we won't tell you lawyers how to snort coke of a hooker's tits.

Re:Adding Politics to Engineering Decisions (2)

kamapuaa (555446) | about 2 months ago | (#47733965)

Wish I could mod parent "+1 Edgy"

If it wasn't so edgy, the suggestion to let the car companies decide for themselves would come off as ridiculous.

Re:Adding Politics to Engineering Decisions (1)

ShanghaiBill (739463) | about 2 months ago | (#47734015)

If it wasn't so edgy, the suggestion to let the car companies decide for themselves would come off as ridiculous.

As long as they, and their insurance company, are willing to accept full liability, I don't see why not.

Re:Adding Politics to Engineering Decisions (3, Insightful)

siphonophore (158996) | about 2 months ago | (#47734033)

A regulatory "light hand" is appropriate here for a few reasons:

1. The current state of the art is, comparatively, extremely dangerous (even with attentive, good drivers).
2. Google (or the next few guys coming down the pipe) already have an extremely strong incentive to make their cars as safe as possible (speed of adoption, fear of future regulation).
3. OTA updates would resolve problem behaviors after only a few incidents.

Google is coming to the public with a (statistical) goldmine for human development. The cold skepticism they're getting is totally unwarranted and will do nothing but delay the enormous social and economic benefits that fully autonomous roads will bring.

Re:Adding Politics to Engineering Decisions (1)

0123456 (636235) | about 2 months ago | (#47734089)

1. The current state of the art is, comparatively, extremely dangerous (even with attentive, good drivers).

One death per 60,000,000 miles (with inattentive, lousy American drivers) is 'extremely dangerous'?

Re:Adding Politics to Engineering Decisions (1)

siphonophore (158996) | about 2 months ago | (#47734097)

"comparatively"

This is (typically) the most dangerous thing people do all day.

Re:Adding Politics to Engineering Decisions (1)

0123456 (636235) | about 2 months ago | (#47734105)

Compared to what? Russian roulette?

As far as I'm aware, no 'self-driving' car has driven anywhere near 60,000,000 miles.

Re:Adding Politics to Engineering Decisions (2)

Your.Master (1088569) | about 2 months ago | (#47734311)

No, not compared to Russian Roulette, compared to the things typical people do in a typical day. Also, with cars, death isn't the only danger. Permanent injury, significant temporary injury, and massive property damage are also dangers.

Typical people live their entire lives without playing Russian Roulette even once.

I don't really know why this is hard. Most people don't do a lot of dangerous things in a day.

In fact, even in terms of death: 22% of people who die between the ages of 1 and 44 in the United States die from a motor vehicle accident. Most of the other itemized are not daily (eg. fire, except for firefighters; firearm, etc.).

http://www.cdc.gov/injury/over... [cdc.gov]

If there was a more deadly daily activity, it should show up on that list. I mostly see things that are more deadly, but not daily. I have to admit I'm not quite sure what to make of "falls" from the under-45 crowd.

Re:Adding Politics to Engineering Decisions (1)

phantomfive (622387) | about 2 months ago | (#47734687)

3. OTA updates would resolve problem behaviors after only a few incidents

You would let your car be connected to the internet? 0_0

Re:Adding Politics to Engineering Decisions (0)

Anonymous Coward | about 2 months ago | (#47734039)

Yes, that worked so well for GM recently.

Re:Adding Politics to Engineering Decisions (4, Insightful)

siphonophore (158996) | about 2 months ago | (#47734063)

The real story is an unbroken 50-year streak of improvements in safety driven and executed by engineers. A series of recalls is nothing compared to the 60% decline in traffic deaths brought about by new safety technology and it's rapid adoption. Driverless cars are a new safety technology. Let's adopt them already!

Would 2014 America hold up seat belt installation for ten years just to make sure they are totally, exactly, 100% safe?

Re:Adding Politics to Engineering Decisions (0)

Anonymous Coward | about 2 months ago | (#47734079)

Many of those improvements were government mandates, correct?

Re:Adding Politics to Engineering Decisions (1)

siphonophore (158996) | about 2 months ago | (#47734087)

Gov't won't mandate this type of car anytime soon. For the time being, it's up to consumers to adopt and the gov't to get out of the way.

Re:Adding Politics to Engineering Decisions (0)

Anonymous Coward | about 2 months ago | (#47734177)

Government still has a large role to play. For example, the fact that you can get into pretty much any car and just drive off is due to the fact that government has FMVSS regulations that require strict adherence to certain standards. The same will be true of autonomous vehicles. They will need to pretty much all behave in the same way or there will be negative consequences for the public. That is but one example.

Re:Adding Politics to Engineering Decisions (1)

siphonophore (158996) | about 2 months ago | (#47734285)

Standards are probably the best thing to come out of regulation. I would love it if those standards were written after anyone knew what the heck the new industry was going to look like! It would be like the 1910 CA legislature mandating turn-crank starters because that solution made the best sense at the time.

Re:Adding Politics to Engineering Decisions (1)

Pentium100 (1240090) | about 2 months ago | (#47734661)

I would like a crank starter on my car as an addition to the electric starter of course. In some cases the battery is too weak to start the engine, but has enough power to operate the ignition, fuel cutoff valves and the field coil of the alternator. Sure, the car can then be push started, but that requires at least one other person and the car to not be at the bottom of a hill (it's difficult to push a car uphill). I could then crank start the car. It does not look lie adding the crank would have cost the manufacturer lots of money.

Re:Adding Politics to Engineering Decisions (1)

penguinoid (724646) | about 2 months ago | (#47734787)

Sure, the car can then be push started, but that requires at least one other person

I know a cheap bastard that would only park his car on a hill. Want to know why?

Re:Adding Politics to Engineering Decisions (1)

Jeremi (14640) | about 2 months ago | (#47734605)

Would 2014 America hold up seat belt installation for ten years just to make sure they are totally, exactly, 100% safe?

Really, you're don't see the difference in added risk between (a computer taking over sole responsibility for the control of a 2500-pound, 65-mile-an-hour car, in all possible traffic conditions), and (adding a strip of reinforced fabric to the cockpit)?

When was the last time your seat belt stopped working due to a buffer overrun? Contrariwise, when was the last time your home computer did something wrong or unexpected?

Re:Adding Politics to Engineering Decisions (0)

Anonymous Coward | about 2 months ago | (#47734667)

Practical driverless cars do not exist and are nowhere near ready. Coverage of this subject has been preposterously uncritical.

It's interesting that nothing close to the level of machine intelligence that would be required has not been demonstrated in any other field, from Google's own search engine to unlimited-budget DoD projects, yet everyone is willing to believe that its very first appearance will be in... cars - on public highways?

Re:Adding Politics to Engineering Decisions (2)

westlake (615356) | about 2 months ago | (#47734103)

Come on, Slashdot, you're a bunch of engineers, right?

Wrong.

If by engineer you mean a licensed professional who stands by his work, and can be called to account for his failures.

It's the height of hubris for outsiders (especially lawyers in the state legislature) to come in and dictate low-level engineering details.

It also the height of hubris for the geek to allow Google to be the sole judge of its own work.

Re:Adding Politics to Engineering Decisions (1)

siphonophore (158996) | about 2 months ago | (#47734141)

It also the height of hubris for the geek to allow Google to be the sole judge of its own work.

Manufacturing in a regulated industry is a constant battle between operations an quality. Operations (with an eye toward revenue) tries to speed things up, Quality (with an eye toward recalls and audits) tries to slow things down. Both report through different paths to the CEO. The Geek in R&D will see his work checked over by a different department with a different set of metrics.

You can pick your exceptions, but the overwhelming result of this organizational method is safer and better products.

Re:Adding Politics to Engineering Decisions (0)

Anonymous Coward | about 2 months ago | (#47734167)

we won't tell you lawyers how to snort coke of a hooker's tits.

I believe "frequently" is the correct answer there.

Re:Adding Politics to Engineering Decisions (1)

Kjella (173770) | about 2 months ago | (#47734171)

You really think this is solely an engineering decision? I'm guessing this is just as much if not more a business decision. We could have real world testing which is expensive where unexpected quirks and flaws could be revealed or we could have simulations which are cheap and quite confined to whatever it is the scenario is testing. Everyone in suits would go with simulations, while engineers know that models are abstractions and simplifications of reality.

Don't get me wrong, I'm sure they do a ton of simulation and regression testing and as a design tool it's invaluable. To use a car analogy I really doubt cars come rolling off the assembly line without some prototyping and real world tests first though. Remember that those affected by regulations tend to have really deep economic interests in skirting those regulations as much as possible.

Re:Adding Politics to Engineering Decisions (1)

siphonophore (158996) | about 2 months ago | (#47734245)

If you were running this I bet you would sign yourself up for an ATE-heavy 100%, a sample plan of trips around town, and an exhaustive DVT (verification in the lab and validation all over the country). You'd hit all the points on the FMEA and performance requirements doc, then throw some gonzo tests in there to add a little spice.

I would say that's sufficient and you acted prudently, and engineers with production experience would say the same. Things would turn out just fine UNLESS some idiot decided to turn it into a political talking point--then common sense and a workable time-to-market flies out the window.

Oh Bullshit (0)

Anonymous Coward | about 2 months ago | (#47734235)

I work in the UAV industry, doing safety protocols. The hubris is on the side of the engineers. For a very simple system about a billion simulation runs in a constructive model, a million in a virtual model (flying against real pilots) and a thousand engagements to validate the modesl will be marginally adequate. The engineers want to claim it's good with a million constructive simulation runs and dozens of live runs, and they're fucking wrong. This is why we have oversight. I'm much more confident in the CA legislation than in the google engineer polyannishness, because driving is a whole hell of a lot more complicated to model than flying.

Re:Oh Bullshit (1)

siphonophore (158996) | about 2 months ago | (#47734273)

I bet Google has plenty of skeptical safety guys there just like you. And I bet they're under a lot of pressure from the suits to prevent incidents in the field.

So far there have been zero problems, but that didn't stop them from setting up a regulatory framework. Guessing the problems of an entirely new technology and mandating rules for an entire industry is the kind of hubris that can hold up widespread adoption by 10 years.

Re:Adding Politics to Engineering Decisions (0)

Anonymous Coward | about 2 months ago | (#47734737)

Insightful my ass. These are people's lives at risk. If google wants software simulation, then they can do that. But at the end of the day they need to to real world tests just like the rest of the world does when people's lives are at risk.

who writes the simulator? (1)

slew (2918) | about 2 months ago | (#47733929)

Let's see if...

Google writes the software for the car
Google writes (or pays someone else to write) the simulator
Google runs the test
Google reports the results

Seems like with simulations we would be somehow implicitly trusting google that their simulator sufficiently models reality vs only modeling what the self driving software expected...

Although simulation has its place to improve testability during training and development, how does this test against reality? The reason to test against reality is generally to cover the stuff that you *didn't* expect. It's generally quite easy to fool yourself (and others) that something is good enough if you remove this link back to reality...

Another advantage of computer sims (0)

Anonymous Coward | about 2 months ago | (#47733941)

It's easier to collect data on the drivers' shopping habits.

Use real drivers on the simulation (1)

Anonymous Coward | about 2 months ago | (#47734005)

Turn the simulation a "car game" with good car simulation (allow to skid or dump a car) and then add the software as a gamer.

You can even move a real car with the same movements on a flat big zone (ej. desert) with people inside the car but with screens instead windows seen the simulation to monitorize the reactions of people.

A mix of virtual reality, augmented reality, real acceleration/speed perception and crazy human drivers and pedestrian f***ing the simulation pushing the software to drive into the limits without real danger (because the obstacles only exists in the simularion, although directly controlled by humans in real time).

Other tests could be record real cars for a lot of hours and later test the software with this video to check if really detects the same that human has seen.

Re:Use real drivers on the simulation (0)

Anonymous Coward | about 2 months ago | (#47734231)

When I took drivers training in high school we had simulators, 0 to 90 in about 135 seconds.

Can't wait to see the hackers in action! (0)

Anonymous Coward | about 2 months ago | (#47734055)

Judging by the malicious activity at my mail server, and all manner of malicious hacking attempts of my computers, I cannot wait to see what happens when driver-less cars become the norm.

Will pedestrians simply step off the sidewalk at any place at any time, safe in the knowledge that the driver-less cars will all stop?

Will car-jackers feel liberated by the free availability of cars that stop on command - just by walking out in front of them.

What will the public liability insurance rates be for driver-less cars, given that they wont be programmed to run pedestrians over, but will therefore be stoppable by any pedestrian waving their arms.

Will running red lights therefore also get easier and safer?

Car Analogy (3, Funny)

ProzacPatient (915544) | about 2 months ago | (#47734117)

Can someone give me the obligatory car analogy?

Re:Car Analogy (0)

Anonymous Coward | about 2 months ago | (#47734161)

Nobody talks about brave men in their proud simulators . . .
What are your? A brain in a vat?

Re:Car Analogy (2)

slashmydots (2189826) | about 2 months ago | (#47734175)

No idea what you mean but how about this: If a car leaves New York traveling 60 MPH and another card leaves from Vegas at 50MPH, how long does it take for Gloria Allred to show up after a Google car crashes into one of them?

Can I pay for Google car with my simulated money? (1)

citizenr (871508) | about 2 months ago | (#47734129)

Can I miss Google spokeswoman Katelin Jabbari?

Both, duh (1)

purplie (610402) | about 2 months ago | (#47734149)

Simulations and real tests aren't mutually exclusive. They have different strengths, and you should do both.

pointless scam (1)

slashmydots (2189826) | about 2 months ago | (#47734159)

They're doing this so they can rig it. Human brains are amazing at adaptating, object indentification, and fast logical reasoning. Computers are horrible at that. Some humans are pretty awful drivers. So the computer would have to be better than a below average intelligence human. They're not even close. In a simulation, you just program the logic to react to only the logic that you programmed into the simulation. In other words, cheat.

Re:pointless scam (1)

epyT-R (613989) | about 2 months ago | (#47734607)

On slashdot, there was an article that linked to a video of google engineers describing how their system works. IIRC, they preprogrammed responses to a bunch of situations (like avoiding a bicycle on the side of the road), using heuristics to detect when/where/which situation was occuring. In contrast, humans are in a constant state of intuitive heuristics. While they take longer to react, they're aware of possible consequences long before a computer can be, which puts them way ahead of electronic idiot savants with lightning reflexes.

can't anticipate other driver stupidity (0)

Anonymous Coward | about 2 months ago | (#47734427)

Just about every day I see a driver perform some maneuver that defies rational explanation. I have little faith that the writers of the simulation will be creative enough to model the levels of real craziness out there.

Re:can't anticipate other driver stupidity (1)

epyT-R (613989) | about 2 months ago | (#47734609)

or random things that happen on the roads. Ice slicks, debris, that truck with the steel bar that's about to bounce off and land in front of you, etc..

Ooops! (3, Funny)

jd (1658) | about 2 months ago | (#47734597)

Found a bug in physics.c, those cars we mass produced last year will spontaneously explode after 367 days of exposure to an atmosphere containing oxygen, or when white lines are painted rather than vinyl, or when attempting a corner of a prime number of degrees when speeding on a cambered road.

Why wasn't this spotted sooner?

Because we hadn't expected to need chemistry or non-Euclidian geometry in a physics engine.

Can't wait (0)

Anonymous Coward | about 2 months ago | (#47734733)

I can't wait for the giant ensuing lawsuits. Someone is going to die, and ensuing legal battle will finally take the media's eye off of, what, squirrel!!

beta (0)

Anonymous Coward | about 2 months ago | (#47734739)

Are these cars going to have a big 'beta' sticker on them the way the simple "type a word here and we will try to find a relevant web page" text box did for ten years or so?

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?