×

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!

Ford Self-Driving R&D Car Tells Small Animal From Paper Bag At 200 Ft.

samzenpus posted about 4 months ago | from the where-you-going? dept.

Transportation 207

cartechboy writes "Autonomous driving is every car manufacturer's immediate R&D project. In car-building terms, even if a new technology isn't due for 10 years — since that's just two full vehicle generations away-- it has to be developed now. So now it is for autonomous car research and testing, and this week Ford revealed a brand new Fusion Hybrid research vehicle built for autonomous R&D with some interesting tech capabilities. Technologies inside the new Fusion Hybrid research vehicle include LIDAR (a light-based range detection), which scans at 2.5 million times per second to create a 3D map of the surrounding environment at a radius of 200 feet. Ford says the research vehicle's sensors are sensitive enough to detect the difference between a small animal and a paper bag even at maximum range. More road-ready differentiations include observation and understanding of pedestrians, cyclists, and plain old stationary objects. Ford is working on this project in cooperation with the University of Michigan."

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered

207 comments

I'm waiting for autonomous taxis being everywhere (1)

hawkinspeter (831501) | about 4 months ago | (#45678719)

So, it has come to this.

Re:I'm waiting for autonomous taxis being everywhe (3, Funny)

Rosco P. Coltrane (209368) | about 4 months ago | (#45678767)

Autonomous taxis already exist: you tell the driver to go the shortest or quickest way, and the driver almost always ignores you and chooses the least direct, more gridlocked route instead, all by himself

Also, you don't have to drive the taxi yourself.

Re:I'm waiting for autonomous taxis being everywhe (4, Insightful)

PolygamousRanchKid (1290638) | about 4 months ago | (#45678917)

I've ridden in a lot of taxis recently in the UK, Belgium, the Netherlands, France, Germany and Greece. I would miss having a live driver to tell me all the gossip in the city. Taxi drivers are always the most informed folks in any city. They can tell you who the mayor is sleeping with and where he buys his drugs.

The NSA shouldn't pay employees to play online games. They should have them drive around in taxis and talk to the drivers. Taxi drivers would make the best intelligence network.

Re:I'm waiting for autonomous taxis being everywhe (1)

gl4ss (559668) | about 4 months ago | (#45678931)

and in any other country a real driver means haggling for the friggin price, fighting to find a cabbie that will take you 15km out of the city and the cabbie not having a fucking clue about where anything is in the city(except nightclubs he gets commission from), since the cabbie is cheap labor imported from the rural area outside the city...

Re:I'm waiting for autonomous taxis being everywhe (0)

Anonymous Coward | about 4 months ago | (#45678989)

When I was living in London, we'd always use unlicensed mini cabs to get back from clubs - mainly because they didn't know where they were going - it meant you could haggle to get the price down to well below what it should be*. Also, the look of their faces when they realise they have no idea how to get back to Souff London from Stoke Newington because you had direct them at every turn.

* Could also be fun getting prices
M: Hi, how much to Central Street?
T: Um, £15?
M: Look at that sign over there.

Re:I'm waiting for autonomous taxis being everywhe (0)

hawkinspeter (831501) | about 4 months ago | (#45678957)

And I've found some taxi drivers to be borderline racist and complain continuously about the "bloody immigrants".

Re:I'm waiting for autonomous taxis being everywhe (2)

ebno-10db (1459097) | about 4 months ago | (#45679105)

You won't hear that in NYC.

Re:I'm waiting for autonomous taxis being everywhe (1)

hawkinspeter (831501) | about 4 months ago | (#45679127)

Probably not, but then I'm in the UK and sound doesn't travel that far.

Re:I'm waiting for autonomous taxis being everywhe (1)

oobayly (1056050) | about 4 months ago | (#45678969)

Taxi drivers like to think that they are always the most informed folks in any city

Re:I'm waiting for autonomous taxis being everywhe (0)

Anonymous Coward | about 4 months ago | (#45678831)

Why do you want them everywhere?

Re:I'm waiting for autonomous taxis being everywhe (1)

hawkinspeter (831501) | about 4 months ago | (#45678977)

So that whereever I am, I can choose to get the taxi and it'll be right there.

Re:I'm waiting for autonomous taxis being everywhe (1)

Big Hairy Ian (1155547) | about 4 months ago | (#45679275)

I'm just waiting for someone to hack the ****s who double park and get their self driving cars to park in the canal!

Slashvertisement (-1)

Anonymous Coward | about 4 months ago | (#45678731)

They don't even try to hide it anymore.

Mis-read the title (2, Funny)

Maow (620678) | about 4 months ago | (#45678739)

I read it as "Ford Self-Driving R&D Car Smells Small Animal From Paper Bag At 200 Ft." and my first thought was, "What the hell kind of test is that?!?"

Split second later, "Waaiit a second, that can't be right."

But hey, my truck smells like a small animal in a paper bag - from 2 years ago.

*goes back to sleep*

Re:Mis-read the title (0)

Anonymous Coward | about 4 months ago | (#45678835)

EPA has announced the winners of the 2013 Presidential Green Chemistry Challenge Awards! Every year for the past twenty years, in partnership with the American Chemical Society, EPA sponsors the Presidential Green Chemistry Awards to promote and reward innovative Green Chemistry technologies. These new technologies developed by industrial pioneers and leading scientists across the nation contribute to the use and manufacture of safer more sustainable chemicals, helping to solve some of our most pressing environmental problems.

This year’s winners are Professor Richard P. Wool, at the University of Delaware, Faraday Technology Inc., in Clayton, Ohio, Life Technologies in Austin, Texas, Dow Chemical Company in Collegeville, PA, and Cargill, Inc. in Brookfield, WI.

Re:Mis-read the title (0)

Anonymous Coward | about 4 months ago | (#45679371)

Lern tu reed

Yes but (5, Funny)

Rosco P. Coltrane (209368) | about 4 months ago | (#45678743)

Can it tell if the small animal is *inside* the paperbag? I'm thinking of cats specifically. Cats and paperbags... cat lovers know what I'm talking about.

Re:Yes but (0)

Anonymous Coward | about 4 months ago | (#45678789)

Can you? But more importantly, can the software behind the sensor determine if it's a cat or a bag? We've got awesome hardware and good object detection techniques, but humans are excellent at object detection. We do it faster than we can consciously perceive it (citation: the articles of the military having people watch images flashing by and using software watching the person's brainwaves to determine if the images contain something interesting). Current object detection also requires training images. How many cat bags found on roadways videos do we have? At lot of the latest impressive object detection examples only specify if an item is in the image, not where that item is.

I don't have a clue about the state of the art for 3D model matching, only static 2D images.

Re:Yes but (0)

Anonymous Coward | about 4 months ago | (#45678791)

I sure do... Some people spend big money on cat toys, when all they need is a paper bag to have some SERIOUS fun :D

Re:Yes but (1)

Anonymous Coward | about 4 months ago | (#45678803)

Bags are the world's top predator. As ants farm aphids, bags farm humans, using us to help produce more of them than we could ever breed of ourselves. Even the world's best designed predator - the cat - is putty around bags: the plastic ones scare them, and the paper ones seduce them. While complex hydrocarbons do rule the roost, Adams' scapegoating of mice was unjustifiably vivicentric.

Re:Yes but (1)

PolygamousRanchKid (1290638) | about 4 months ago | (#45678887)

I'm thinking of cats specifically.

Actually, I was thinking more Monty Python "Four Yorkshire Men":

"When I was a lad, we lived in a paper bag in the middle of the road . . ."

Have you seen the dark? (-1)

Anonymous Coward | about 4 months ago | (#45678757)

Have you been saved by Satan? Joun us and be one of the chosen.

salt and de-icer (4, Insightful)

hunter44102 (890157) | about 4 months ago | (#45678763)

lets see what it can detect in the Northeast after 2 days of snow, salt and de-icer puts a 'film' of gunk covering 90% of the vehicle

Re:salt and de-icer (1)

Rosco P. Coltrane (209368) | about 4 months ago | (#45678781)

You miss a crucial point : no small animal will be out and about when it snows in the northeast - and paperbags will get soggy in a hurry too - so the detection feature is not needed in those conditions.

Re:salt and de-icer (1)

dugancent (2616577) | about 4 months ago | (#45678825)

That's a good point. My car currently looks like it's covered with dirty white sand and it's get covered with snow when I drive. My backup camera is useless unless I clean it every time.

Re:salt and de-icer (0)

Anonymous Coward | about 4 months ago | (#45678893)

If that's a common issue then I'm surprised auto manufacturers haven't yet offered a windscreen-wiper-like device to clean to sensor. I would expect production versions of self-driving cars to have similar cleaners for their sensor suites.

Re:salt and de-icer (1)

ebno-10db (1459097) | about 4 months ago | (#45678991)

lets see what it can detect in the Northeast after 2 days of snow, salt and de-icer puts a 'film' of gunk covering 90% of the vehicle

Northeast. What about Michigan? At least this is being developed by people who don't live in sunny California. Seriously, that may have an effect. I keep asking how Google cars do in a rainstorm, but they don't seem to understand the concept.

OTOH, if the ability of a car to handle various types of weather reflects where the designers live, then why were most American cars for many years so bad in the snow? Seriously, never figured that out. US cars were amongst the last to adopt FWD (although IIRC Mercedes & BMW were even later - what, it doesn't snow in Germany?). The only thing I can think of was that it was the triumph of the marketing department, which thought that cars should compensate for various sexual inadequacies. Left to themselves, the engineers would probably have come up with something that handled even the unlikeliest weather - like snow in Michigan.

Re:salt and de-icer (2)

somersault (912633) | about 4 months ago | (#45679157)

I love RWD in the snow. I'd say the width of your tyres mattes more than the drive system. It also depends how much snow you get I suppose. Snow is never a problem for me, but ice can really suck when it's on an incline (as in the car park at my last flat, where I had a lot of fun trying to get going some days..).

Re:salt and de-icer (1)

ebno-10db (1459097) | about 4 months ago | (#45679357)

I love RWD in the snow.

Why? FWD has better traction because more weight is over the drive wheels, and it's more stable (when rear drive wheels slip the car fishtails). As for tire width, I never noticed that. The cut of the tread is another matter. We usually have only moderate snow here in the NYC area (though a few feet once in a while) so with modern all-weather tires I don't bother with snow tires. If you do get real snow tires though, they work great (used to use them before all-weather tires were as good as they are today).

It also depends how much snow you get I suppose.

How much snow do you get? I presume you're in the UK. I don't think of it as very snowy, but I'm hardly sure.

ice can really suck when it's on an incline

It all depends - it's very easy to get going downhill.

About the only problem I know of with FWD in slippery conditions is that the weight gets transferred to the rear when going uphill. If you can't make it the regular way though, you can always drive backwards (seriously - I live on a hill and it works great).

Re:salt and de-icer (2)

somersault (912633) | about 4 months ago | (#45679501)

Why? FWD has better traction because more weight is over the drive wheels, and it's more stable (when rear drive wheels slip the car fishtails)

Well, for one thing, I enjoy drifting/fishtailing when it's raining or there's snow (I only do that if there aren't other cars around though). Having weight over the drive wheels is pretty good for grip yes, but having the drive wheels also doing the steering is not a good thing, especially in unexpected situations. I suppose that a driver that's aware of the limitations of their vehicle will always fare better in poor weather than someone who knows nothing about drive systems and weight distribution, so it just comes down to preference. I prefer RWD (even over all wheel drive).

With thinner tyres, your car is more likely to sink through the snow and get better grip. It's perhaps bad in really deep snow, I wouldn't know.. but for the less than a foot of snow that we usually have on UK roads, it's definitely better with thinner tyres. I've never used real snow tyres, so I don't know about them.

Re:salt and de-icer (3, Informative)

MightyYar (622222) | about 4 months ago | (#45679179)

Jeep? That's a pretty American brand. :) Most of the time a rear-wheel drive vehicle with some extra weight in the trunk and a set of snow tires was pretty decent in the snow. My dad is from Pittsburgh, and if he could get around snowy hills with that configuration, I'm pretty sure other folks could too.

Four wheel drive was complicated and expensive, and you ended up with an extra bulge and shifter on your floor. FWD was and is pretty crappy for handling in all of the rest of the year, with a few standout exceptions. FWD is cheaper and gives you a flat floorpan - that is the primary reason why it was adopted.

Re:salt and de-icer (1)

gstoddart (321705) | about 4 months ago | (#45679261)

FWD is cheaper and gives you a flat floorpan - that is the primary reason why it was adopted.

Well, it's supposed to be cheaper on gas since the engine is pulling you forward instead of pushing.

But, I've been in a few North American cars which, despite being FWD, have a big hump going through the middle for no good reason, the same as if there was a drive shaft to the rear wheels.

It made absolutely no sense, and the only thing I can figure is the car company decided it would be more expensive to retool the plant to actually give this flat floorpan.

I've also seen several cars which still more or less put in a rear axle (even if it's not a drive axle) when you'd be better using independent suspension. The Pontiac Aztec and I think some of the Dodge minivan type things are good examples of this.

Except for at the higher end, some car companies are lazy, stupid, and cheap. And you still end up with a senseless hump in between the rear passenger seats, or a ride which is made silly by having a rear axle (try driving over a speed hump diagonally in a vehicle which has an axle, you'll see that the whole vehicle moves when it doesn't really need to).

Re:salt and de-icer (1)

ebno-10db (1459097) | about 4 months ago | (#45679411)

Well, it's supposed to be cheaper on gas since the engine is pulling you forward instead of pushing.

Never heard that one, although I think the extra friction of the drive shaft is a very slight inefficiency. FWD cars also weigh slightly less too, due to the absence of a drive shaft and separate differential housing.

I've been in a few North American cars which, despite being FWD, have a big hump going through the middle for no good reason, the same as if there was a drive shaft to the rear wheels

Were those models available in 4WD or AWD? They might have just used the same floor pan for both. Still a bit sloppy, but marketing probably figures if you have the hump anyway, you're more likely to pay the extra for AWD.

Re:salt and de-icer (1)

ebno-10db (1459097) | about 4 months ago | (#45679473)

My dad is from Pittsburgh, and if he could get around snowy hills with that configuration ...

It's not just a question of whether you can, but which is the preferable approach.

Four wheel drive was complicated and expensive

Agreed. AWD is very popular these days, but unless you live in a very snowy area it doesn't make sense. I don't need two extra differentials, two extra half-axles, and 6 extra U-joints (the last being the most likely source of trouble).

FWD was and is pretty crappy for handling in all of the rest of the year, with a few standout exceptions.

If there are a few standout exceptions, it proves it's not an inherent problem with FWD. The whole "bad handling" thing just isn't an issue in the 21st century, unless you have a serious sports car or something (and actually drive it as such). Having left the Formula 1 circuit, I don't have problems in dry weather. Hence whatever small handling or traction issues there are w/ FWD in the dry, is more than compensated for by the superiority in rain and snow.

ONE independent demo, please (0)

Anonymous Coward | about 4 months ago | (#45678769)

All this self-driving car news is very hep for geeks an' all, but all of it - including stuff from Google - comprises press releases and footage from the companies involved. And, for some reason, despite the non-existent track record of all these firms when it comes to creating self-driving cars, we believe everything they have to say. What has happened to the passion for academic rigo(u)r that geeks used to enjoy? Has it really been replaced by the new religion of marketing?

I will believe that there is an even remotely usable self-driving car in existence when I see ONE independent evaluation of these cars being taken through a real world driving scenario: my choice would be a commuter route along the south coast of England, starting somewhere in the centre of Brighton, taking the main roads up to the M25, round to the Dartford tunnel, then negotiating the centre of London, stopping just outside the Houses of Parliament. And nobody on the company payroll would be allowed n the car, nor to give ANY remote feedback. Just like, you know, real autonomous driving.

Re:ONE independent demo, please (1)

rodrigoandrade (713371) | about 4 months ago | (#45678813)

Well, it's not like Consumer Reports can just go out and buy one of these self driving cars to test them out yet.

This is all very early research and we have to take their word for it for the time being.

Once they become commercially available, I definitely expect to see vastly different real-world performance of theses systems.

Re:ONE independent demo, please (0)

Anonymous Coward | about 4 months ago | (#45678879)

"...and we have to take their word..."

Unlike every other research endeavour, we have to take the word of the companies which stand to profit from some creation? BS. Give me one of them to drive through the winding country roads of Sussex, and I'll get back and tell you whether it slows down because of that fallen branch just round the blind turn which I was just warned about (just next to the pothole), or can hear the sounds and read the movements of horses to know how much space to give them.

Inter-state driving in the US along the main roads is incredibly enjoyably easy. Even driving through a modern US city is a walk in the park (wait what) compared to pretty much anywhere in the world.

"...I definitely expect..."

Given sufficient time, I also definitely expect technology to get vaguely better.

Re:ONE independent demo, please (4, Insightful)

somersault (912633) | about 4 months ago | (#45678897)

They don't stand to profit from anything right now, this is just news about a research project. If you are annoyed at the lack of product reviews for a product that doesn't even exist yet, maybe you should stop reading tech news sites.

Re:ONE independent demo, please (1)

somersault (912633) | about 4 months ago | (#45678851)

The difference is that these articles are about research projects, not final products. This one doesn't even say that the car moves, just that it can detects things. So it's probably about one student's project into computer vision.. no, I haven't RTFA :p

Re:ONE independent demo, please (1)

ebno-10db (1459097) | about 4 months ago | (#45679019)

I will believe that there is an even remotely usable self-driving car in existence when I see ONE independent evaluation of these cars being taken through a real world driving scenario

I agree, as (despite your previous paragraph) do many of the people here (e.g. hunter44's comment above). I don't actually expect independent evaluations of this stuff, as the details are very proprietary, but it would be interesting to have claims beyond Google's "300,000 miles without an accident". That means little unless weather and traffic conditions, etc., are specified.

my choice would be a commuter route along the south coast of England ...

Bah, our traffic, weather, drivers and roads are way worse than yours. That's a generic statement. A person from anywhere except southern England is expected to say that. Odd point of pride, isn't it?

Re:ONE independent demo, please (1)

digitig (1056110) | about 4 months ago | (#45679057)

I suspect the biggest issue isn't technical. At the moment, if a driver drives full speed into a line of kids crossing the road it's the driver who ends up in court. If it's an autonomous self-driving vehicle, it's likely the vehicle manufacturer who ends up in court.

I don't expect the lawyers to allow these vehicles on the road in my lifetime.

Moore's law (1)

spectrokid (660550) | about 4 months ago | (#45678865)

If production is 10 years from now, we will have hit the concrete wall by then. 2.5 million scans per second is not going to get processed by a 10$ chip. It will be interesting to see how the end of Moore's law will affect this and similar projects.

Re:Moore's law (3, Interesting)

ebno-10db (1459097) | about 4 months ago | (#45679029)

It will be interesting to see how the end of Moore's law will affect this and similar projects.

Maybe programmers will learn the nearly lost art of writing efficient code.

Re:Moore's law (2)

rally2xs (1093023) | about 4 months ago | (#45679237)

The production of the flying car has always been just 10 years in the future, for about 60 years now. Wonder if this is the same situation.

Re:Moore's law (1)

ebno-10db (1459097) | about 4 months ago | (#45679527)

Probably so. Of course in the 60's they also predicted that flat screen TV's were 10 years in the future, so maybe we'll eventually get it.

Noise (4, Interesting)

jklovanc (1603149) | about 4 months ago | (#45678873)

I wonder about all these active technologies; lidar, radar, ultrasonic, etc. They work very well when there is only one vehicle in the area. What happens on a crowded freeway when there are a couple hundred vehicles an the area pumping out all those emissions? Wouldn't it be difficult to differentiate between returns due to your emitters and the emitters from other vehicles? Unless each emitter is working on a different frequency interference is a possibility. There is also the issue of sensors being sensitive enough to detect return but filtered enough not to be dazzled by the direct emissions from other vehicles close by.

Re: Noise (0)

Anonymous Coward | about 4 months ago | (#45678889)

By "emitters from other vehicles" you mean the bored passenger with a laser pointer?

Re: Noise (1)

jklovanc (1603149) | about 4 months ago | (#45678937)

I mean the other autonomous vehicles on the road with their active ranging technologies. If every \car on the freeway is autonomous there are a lot of emitters.

Re:Noise (0)

Anonymous Coward | about 4 months ago | (#45678945)

I think it will be pretty scalable. Also, I expect that as these sensors become commonplace on vehicles and we get some joined-up-thinking between the manufacturers, the vehicles will start sharing data with one another - so your car will be able to shut down some of its sensors and instead partially rely on data being sent from the cars in front and behind. When *that* happens, we'll see sensors popping up in street furniture as well, beaming data to pasasing vehicles.

Also, don't know about Lidar and radar, but I'm pretty sure it's possible for lots of independent sonar sensors to operate successfully in a crowded area:

https://www.google.co.uk/search?q=a+million+bats&source=lnms&tbm=isch&sa=X&ei=Se-qUs6xB8eFtAb29YGYAg&ved=0CAkQ_AUoAQ&biw=1246&bih=730

https://www.google.co.uk/search?q=a+family+of+dolphins&espv=210&es_sm=93&source=lnms&tbm=isch&sa=X&ei=3_GqUoXGKcWbtQaTyYG4Bw&ved=0CAkQ_AUoAQ&biw=1392&bih=730

Re:Noise (1)

ebno-10db (1459097) | about 4 months ago | (#45679037)

your car will be able to shut down some of its sensors and instead partially rely on data being sent from the cars in front and behind

Oh, that'll be reliable. Adventures in propagation of sensor and processing problems from car to car. Cute science project though.

Re:Noise (1)

Anonymous Coward | about 4 months ago | (#45679061)

Ha ha, indeed. For some reason these armchair propeller-heads always mention sensor networks, vehicle-to-vehicle communication, etc. in any thread about autonomous cars.

But seriously: If you think it's going to be tough getting insurer and type-certificate approval for a self-driving car _as such_, just try floating the idea of a self-driving car that accepts / partially relies on (intermittent, unknown quality) third-party sensor data.

They'd laugh you out of the office!

Re:Noise (1)

jklovanc (1603149) | about 4 months ago | (#45679069)

Getting multiple vehicles to communicate and cooperate is a much more complex problem than individual vehicles navigating on their own. We have enough problems sharing data between PCs,,Macs and Unix devices and we have been trying for decades. Just try to get all manufacturers to agree on a data standard. It could take decades.

In both your examples the speeds are very different from vehicles and the consequences of collisions are non fatal. If a couple of bats collide they bounce. If a couple of vehicles collide they crash. There is also the probability that each animal can send out a slightly different signal and detect it. While active technologies can also do this it is an added layer of complexity.

Re:Noise (3, Interesting)

AmiMoJo (196126) | about 4 months ago | (#45679151)

It generally isn't a problem because single readings are never used. They are always averaged over time and combined with other sensors. They also pulse their output and can detect interference and adjust their timing randomly to avoid it.

Think about how many devices manage to share unlicensed radio spectrum and how few cars will be that close together. The reason for having so many sensors is that if any one fails the others can make up for it.

Of course it will still fail from time to time, but less than a human.

What are they really saying? (4, Insightful)

jklovanc (1603149) | about 4 months ago | (#45678911)

Ford says the research vehicle's sensors are sensitive enough to detect the difference between a small animal and a paper bag even at maximum range.

Given that the sensors can detect a difference here are some follow on questions that seem important.
1. Can it detect which one is the animal and which one is the bag? (they talk about difference not identification)
2. Can it tell if the small animal is alive or dead if it is not moving.
3. Can it tell if the animal is on a leash and not going to be an issue?
4. Can it detect if there is a barrier between the animal and the desired route of travel and the animal not being an issue?
5. Can it tell the difference between a turtle and a rabbit? Turtles having much more restricted movement possibilities than a rabbit.
6. Will it remember that the small animal went into the bag. Out of sight out of mind.
7. Can it differentiate between an empty bag and a bag of cement? Driving over an empty bag is not a problem. Driving over a bag of cement is probably a problem.
Detecting the difference between a small animal and a paper bag is important but it is only the first step in in a very complex decision process to determine what to do with that information.

Re:What are they really saying? (1)

captainpanic (1173915) | about 4 months ago | (#45678941)

What they are really saying is that they are programming their cars to identify an certain object, and in certain cases ignore it and just drive over it.

Ford: "We are terribly sorry our autonomous car ran over your baby. To the car it looked like a paper bag. Next time dress your child in brown fur, and we promise we'll go around it."

Re:What are they really saying? (0)

Anonymous Coward | about 4 months ago | (#45678995)

My answer to this is that it shouldn't matter.

A human driver should never intentionally run over anything. Even a plastic bag, seemingly harmless, may have something inside it; in fact that is their sole job. The bag may contain something that would damage your tyres and should be avoided if at all possible.

Re:What are they really saying? (4, Insightful)

ustolemyname (1301665) | about 4 months ago | (#45679031)

Bag: Should be avoided.
Baby: Should be avoided.

Bag: May involve gently changing direction, do not brake erratically, do not disturb flow of traffic.
Baby: May involve driving into the ditch, other traffic, making full use brakes, honking horn, etc.

You really think it doesn't matter?

Re:What are they really saying? (1)

Anonymous Coward | about 4 months ago | (#45679073)

I would put it to you that at the speeds a motor vehicle travels at it's impossible for a human driver to:

- Detect the object.
- Recognise the object as a baby.
- Be so close as to be unable to brake.
- Be so hemmed in by other traffic as to be unable to dodge.
- Be cognizant of the above two facts at all times, including when driving home after having a fight with the missus, bored, tired, momentarily distracted, etc.
- Make the moral and ethical decision to sacrifice oneself for a baby, decide how to do so, and then execute the manouver with minimal fuss.

I can back this up with a little example and some maths if you want. But as someone who hit a kangaroo yesterday, these things tend to happen so fast that you are more like "hey wha-THUMP." There was certainly no time to go "What's that? It's a thing. Let's look closer. It's a baby! It's a human baby. And I have nowhere to go. And I'm too close to brake. Wow, I guess I'd better assess my options and make a sane rational decision to drive into a ditch or whatever."

Re:What are they really saying? (1)

somersault (912633) | about 4 months ago | (#45679211)

I don't really mind that you killed a kangaroo, but I don't think it's valid to use the same logic in areas where there's a high chance of humans being near the road.

If you don't have time to detect and avoid someone/something you don't want to kill (or is illegal to kill) walking out from cars or other objects at the side of the road, and especially if you don't have time to detect something that's already on the road, you're going too fast for the conditions.

Re:What are they really saying? (1)

Anonymous Coward | about 4 months ago | (#45679319)

That wasn't my point. My point was that if there's time enough for a human driver to react, process the facts, and avoid the collision... the computer driver can do it too.

Re:What are they really saying? (1)

ustolemyname (1301665) | about 4 months ago | (#45679235)

I would put it to you that at the speeds a motor vehicle travels

Such as 10km/h?

I would put it to you that situations where one would have to make a bag/baby decision one should not be travelling at highway speeds.

Even though a perfect decision can't be made in every situation, I contend one can do better than, "Fuck it, I'll probably hit it regardless," when operating a motor vehicle.

As someone who has successfully prevented collisions with cats, deer, and moose under differing circumstances (a moose in fog at night is about the most frightening thing I've ever come across), I think the ability to inform ones driving based upon the nature of a sudden unexpected obstacle is a critical part of driving well.

Re:What are they really saying? (1)

jklovanc (1603149) | about 4 months ago | (#45679027)

The article does not say they can identify which is the bag and which is the animal it just says they can detect a difference. In an experiment where there was a paper bag and a small animal in the field of view of of the sensor there are at least two outcomes.
1. The sensor returns "there are two different kinds of objects out there". Therefore the sensor has detected a difference between a paper bag and a small animal. That is exactly what the claim states.
2. The sensor returns that object a is a paper bag and object b is a small animal. That would be identification and nowhere in the statement is there a claim of identification.
Had they meant the second outcome they should have said something like "The sensor can identify a paper bag and a small animal by their differences"
We often read too much into a statement and don't really think about what it actually said. It reminds me of one of my favorite mathematician jokes.

An economics professor, an Engineer and a mathematician are on a train to Glasgow.
The economics professor looks out the window and sees a field full of sheep and says "Wow, all the sheep in Scotland are black."
The Engineer look out and says "Some of the sheep in Scotland are black."
The mathematician looks out and says "In Scotland there exists at least one field in which the sheep are black on at least one side."
The mathematician is the most correct in that the statement is based on exactly what he saw. Only one field and only one side of each sheep.

Re:What are they really saying? (0)

Anonymous Coward | about 4 months ago | (#45679053)

The article does not say they can identify which is the bag and which is the animal it just says they can detect a difference. In an experiment where there was a paper bag and a small animal in the field of view of of the sensor there are at least two outcomes. 1. The sensor returns "there are two different kinds of objects out there". Therefore the sensor has detected a difference between a paper bag and a small animal. That is exactly what the claim states. 2. The sensor returns that object a is a paper bag and object b is a small animal. That would be identification and nowhere in the statement is there a claim of identification. Had they meant the second outcome they should have said something like "The sensor can identify a paper bag and a small animal by their differences" We often read too much into a statement and don't really think about what it actually said. It reminds me of one of my favorite mathematician jokes.

An economics professor, an Engineer and a mathematician are on a train to Glasgow. The economics professor looks out the window and sees a field full of sheep and says "Wow, all the sheep in Scotland are black." The Engineer look out and says "Some of the sheep in Scotland are black." The mathematician looks out and says "In Scotland there exists at least one field in which the sheep are black on at least one side." The mathematician is the most correct in that the statement is based on exactly what he saw. Only one field and only one side of each sheep.

If he were a Scottish mathematician he would certainly have seen the rear end of the sheep too.

Re:What are they really saying? (3, Funny)

Chrisq (894406) | about 4 months ago | (#45679063)

...The mathematician is the most correct in that the statement is based on exactly what he saw. Only one field and only one side of each sheep.

If he were a Scottish mathematician he would certainly have seen the rear end of the sheep too.

not just seen it!

Re:What are they really saying? (1)

Derec01 (1668942) | about 4 months ago | (#45679191)

All good observations, because I'm not so concerned about it avoiding one-off obstacles encountered serially as I am about the choices it makes between two bad options, like the braking path that goes through a small dog vs. a crawling toddler.

Re:What are they really saying? (1)

fnj (64210) | about 4 months ago | (#45679217)

Given that the sensors can detect a difference here are some follow on questions that seem important.
1. Can it detect which one is the animal and which one is the bag? (they talk about difference not identification)
2. Can it tell if the small animal is alive or dead if it is not moving.
3. Can it tell if the animal is on a leash and not going to be an issue?
4. Can it detect if there is a barrier between the animal and the desired route of travel and the animal not being an issue?
5. Can it tell the difference between a turtle and a rabbit? Turtles having much more restricted movement possibilities than a rabbit.
6. Will it remember that the small animal went into the bag. Out of sight out of mind.
7. Can it differentiate between an empty bag and a bag of cement? Driving over an empty bag is not a problem. Driving over a bag of cement is probably a problem.
Detecting the difference between a small animal and a paper bag is important but it is only the first step in in a very complex decision process to determine what to do with that information.

My response to every single one of the questions except #1 and MAYBE two others is: "can any driver do so?".

Background: I once successfully avoided hitting a fox which darted into a deserted rural road suddenly very close ahead of me - but totalled the car due to a succession of improbable details. Ever since then I have ingrained a deliberate policy of NEVER braking or swerving to avoid small wild animals. I was lucky in that my lesson affected only me, and did not injure me. You can never be sure of that in general. No one can be sure 100% of the time, on zero time notice for checking, that his car is sufficiently isolated from other cars and people.

Another time I drove over what looked like a black line painted on the road, not to swerve into traffic. It turned out to be an X piece of construction staging which teetered and took out my gearbox. That one I repaired. I think I got comprehensive insurance coverage for it - "road hazard". I didn't second guess myself.

Re:What are they really saying? (0)

Anonymous Coward | about 4 months ago | (#45679631)

But the bad news is Ford went cheap on the brakes and it takes 201 feet to stop!

OMG, No! Not Ford! (2)

Wingsy (761354) | about 4 months ago | (#45678915)

I won't sit in a Ford with the engine running, and in the future it seems I won't get on the highway with Ford's self driving cars on the road. I'm terrified that there's going to be some leftover Microsoft code in there somewhere (i.e., from Sync).

Paper bag or animal. (0)

Anonymous Coward | about 4 months ago | (#45678921)

But can it detect a brick in a paper bag that youngsters put for fun on the street?

What could possibly go wrong? (1)

GauteL (29207) | about 4 months ago | (#45678955)

What happens when the car realises it doesn't need the driver to get around and could easily pop down to the local garage itself when it needs spare parts or petrol/electricity? Or when it gets tired of smelling faintly of sick, or having its lovely seat fabric ruined by small humans?

And if it can tell a paper bag from a small animal from 200 ft, perhaps it can also distinguish a rubbish bin from a human so it knows WHICH ONE TO KILL?

I'm not saying this will happen, I'm just asking questions.

Future is good for the NSA (1)

mt1104 (3462603) | about 4 months ago | (#45678961)

Imagine all these self driving cars networked together... scanning a 200ft radius millions of times a second creating a effectively recorded 3d world. If there's enough cars, they could have a 3d record of most places - though admittedly storage would be an issue. Good luck trying to do ANYTHING wrong.

"Sorry, car 23034 identified you as speeding, here's your fine..."

On a lighter note, pretty good news for racing sim fans, getting details 3d scans of awesome roads won't be as difficult.

Re:Future is good for the NSA (0)

Anonymous Coward | about 4 months ago | (#45679025)

> though admittedly storage would be an issue

Bandwidth too. That's a hell of a lot of data to be sent to some central spy-house via some kind of wireless connection.

Then again, if you could go back in time 30 years and describe google earth to people, they would think it beyond the capabilities of even the most optimistic sci-fi technology. These days I'm very reluctant to say "that's impossible" when it comes to data.

Paper jam (0)

Anonymous Coward | about 4 months ago | (#45678973)

Ford gave "Paper jam" a whole new meaning.

cool, but... (2)

Wasusa (1633263) | about 4 months ago | (#45678979)

200ft? That's about 60m. That puts it far to close to the ideal, best condition stopping distance of a car moving at about 60km/h. The software for detection isn't new, and ladar has had this sort of range for a while. Quintiple the range and keep processing real time, then it'll be worth news

Re:cool, but... (0)

Anonymous Coward | about 4 months ago | (#45679143)

It really isn't: the stopping distance at 60 km/h for a car with modern tyres and ABS, even with a human driving, is closer to 20m than it is to 60m. Without ABS and with cross-ply tyres you will get the "Highway code" distance of 36m, 1/3 of which is "thinking time" which should be reduced in an autonomous car as it has no need to move its foot from one pedal to the other.

The last time I tried it out, at Mercedes-Benz World Brooklands, we were stopping in around 50m from 113km/h. That was an E63 AMG on road tyres on a dry track.

What's Inside The Paper Bag? (1)

Bing Tsher E (943915) | about 4 months ago | (#45679111)

Just detecting the paper bag and differentiating it from a rabbit is really kinda irrelevant. What is inside the paper bag? It could be rabbit food (harmless little pellets) or it could be a trailer hitch. History shows that this is relevant.

Nope. (0)

Anonymous Coward | about 4 months ago | (#45679155)

This emerging technology is not working absolutely perfectly, therefore it never will. The recently released news of this advancement does not meet real-world worst-case scenarios, therefore we should lambast the manufacturers and researchers for pursuing what is obviously dead-end tech.

DUE? (0)

Anonymous Coward | about 4 months ago | (#45679189)

What makes a new technology "DUE" in 10 years, 15 years, at all?

Are we somehow obligated to a mandate?

I even RTFA and no answer on why the technology is due in 10 years.

Let's rush to market with this....wait...has somebody forgotten Google already has this?

"Bear fruit for real-world cars..." ??

Cool, but (1)

argStyopa (232550) | about 4 months ago | (#45679199)

While the whole system is very cool and 200' sounds like a lot, remember that at highway speeds, a car is covering ~100' per second, so 2 seconds to identify, contemplate, and react to that obstacle.

Logically, in oncoming situations (as a worst-case), two highway-speed vehicles 'detecting' at 200' have only about one second (actually less thanks to inertia, given that control-input and -effect isn't instant) to resolve, contemplate, and react.

I have to imagine the guys working on these systems are acutely aware driving home every day of how astonishingly capable our brains are.

Coincidence (1)

SirGarlon (845873) | about 4 months ago | (#45679223)

200 feet is just a tad under the distance required [csgnetwork.com] to decelerate from 65 mph to zero on dry pavement. In other words, the system gives gives enough advance warning so you know what you're about to gently bump into after screaming to a stop in a cloud of smoke. Or crash into, if the pavement happens to be wet.

I'd say 10 years to mass market is optimistic.

Re:Coincidence (2)

Virtucon (127420) | about 4 months ago | (#45679247)

Yeah but if it misinterprets a squirrel or a cat vs a plastic bag you're going to get a sudden deceleration you weren't expecting. When people are in charge you can determine that if it's a small animal which allows you to swerve or just use it as a speed bump.

OK, It Works, But What's Next (2)

rally2xs (1093023) | about 4 months ago | (#45679249)

The autonomous car detects a cat in the road, and then what does it do? Does it slam on the brake even tho you're doing 65 mph and there's an 18 wheeler 3 feet from your rear bumper? Does it try to brake and swerve even tho there's a glaze of ice on the road?

Can it tell a small animal inside a paper bag? (2, Funny)

140Mandak262Jamuna (970587) | about 4 months ago | (#45679289)

Well the Russians are way ahead of Ford. They drive around with dash cams all the while and their systems can not only tell a paper bag from a small animal, it can tell if there is a small animal inside the paper bag. Not only that, it would take that cute cat in a paper video and upload it to the click bait web site also has a drive by download malware. Sergey Gregorovich, the owner of the malware site, says, "My R&D investment in integrating small animal in paper bag detection technology with dash cam, auto upload and drive by download technologies have given me rich dividends".

Excellent (1)

machine321 (458769) | about 4 months ago | (#45679377)

I can't wait until Ford starts making hybrid fusion cars. We only have a couple of years to make Mr. Fusion happen.

Yes, but can it shift? (1)

TheloniousToady (3343045) | about 4 months ago | (#45679431)

I have a Ford Focus that features a computer-controlled manual transmission. So it's easy to drive, like an automatic, but gets somewhat better MPG, like a manual. Problem is, the computer often shifts it like somebody who doesn't know how to drive a stick. It used to stutter when backing up, but that got fixed via a software update in factory recall. (Hackers, here's a new attack vector.) Anyway, once they can get that right, then maybe they'll be ready to drive the whole car.

Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Sign up for Slashdot Newsletters
Create a Slashdot Account

Loading...