U. Michigan Opens a Test City For Driverless Cars 76
An anonymous reader writes: The University of Michigan has opened Mcity, the world's first controlled environment specifically designed to test the potential of connected and automated vehicle technologies that will lead the way to mass-market driverless cars. Mcity is a 32-acre simulated urban and suburban environment that includes a network of roads with intersections, traffic signs and signals, streetlights, building facades, sidewalks and construction obstacles. The types of technologies that will be tested at the facility include connected technologies – vehicles talking to other vehicles or to the infrastructure, commonly known as V2V or V2I – and various levels of automation all the way up to fully autonomous, or driverless vehicles.
At least it is a place that gets some snow... (Score:5, Insightful)
Re:At least it is a place that gets some snow... (Score:5, Interesting)
More than that ... they need to recruit some of the absolutely terrible drivers we've all seen, and send them into the mix to do their usual random shit.
Because I think it will demonstrate how this stuff will totally fall apart when non-connected vehicles are in the mix, and highlight that there is no way in hell the entire road infrastructure and all cars are going to be updated for this connected stuff.
This stuff all seems to assume the world will change to suit it and we'll spend huge sums of money to make the infrastructure work.
And that's simply not true.
Re: (Score:2)
"Somebody's got to go back and get a shit-load of dimes."
Re: (Score:1)
All the previous posts seem right on target. I'll add that the area is still too small. Maybe they (the US government, or whoever) should turn an old abandoned military base to be used for this sort of test. Some of those places are huge and completely abandoned. Just had to them any features lacking in it's original layout, to make it as real and inclusive as possible, and just populate it with vehicles from any car maker on navigation company requiring a perfect sandbox to play around with the technology.
Re: (Score:2)
Self-driving cars and fraud (Score:2)
THIS is why we need dash cams. Good ones, looking fore and aft with a wide enough view to deal with stuff like the cyclists and biker's lane splitting shenanigans.
Well, it's something that tends to be integrated into self-driving cars. Google has very good views of all the accidents it's cars have been in.
Since I don't reply to AC's:
1. Can't do much about cyclists other than to build your mirror a little more sturdy. On the other hand. Self driving car! It wouldn't have a mirror there, because it uses a camera & other systems, and isn't stuck in the 'driver' seat.
2. Given self-driving car reflexes, is going to result in them eating a lot of pavement for no
Re: (Score:2)
they need to recruit some of the absolutely terrible drivers we've all seen
I humbly volunteer.
Re: (Score:2)
The cars aren't connected to each other at this time, they just react to other drivers based on what they see, same as human drivers. Except much faster and without distraction.
Re: (Score:3)
... they need to recruit some of the absolutely terrible drivers we've all seen, and send them into the mix to do their usual random shit.
As someone who frequently drives in the Ann Arbor area, I suspect they have been recruiting for decades.
Re: (Score:3)
Yes, because the terrible drivers we have all seen are not causing accidents as it is.
Every time I see a discussion about autonomous cars, someone chimes in that there are terrible human-driven cars on the road, and that an autonomous vehicle cannot deal with that. What they fail to mention is that no human drivers can really deal with them either, if the terrible driver is driving so badly that an accident is bound to happen.
Bad drivers causing accidents because they are on the cell phone? Yep. Bad drivers
Re: (Score:3)
why have a camera in the car to determine the color of the light when the intersection can just broadcast directly to vehicles?
Not sure I want to need a firewall and strong encryption on my car though ...
Re: (Score:3)
Re: (Score:1)
Implementing a driverless vehicle network that survives incomplete participation is easy. Just use ipv6.
--
Abandon all hope, ye who press ENTER here.
Why? (Score:1)
Gary, Indiana, would have been perfect.
Re: (Score:2)
>> Gary, Indiana
Unless you equipped it with a weapons system, I'd expect to see nothing but a steel chassis 400 yards from the starting point.
(And WTF is with the top-of-screen page refreshes now, Dice? I suspect it has something to do with the cheesy side videos...)
Re: (Score:2)
(And WTF is with the top-of-screen page refreshes now, Dice? I suspect it has something to do with the cheesy side videos...)
I finally got irritated enough to disable ads today. Here's a greasemonkey script that knocks out the flash/html5 ones.
var remove_classes=['railad', 'adwrap'];
for(var i=0; i<remove_classes.length; i++) {
var nodes = document.evaluate("//*[@class='" + remove_classes[i] + "']", document, null, XPathResult.UNORDERED_NODE_SNAPSHOT_TYPE, null);
for(var j=0; j<nodes.snapshotLength; j++) {
nodes.snapshotItem(j).parentNode.removeChild(nodes.snapshotItem
Re: (Score:2)
(And WTF is with the top-of-screen page refreshes now, Dice? I suspect it has something to do with the cheesy side videos...)
Cheesy side videos?
Dang, I love ScriptSafe ...
Just curious. (Score:1)
Re: (Score:2)
Or when there's a detour which technically takes you off the road. Or when there's an enormous puddle. Or a half a foot of snow. Or black ice. Or people who drive on your side of the road into oncoming traffic because there's something on their side. Or that guy I saw turn left from the straight lane the other day. Or when that driver next to you drifts into your lane.
The number of corner cases is simply staggering. And the chance they'll miss a bunch is pretty high.
If they just create a little test
Re: (Score:1)
This just in, new technology not ready to be used in every circumstance.
Yes, there are many problems. Let's find the ones we can on the test track and move to the next step. No one is saying that a successful lap around this track means we should start selling them.
Re: (Score:3)
They do the same thing as a human? Treat it like a four way stop.
I'm confused. Will they do what humans do, or treat it as a four-way stop?
Re: (Score:2)
Hell. Most human drivers I've seen recently don't know what to do.
Re: (Score:2)
Ethernet contention rules. Wait a random time, if none of the others are going, proceed. If another car starts going before, wait, if at the same time, both stop and wait a random time again.
What can possibly.... (Score:2)
....go wrong with v2v communication?
All it would take it 1 compromised vehicle to gain access and cause complete and utter chaos.
Humans, for all their faults, are for the moment still not remotely hackable. Until this changes, I do not see automated vehicles becoming the norm any time in the foreseeable future.
Unfortunately I think it will take a major disaster before the majority of people realize this.
Re: (Score:2)
Yes, but that's a social hack, not a technological one.
Re: (Score:2)
Re: (Score:2)
You don't need autonomous vehicles or v2v communication for them to be hack able and cause major disasters.
I think the point is not that you need to have v2v/autonomous stuff, but that the problem becomes much more serious when you do. When there's a driver behind the wheel you have some backup; when the passenger is asleep and/or the car has no controls you don't.
Re: (Score:2)
All it would take it 1 compromised vehicle to gain access and cause complete and utter chaos.
This seems rather likely as my server is constantly being probed for exploitation by something at the University of Michigan.
Re: (Score:1)
Oh, come now, it's not like any decent hacker can compromise an automated car in under 10 seconds.
Oh.
Wait.
Why create a model city? (Score:5, Interesting)
Just use Detroit: it's full of real roads and building, full of perils, and many parts of the city are virtually devoid of people.
Re: (Score:2)
Of course there are no people. Look what happened to all the pedestrians.
https://www.youtube.com/watch?... [youtube.com]
Good it's about time (Score:2)
It's hard enough doing simple things like straight line freeway driving that it's seen as a major accomplishment when no one dies and they can out do drunk a
Re: (Score:2)
citation given. MIT knows autonomous cars. I was suggestion google is the best car, which is ok on freeway but is not ready for unassisted neighborhoods and it's not even by google admission. Not for 10 years at least in my opinion. It's a total fail at a very very long list of things.
Re: (Score:2)
The grandparent was challenging the specific claim YOU made that SDC's get rear-ended because they stop too often.
The article you linked doesn't even mention any of the collisions the SDC's have been involved in, and certainly don't support the claim you made about them.
Try again.
Ok mr coward here are the actual citations, I was quick to post and put the wrong post above. Too many hipsters with common place movie knowledge and not actual engineerinrg knowledge so here you go I hope someone actually reads this that will appreciate facts.
The number of miles that google cars have driven so far including its safety record as stated by google directly : http://venturebeat.com/2015/06... [venturebeat.com]
This equates to an accident every 90.9 thousand miles though https://en.wikipedia.org/wiki/... [wikipedia.org] th
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
And then the human driver gets lost in thought (or tired, or angry, or distracted, etc. etc.) and crashes anyway, as they are intrinsically terrible at driving.
You should heed your own advice - if anecdotal stories are not evidence, what does that make your ass-delving hypothetical situations and guesses?
Re: (Score:2)
Re: (Score:3)
It goes from Google, who is extremely professional, but still gets rear ended a lot because the vehicle is over cautious
Troll much?
Anyone in the field gets an immediate appreciation of how their toddler far exceeds a supercomputer and 500k in sensors even in 2015.
Last I checked toddlers can't drive a car, sunny highway conditions or not.
etc. when a computer 'sees' a cyclist they may or may even not recognize its a cyclist (ie maybe it assumes pedestrian given its sensor history)
Actually, they've already learned to recognize hand signals that indicate where they're going.
If you look at any of the videos where they show the cars "vision" of the world it does a damn good job of tracking cars, trucks, pedestrians and cyclists, spotting them in plenty time. You're right they don't do subtler things like make eye contact or consider if the person is drunk, but they're probably good at spotting someone
Re: (Score:2)
It goes from Google, who is extremely professional, but still gets rear ended a lot because the vehicle is over cautious
Troll much?
Not a troll it's been rear ended 14 times, and although it's mostly been attributed to in attention, numerous admissions from google show that the car is overly cautious and will often stop in videos I have seen where humans won't.
Anyone in the field gets an immediate appreciation of how their toddler far exceeds a supercomputer and 500k in sensors even in 2015.
Last I checked toddlers can't drive a car, sunny highway conditions or not.
Last I've seen the best super computer clusters in the world coupled to the best sensors available anywhere and unlimited amounts of programming and algorithms cant self learn slam, pattern recognition and numerous complicated algoritms like a 2 year old can with two crappy cameras, dual three axis accelerometers dual stereo microphones and some touch and thermal sensors.
etc. when a computer 'sees' a cyclist they may or may even not recognize its a cyclist (ie maybe it assumes pedestrian given its sensor history)
Actually, they've already learned to recognize hand signals that indicate where they're going.
If you look at any of the videos where they show the cars "vision" of the world it does a damn good job of tracking cars, trucks, pedestrians and cyclists, spotting them in plenty time. You're right they don't do subtler things like make eye contact or consider if the person is drunk, but they're probably good at spotting someone swerving in their lane which is the second best thing.
Fact is, I don't know WTF some people are trying to do. I just keep my distance and speed such that I don't end up in a collision with them. So will presumably the Google car, here's a loose cannon on deck that doesn't drive like the other 95% so just give it a wide berth. You really don't have to figure them out to drive safely, you just need to recognize the signs to spot them.
Exactly I see you at least have a basic working understanding of the state of the art. Yes there has been some work on hand signals and even sign reading by google. But they can't even do as well as an average driver much less a decent attentive one. As you said you need to recognize the signs to spot them and these systems cannot do this reliably yet. I suggest you voulenteer on this course because I for one sure as hell don't want my children on public roads with jackass college kids and thier junk bo
Related News (Score:2)
Seems Legit (Score:2)
This, just two hours after the headline of "Remote Exploit On a Production Chrysler To Be Presented At BlackHat"
SEEMS LEGIT!
Seriously though, I'm all for automation, communication between devices, and anything else that can help optimize any system out there (this being the transportation system as a whole, not just the internal computer system within a single vehicle) - BUT we need some serious security and accountability. We've seen serious issues with cell phone manufacturers delaying security updates by
Wouldn't a Retirement Community make More sense? (Score:1)
Seriously, why should automated cars be operating in places where kids on bikes and skateboards and pets exist?
Automated cars might make sense in secure retirement communities, where everyone is 55 and nobody minds if they die.
Re: (Score:2)
Get in touch when you turn 55. Let's see how ready to die you are.
Re: (Score:2)
If you want a real world test, it has to be where kids, with or without bikes and boards, and pets dart in and out of traffic. Some of the 55 y/os might be dumb enough to do that, but they're too slow to make it a proper test.
Re: (Score:1)
Why are we testing on humans?
Now, hamsters ...
Re: (Score:2)
Seriously, why should automated cars be operating in places where kids on bikes and skateboards and pets exist?
Because reaction times measured in the milliseconds are handy at avoiding hitting them when they dart into the road, much better than people with reactions upwards of a full second?
Did you say Rome, Italy? (Score:1)
Now that's driving.
First time they deploy these in public, some small kids will get killed and it's game over for the auto companies. Parents with dead kids don't ever forget.
Ever.
Re: (Score:1)
Autonomous cars arent going to be better than humans at everything, but in the long run they will have far fewer crashes because they pay attention 100% of the time and have fast reaction times.
Humans are terribly unreliable. Yes they can foresee some certain types of incidents, but only if they are paying attention, aren't using their phone, driving drunk, putting on make-up, screaming at their own kids in the back seat, eating, of about a dozen other things that make humans terrible drivers regularly.
Re: (Score:2)
Then Google can teach the cars to do just that. You seem to think there are things these cars can't even conceive of, which is patently nonsense as they are trained by humans. If there is a great way to behave in a certain situation, the car can be trained to do just that, but with its far superior reaction times.
Try your test with human drivers and see how many toddler dummies you get through.
Will Mcity get gridlocked like A2 on Fball Sats? (Score:2)
They have a real football coach to test all this with, too?
I can only hope (Score:1)