MIT Technology Review - Your Driverless Ride Is Arriving

WeirdBob

Well-Known Member
Uber thinks its self-driving taxis could change the way millions of people get around. But autonomous vehicles aren’t anywhere near to being ready for the roads.


by Will Knight | October 18, 2016

. . .

The three of these CMU robots show how gradual the progress toward self-driving vehicles was until recently. The hardware and software improved, but the system struggled to make sense of the world a driver sees, in all its rich complexity and weirdness. At NREC, I meet -William “Red” Whittaker, a CMU professor who led the development of Terregator, the first version of NavLab, and Boss. -Whittaker says Uber’s new service doesn’t mean the technology is perfected. “Of course it isn’t solved,” he says. “The kinds of things that aren’t solved are the edge cases.”

And there are plenty of edge cases to contend with, including sensors being blinded or impaired by bad weather, bright sunlight, or obstructions. Then there are the inevitable software and hardware failures. But more important, the edge cases involve dealing with the unknown. You can’t program a car for every imaginable situation, so at some stage, you have to trust that it will cope with just about anything that’s thrown at it, using whatever intelligence it has. And it’s hard to be confident about that, especially when even the smallest misunderstanding, like mistaking a paper bag for a large rock, could lead a car to do something unnecessarily dangerous.

. . .

Still, the edge cases matter. The director of NREC is Herman Herman, a roboticist who grew up in Indonesia, studied at CMU, and has developed automated vehicles for defense, mining, and agriculture. He believes self--driving cars will arrive, but he raises a few practical concerns about Uber’s plan. “When your Web browser or your computer crashes, it’s annoying but it’s not a big deal,” he says. “If you have six lanes of highway, there is an autonomous car driving in the middle, and the car decides to make a left turn—well, you can imagine what happens next. It just takes one erroneous command to the steering wheel.”

. . .

Another problem Herman foresees is scaling the technology up. It’s all very well having a few driverless cars on the road, but what about dozens, or hundreds? The laser scanners found on Uber’s cars might interfere with one another, he says, and if those vehicles were connected to the cloud, that would require an insane amount of bandwidth. Even something as simple as dirt on a sensor could pose a problem, he says. “The most serious issue of all—and this is a growing area of research for us—is how you verify, how you test an autonomous system to make sure they’re safe,” says Herman.

. . .

I get to experience the reality of the technology’s limits firsthand, about halfway through my ride in Uber’s car, shortly after I’m invited to sit in the driver’s seat. I push a button to activate the automated driving system, and I’m told I can disengage it at any time by moving the steering wheel, touching a pedal, or hitting another big red button. The car seems to be driving perfectly, just as before, but I can’t help noticing how nervous the engineer next to me now is. And then, as we’re sitting in traffic on a bridge, with cars approaching in the other direction, the car begins slowly turning the steering wheel to the left and edging out into the oncoming lane. “Grab the wheel,” the engineer shouts.

Maybe it’s a bug, or perhaps the car’s sensors are confused by the wide-open spaces on either side of the bridge. Whatever the case, I quickly do as he says.
 

WeirdBob

Well-Known Member
Robotics
My Self-Driving Uber Needed Human Help

A test ride in a semiautonomous taxi in Pittsburgh shows the technology is not quite ready.




by Will Knight | September 14, 2016

https://www.technologyreview.com/s/602351/my-self-driving-uber-needed-human-help/

A handful of people who order Ubers in Pittsburgh this morning will discover that their driver is less chatty than usual. And like those lucky riders, I got to experience being chauffeured around town in one of the company’s experimental self-driving cars. I also got to sit behind the wheel and try driving—or, rather, supervising—one of Uber’s new vehicles.
. . .
Uber is exploring the technology in the face of competition from automakers and tech companies investing in automated driving, like Google and Apple. The company’s hope is that the technology will eventually allow it to do away with drivers altogether—something that would help it save a lot of money, even if it were only rolled out in some areas. But for now Uber’s vehicles come with a driver who is trained to take over in an emergency, something I was thankful for on my test ride earlier this week.
. . .
I jumped at the chance to sit behind the wheel and see how drivers would experience the ride. It was possible to retake control by moving the steering wheel or pressing either the gas pedal or the brake, and there was even a large red button to disengage the system immediately. The biggest challenge, however, was staying absolutely vigilant. Sometime the car drove so adeptly that I had to be reminded to pay attention, and a couple of times I was asked to retake control—once when it seemed as though the car might travel extremely close to a parked vehicle, and again when it mysteriously began turning to the left while we sat in traffic on a bridge.
. . .
Herman Herman, who directs Carnegie Mellon University’s National Robotics Engineering Center, a subunit of CMU created to help commercialize automated vehicles and other robotic technologies, is skeptical that Uber will be able to do away with drivers altogether in short order. Herman says Uber has an advantage in being able to choose where it sends its driverless cars, but he adds that guaranteeing safety and reliability will be particularly challenging. “The last thing you want if you’re a passenger is for it to stop, or to crash into something,” he says.
. . .​
 

Jermin8r89

Well-Known Member
So just couple of days ago google brought out "fact check". I used to get news up front for wiki leaks now i cant find wiki leaks on my news feed cuz its not "factual". They say we will help you find whats real or not. Yea ok baseically what they think is real or not. Samething with these SDCs. WW3 bring it on! Ill survive and make my life how i want it!
 

Flarpy

Well-Known Member
Pay no attention to the driver behind the curtain!

(And RamzFanz is a true-believer fanboy, his cognitive dissonance will kick in and make him throw out any data that flies in the face of his fantasies. Of course, a lot of people are like that, only not with self-driving cars.)
 

rembrandt

Well-Known Member
This can't be true. MIT knows nothing about technology when 99% psychopath venture capital experts agree that SDC is the future ! 99% marketing experts agree too ! All the percentage experts agree ! Let MIT learn technology from the percentage experts.
 

RamzFanz

Well-Known Member
Pay no attention to the driver behind the curtain!

(And RamzFanz is a true-believer fanboy, his cognitive dissonance will kick in and make him throw out any data that flies in the face of his fantasies. Of course, a lot of people are like that, only not with self-driving cars.)

Except, of course, I'm the biggest skeptic of Uber's attempt at self driving. They are way way behind, they can't get an app to work well, and launching them now for test rides is just a dangerous publicity stunt. In the end, I think they'll partner with one of the many quality technology/auto companies (the line is becoming blurred) who are well ahead of them.

They did raid some top industry experts though, so you never know.
 

RamzFanz

Well-Known Member
This can't be true. MIT knows nothing about technology when 99% psychopath venture capital experts agree that SDC is the future ! 99% marketing experts agree too ! All the percentage experts agree ! Let MIT learn technology from the percentage experts.

I agree with MIT, or rather this particular article, Uber is not even close. Actual MIT experts will also tell you others are very close, but that will be ignored, yes? In fact MIT may have been the one to solve many weather related issues just a few months ago, not that I expect you would know that.

By the way, in technology years, not close or very close could both mean a few years away, especially when it's a race to a new 14 trillion dollar market by the world's leading companies, actual automation/robotics experts, and universities.
 
Last edited:

rembrandt

Well-Known Member
I agree with MIT, Uber is not even close. MIT will also tell you others are very close, but that will be ignored, yes? In fact MIT may have been the one to solve many weather related issues just a few months ago, not that I expect you would know that.

Caution : I do not want to judge your academic background or knowledge in science.

Scientific predictions are evidence based unlike business model that sees the result and then does the retrodictions. For example , x amount of force will cause object m to travel d amount of distance. That prediction will be put to test and the result will either confirm or falsify the prediction. It does not matter who says what because otherwise it will become an appeal to authority - a logical fallacy. We do not expect a post doctoral physicist to confirm if an anti wrinkle cream of a leading brand can actually work regardless how many people use that product. Popularity does not make something right or wrong , it only shows that it is popular.

All we want to see is how an SDC operates on regular traffic without anyone inside the vehicle. Science does care who says what. For anything to become science, the claim must be testable and the result must be replicable. You can not claim something which does not even exist.

Just to let you know that , no scientific theory has been able to predict the weather of a given date. For example , x amount of rainfall on 12/07/2017. Weather forecast is not science - it just a model based on the average of past weather pattern.
 
Last edited:

RamzFanz

Well-Known Member
You can not claim something which does not even exist.

And you can not claim that was does exist, does not.

Just to let you know that , no scientific theory has been able to predict the weather of a given date. For example , x amount of rainfall on 12/07/2017. Weather forecast is not science - it just a model based on the average of past weather pattern.

And yet that means nothing. SDCs will eventually be able to deal with any amount of rainfall. MIT has shown that. Can you?
 

RamzFanz

Well-Known Member
Caution : I do not want to judge your academic background or knowledge in science.

Scientific predictions are evidence based unlike business model that sees the result and then does the retrodictions. For example , x amount of force will cause object m to travel d amount of distance. That prediction will be put to test and the result will either confirm or falsify the prediction. It does not matter who says what because otherwise it will become an appeal to authority - a logical fallacy. We do not expect a post doctoral physicist to confirm if an anti wrinkle cream of a leading brand can actually work regardless how many people use that product. Popularity does not make something right or wrong , it only shows that it is popular.

All we want to see is how an SDC operates on regular traffic without anyone inside the vehicle. Science does care who says what. For anything to become science, the claim must be testable and the result must be replicable. You can not claim something which does not even exist.

Just to let you know that , no scientific theory has been able to predict the weather of a given date. For example , x amount of rainfall on 12/07/2017. Weather forecast is not science - it just a model based on the average of past weather pattern.

So, what you're saying is that a weather predictor today that saves millions of lives is invalid because it's not perfect? Or am I missing your point?
 

WeirdBob

Well-Known Member
Like, 6 months to a year, if they can't already.

Why are they keeping it so quiet, when others in the field crow loudly about relatively minor things?

By any chance can you share some links? I'll scour MIT and Carnegie Mellon to see what's what, but if you have anything I might overlook, I would appreciate the info.
 

WeirdBob

Well-Known Member

Right. I remember that from another thread. Fantastic concept, scary how it hangs low, years away from commercial usefulness, Gonna need a s***t ton of data for even small areas of mapping, gonna need a lot of cars to make the prior maps (unless cars generate their own local maps, in which case you are restricted to previously travelled areas only) even more $$$ on the final tab.

Complications of this system aside, nice catch! Thank you! I am gonna call the Lincoln Laboratory tomorrow.
 

RamzFanz

Well-Known Member
Right. I remember that from another thread. Fantastic concept, scary how it hangs low, years away from commercial usefulness, Gonna need a s***t ton of data for even small areas of mapping, gonna need a lot of cars to make the prior maps (unless cars generate their own local maps, in which case you are restricted to previously travelled areas only) even more $$$ on the final tab.

Complications of this system aside, nice catch! Thank you! I am gonna call the Lincoln Laboratory tomorrow.

In technology years, it doesn't need to be difficult or expensive. The original Lidar Google used cost them $70,000. Now they are in the hundreds. The industry is saying they'll be under $100 soon and the new rumored solid state Lidar may be even cheaper.

I'm not sure they will go in that direction, but I think the main point is there are ways to solve these commonly posted problems, it's just a matter of time.
 

WeirdBob

Well-Known Member
In technology years, it doesn't need to be difficult or expensive. The original Lidar Google used cost them $70,000. Now they are in the hundreds. The industry is saying they'll be under $100 soon and the new rumored solid state Lidar may be even cheaper.

I'm not sure they will go in that direction, but I think the main point is there are ways to solve these commonly posted problems, it's just a matter of time.

Hence the word "Eventually".

Self driving cars ARE coming soon. Even before they are ready, I am sure. But, short of a well armed police state conducting a massive and bloody crackdown, they will have to share the roads with humans for at least 30 more years.

Which brings up the point, if the government has to spend trillions of dollars buying everyone's human driven car, and chasing, arresting, and prosecuting outlaws, what money will be left to maintain the roads?
 
Top