Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Toyota Research Institute head says full autonomous driving is “not even close”

techcrunch.com

Post reply on HN
Print view View original

301–310 of 443 posts

Re: Toyota Research Institute head says full autonomous driving is “not even close”

#301

Post by stevenwoo »

vertex-four wrote: post #290
pg314 wrote: post #261

Earlier quoted context omitted.

Are deaf people allowed to drive? How do you think they handle these situations?

According to a quick google, noticing that other cars are pulling in/slowing down usually works if they can't see the emergency vehicle. Still, it's not "perfect", but then Hearing drivers are far from perfect either, and there's plenty of failsafes before an accident happens.

Fire trucks and ambulances I've seen when driving against traffic lights/flow of traffic always slow and stop to make sure that there will not be an accident even if they have the right of way - they don't drive like police in pursuit on TV. I'm sure there are exceptions but the general case is the emergency vehicles are planning for other traffic to not yield until it is clear the other traffic is yielding.

Re: Toyota Research Institute head says full autonomous driving is “not even close”

#302

Post by vertex-four »

PeterisP wrote: post #232
rayiner wrote: post #166

Earlier quoted context omitted.

Im skeptical you can do real autonomous driving without context. In DC, we have roads that flow one direction part of the day and another direction the other part. We've got roads that will be shut down unpredictably when there is a diplomatic event. We've got constant construction, where a two lane road might be reduced to one lane with a human holding a sign or using hand signals to usher cars through on their turn…

For a self driving car, it's sufficient if its understanding of weird situations is limited to detecting "yep, I'm in a weird situation, I'm going to stop now and wait for a remote human to take control". The situations you describe are rare - I've once had a diplomatic event that required weird rerouting and twice had cases where traffic was regulated by hand signals due to some crash on the road, but that means jus…

We actually now understand that passing control to a human is seriously dangerous - unless you can do it a minute or so in advance, the human has to switch context from being a passive passenger (or, more likely, actively engrossed in something else) into being an active driver very quickly. Everything up to level 4 automation will cause accidents when the car attempts to hand control to a human.

Of course, there's a very reasonable argument that e.g. level 3 automation might cause fewer accidents overall, even if it kills people when it has no idea what to do, but convincing Joe Public that such a car with such a known flaw is safe is another matter.

Re: Toyota Research Institute head says full autonomous driving is “not even close”

#303

Post by stevenwoo »

Bahamut wrote: post #92
chrismealy wrote: post #42

Earlier quoted context omitted.

Other countries have much lower car death rates. It's a social problem that can be solved without waiting technological miracles.

The US death rate is lower than most countries: https://en.m.wikipedia.org/wiki/List_of_countries_by_traffic...

The general trend from that data appears that the higher the standard of living, the higher the safety is per driving mile and the US is where one would expect in such a list, better than third world countries, worse than Europe.

Re: Toyota Research Institute head says full autonomous driving is “not even close”

#304

Post by watwut »

alex_anglin wrote: post #258
49para wrote: post #239

Earlier quoted context omitted.

http://www.safetyresearch.net/blog/articles/toyota-unintende... They might do better with hardware than software ...

Counterpoint from Malcolm Gladwell: http://revisionisthistory.com/episodes/08-blame-game The argument he puts forth is that pedal error on the drivers part is an explanation for the unintended acceleration.

If drivers pedal errors lead to unintended acceleration in one car, but somehow don't cause unintended accelerations in all the other cars, then maybe there is something wring with how pedal reacts.

Re: Toyota Research Institute head says full autonomous driving is “not even close”

#305

Post by kajecounterhack »

kpil wrote: post #233
kajecounterhack wrote: post #209

Earlier quoted context omitted.

I don't know by what metrics you're making these comparisons. Audio recognition and self-driving vehicles are apples and oranges. Autonomous driving is difficult primarily because of a changing world and low tolerance for mistakes. The state space of situations you're trying to map is just large. It will take time. But it's not even close to impossible. Audio recognition is difficult for a different reason: language…

I think that audio recognition is an order of magnitude less complicated than fully autonomous driving. The world is fully contextless outside the road to an not-even-at-insect-level brain driving two tons of metal, and anything can happen. Voice recognition is getting just barely tolerable. If you have tried to do something important using voice recognition you'd probably go bat shit crazy after a while. If it had t…

> The world is fully contextless outside the road to an not-even-at-insect-level brain driving two tons of metal, and anything can happen.

See that's where you're wrong. An autonomous vehicle doesn't have to have a human brain. It has to have very accurate sensors and classifiers tuned with generous safety params.

Like any vehicle it also needs redundancies for safety and sane default behavior (mostly "slam on the breaks").

Also, not "anything can happen." There are rules that govern the road that make this problem tractable. There are rules that govern physics that mean if you have adequate sensors + compute you can avoid hitting any objects at all, whether it's a person or otherwise. "Object x is 30 ft away with trajectory y, we're going 15mph, slam on the brakes."

The difficulties mostly lie in how we can "not slam on the brakes all the time and never make progress." e.g if you enter a construction zone you better know what to do and not just sit still, otherwise you'll never get anywhere.

Re: Toyota Research Institute head says full autonomous driving is “not even close”

#306

Post by bluGill »

gboudrias wrote: post #4

I'm sure he's right, but then why is everyone joining the race now? Wouldn't it be way less expensive to wait until at least some of the problems are solved? Also, it sure seems like level 5 autonomous driving is just a few steps short of general AI, which is still lightyears away.

No car maker dares not be in the race. There is the very real risk that somebody in the race will release an autonomous car, and in just a few months(worst case, but it is believable) governments will see those car is significantly safer and mandate it on all cars. If that happens any manufacture not close to finished won't exist anymore.

Note that being in the race just means they have a plan in place. Car makers partner all the time - it is common to see the same car from several different makes with only the logo changed, or an optional engine from someone else.

I expect that in the end there will be about 5 different self driving systems on the road that are shared between different cars. Designing a system is complex and expensive on the one hand; and not a differentiator that customers will pay for on the other hand: so it won't be worth the cost to continue to develop a system if you have it when you can buy from someone else. (though each might customize the UI as the UI is a feature they can sell)

Re: Toyota Research Institute head says full autonomous driving is “not even close”

#307

Post by semi-extrinsic »

rayiner wrote: post #166
vamin wrote: post #127

Earlier quoted context omitted.

I disagree with the analogy to speech recognition. What makes speech recognition difficult is that it's highly dependent on context (sounds the same, but means something different depending on surrounding words, what the conversation is about, or even who you're speaking with). With driving, you should be able to make a good decision with just the instantaneous state, given enough information about that state (object…

Im skeptical you can do real autonomous driving without context. In DC, we have roads that flow one direction part of the day and another direction the other part. We've got roads that will be shut down unpredictably when there is a diplomatic event. We've got constant construction, where a two lane road might be reduced to one lane with a human holding a sign or using hand signals to usher cars through on their turn…

For a few more very common examples of humans using context:

A human will spot a person wearing headphones and recognize that person has a low situational awareness. The computer doesn't come close to even having the optical resolution to do that if the AI was perfect - remember human vision is 570+ megapixels, even a 4K video stream is literally two orders of magnitude lower.

[Now think about the fact that if we built a camera capable of recording 400 megapixels, you'd currently need to schlep around a ~750 lbs 25 node cluster, consuming about 50 horsepower to feed it with electricity, just to be able to process the video stream at 25 fps. Moore's law aint' growing that fast these days, so matching the resolution of human vision is not a realistic option.]

Another example is kids. How does the AI recognize that the 5'1" 30-year-old woman has much better awareness and can be treated differently from the 5'2" 12-year-old boy? Humans can spot that difference even from behind.

How about recognizing an adult who is drunk? Or a blind person? Mourners at a funeral, or fans celebrating after a football game? Or a million other conditions that significantly affect pedestrian situational awareness that human drivers will instantly infer from context?

What will happen when kids figure out they can stop a driverless car on its way to collect its owner just by standing in the street in front of it? They'll have a lot of fun, for sure.

How about when carjackers figure out the same? That they can dress up like construction workers, stop the car in the street, tow it onto a flatbed with built-in RF jammer and head straight for their underground chop shop? There goes your cheaper insurance.

Re: Toyota Research Institute head says full autonomous driving is “not even close”

#308

Post by Someone »

dperfect wrote: post #168
dperfect wrote: post #57

I've been saying this for a while. The problem is that people are mostly familiar with the rate of overcoming traditional technical challenges (e.g., making your current computer/phone more compact, improving graphics quality, making cameras and screens with more pixels, etc.). What people don't realize is that full autonomous driving will require more than just faster/smaller/cheaper technical innovation - it will r…

A little more context on the speech recognition part: I remember going to a trade show (many years ago) where a representative from one of the major speech recognition companies was showing off the technology. He wasn't just dictating text, but was also using the software to control the computer. I was floored by it. I was 100% convinced we had arrived at that dream of intelligent voice-computer interaction. I've fel…

"I was floored by it. I was 100% convinced we had arrived at that dream of intelligent voice-computer interaction."

I remember talking to Apple's Kim Silverman, ¿head? of speech recognition, somewhere in the end of the '90s. He said you had to spend a few hundreds of hours training the recognizer to get at a good level. That's not a lot more than one would spend learning to touch type at speed, but a large fraction of _that_ time is productive; training a speech recognized wasn't.

Also, touch typing, once you can do it, works everywhere; speech recognition didn't work as well when there was background noise or echos. So, few people were willing to invest the time. And they probably were right.

I also agree with your statement that we will solve restricted, but useful domains first, and that a general solution for autonomous driving will be a long way of.

I also agree roads will be adapted to the self-driving cars. It isn't rocket science to embed a steel wire in the center of each car lane that a robot car can detect, for example.

I remember a television program where the engineers of some European car manufacturer thought universally usable self-driving cars would be safer than human driven ones in 10 years or so, but their human factors specialist said it would be something like 40 years before they would hit the road because she knew you can't expect humans to fully attend to driving on very short notice for a few seconds each week.

(that show also said, and showed, that features such as lane assist are more limited than the cars are capable of because of human factors)

Re: Toyota Research Institute head says full autonomous driving is “not even close”

#309

Post by kajecounterhack »

speby wrote: post #236
kajecounterhack wrote: post #209

Earlier quoted context omitted.

I don't know by what metrics you're making these comparisons. Audio recognition and self-driving vehicles are apples and oranges. Autonomous driving is difficult primarily because of a changing world and low tolerance for mistakes. The state space of situations you're trying to map is just large. It will take time. But it's not even close to impossible. Audio recognition is difficult for a different reason: language…

Audio recognition may be apples and oranges to self-driving vehicles. But as it relates to autonomous driving, audio recognition (and I don't mean speech but general sounds) is something nobody has been talking about (at least publicly) as a sensor input for self-driving cars. Think about how much you rely on your hearing to drive safely and well. Sure, we use sight/depth and so forth substantially but we also rely o…

"Nobody talking about it" doesn't mean nobody is working on it ;)

Re: Toyota Research Institute head says full autonomous driving is “not even close”

#310

Post by jacquesm »

rayiner wrote: post #132
redbeard0x0a wrote: post #94

People have a habit of thinking linearly, however technology builds on top of technology (leading to exponential improvements). Half way through the Genome project, they had only mapped out 1% of the genome. A lot of people in that field and working on that project were thinking the same thing - "not even close". But the next 7 years, they completed the next 99%. This is the power of exponential progress. The only th…

Technological curves tend to look exponential at first, then logarithmic. We went from first manned flight to first supersonic manned flight in just 44 years. Seventy years later we still don't have supersonic commercial flights. In the energy sector, the thermal efficiency of coal plants improved dramatically from 1880 to 1950, then pretty much hasn't improved at all since then. The number of years someone can expec…

> Seventy years later we still don't have supersonic commercial flights.

Worse still, we have already had and lost them.

And the age for qualifying for social security is going up faster than longevity in plenty of countries.

Post reply on HN