Tesla Autopilot • Hacker News Board

Re: Tesla Autopilot

#301

Post by lern_too_spel » Sat, Jun 17, 2017, 5:52 PM UTC

Matthias247 wrote: post #293

lern_too_spel wrote: post #12

Earlier quoted context omitted.

You can look at their CA DMV disengagement report here: https://www.dmv.ca.gov/portal/dmv/detail/vr/autonomous/disen... . They were very far away as of the start of this year.

The lists are interesting. And for me they are mostly telling that they are all in some super early prototyping phases. E.g. Tesla lists tests with To give some comparison numbers how normal series cars are tested at bigger automotive companies: There are test fleets of partly over 100 cars for a new car model, where some of those are tested all around the clock (> 600 miles per day). All in all often 2digit million…

The autonomous car services are going to launch in specific areas first, so they do not need to be tested in all the conditions that a Corolla would be tested in and can instead be tested in the launch markets. The key figure is miles per disengagement, and Tesla appears to be very far from having a viable autonomous car.

Re: Tesla Autopilot

#302

Post by extrapickles » Sat, Jun 17, 2017, 5:56 PM UTC

the_rosentotter wrote: post #152

Animats wrote: post #64

Watch this at 0.25x speed or slower to see what's going on. This is a carefully chosen environment. Every place it drives has very clear highway centerline markings. It seems to be highly dependent on those for guidance. Sometimes it can't quite identify the road edge, but the centerline provides a position reference. The inputs seem to be road line recognition, optical flow for the road, and solid object recognition…

It terrifies me to think of relying on image recognition software to correctly determine an upcoming crossing road (with cars zipping across) so it can properly slow down, rather than get broadsided at full speed. Or a number of other life-and-death situations (which are common during driving). It just seems fragile (what if the 'vision' is somehow impaired, f.ex. blinded by sunlight, or the road markings are wrong o…

It doesn't have to rely on vision.

They probably use GPS+map for a low resolution location and trajectory planning. Vision should only be used for fine positioning and obstacle detection.

Re: Tesla Autopilot

#303

Post by f0under » Sat, Jun 17, 2017, 5:57 PM UTC

Anyone identify which road the car is driving on? Looks familiar like the area around Foothills but couldn't tell.

Re: Tesla Autopilot

#304

Post by dawnerd » Sat, Jun 17, 2017, 6:08 PM UTC

dsfyu404ed wrote: post #262

jacquesm wrote: post #217

Earlier quoted context omitted.

One day some joker with two pots of paint (one white, one gray) is going to have a field day causing cars to run off the road.

I drive through a construction zone once a week where the old lane shift lines and the new ones are close enough in quality to make following the lines instead of the traffic around you a very bad idea.

My Passat (2016) with lane assist falls into these traps all the time. Same with offramps. It can be a fight to keep it from jeering off. It is really nice on long drives though.

Re: Tesla Autopilot

#305

Post by takeda » Sat, Jun 17, 2017, 6:13 PM UTC

willvarfar wrote: post #160

the_rosentotter wrote: post #152

Earlier quoted context omitted.

It terrifies me to think of relying on image recognition software to correctly determine an upcoming crossing road (with cars zipping across) so it can properly slow down, rather than get broadsided at full speed. Or a number of other life-and-death situations (which are common during driving). It just seems fragile (what if the 'vision' is somehow impaired, f.ex. blinded by sunlight, or the road markings are wrong o…

> It terrifies me to think of relying on image recognition software to correctly determine (... snip) Do you not drive using only your eyes? If you are not terrified of the sensors, then software? Turing's central belief was that the human brain was 'just' a computer. Regards doing things like embedding reflectors in roads and other ways to simplify lane holding, completely agree. But we can't forego the cameras etc…

We are far away from hard AI (computer actually can think) some people start to believe we might not be able to reach it. What we currently succeeding is developing soft AI (solving specific problems) the problem is that such AI might do fine when things are clearly labeled, but might not know what to do in unexpected situations. With car stopping might often be correct, but in other situations actually not stopping is best etc.

Another thing is that your eyes can last you 100+ years, technology is not that durable and breaks more often, the objectives in cameras get dirty etc.

The cameras typically aren't as good as human eye, for example there are reports where Tesla wanted to jam into a truck in front only because its back in the camera couldn't be differentiated from the sky.

Yes, relying on cameras only is perfectly fine when you play PS4 game, but when life is on the line you want extra safety checks. Kind of like cars have brakes on every wheel and then also a handbrake. How every car has minimum of 3 stop lights (how often you see that one or more lights are bad in other cars?)

Your belief that we have hard AI (and this is kind of indirectly created by companies like Tesla, Google, Amazon, IBM etc) gives you conclusion that just two cameras should be enough in reality we did not made much progress in that area and instead just concentrated on specialized AI that is capable solving specialized problems, that kind of approach absolutely works better with more sensors.

Re: Tesla Autopilot

#306

Post by takeda » Sat, Jun 17, 2017, 6:22 PM UTC

delinka wrote: post #297

joeblau wrote: post #190

Earlier quoted context omitted.

You don't necessarily have to train it to see elephants, but Neural Networks fail in pretty interesting ways. This that are very obvious to you and I have the ability to confuse a CNN[1]. [1] - http://www.evolvingai.org/fooling

These look like a digital Rorschach test. With the minor difference that a human "knows" the image is not really an object and is being asked to interpret in some way; where the machine has no "knowledge" nor "understanding" but has an imperative to match this input to something in its repertoire of knowledge. As a human, if you asked me to match these synthetic images to a most-likely real-world match, then my respo…

The thing is that computers also rate them with 99% certainty.

Re: Tesla Autopilot

#307

Post by xapata » Sat, Jun 17, 2017, 6:39 PM UTC

TeMPOraL wrote: post #180

willvarfar wrote: post #160

Earlier quoted context omitted.

> It terrifies me to think of relying on image recognition software to correctly determine (... snip) Do you not drive using only your eyes? If you are not terrified of the sensors, then software? Turing's central belief was that the human brain was 'just' a computer. Regards doing things like embedding reflectors in roads and other ways to simplify lane holding, completely agree. But we can't forego the cameras etc…

The thing is, human "machine vision" has graceful failure modes. You don't switch from seeing cars to seeing nothing to seeing an elephant just because the input got a little noisy. The same cannot be said about current ML demonstrations - because they operate on just vision. Humans continuously reconcile visual input with their model of the world and with other inputs, to the point of overriding visual data if neede…

That's just Bayesian priors. Easy peasy for ML.

Re: Tesla Autopilot

#308

Post by Animats » Sat, Jun 17, 2017, 7:17 PM UTC

Reason077 wrote: post #215

the_rosentotter wrote: post #152

Earlier quoted context omitted.

It terrifies me to think of relying on image recognition software to correctly determine an upcoming crossing road (with cars zipping across) so it can properly slow down, rather than get broadsided at full speed. Or a number of other life-and-death situations (which are common during driving). It just seems fragile (what if the 'vision' is somehow impaired, f.ex. blinded by sunlight, or the road markings are wrong o…

"I don't fully understand why more effort is not put into a hardware solution, where roads are simply marked up for self-driving vehicles, e.g. magnets lining the lanes or something like that." How would "magnets" be any improvement over visual markings? Is there some sensor that can track magnets at greater distance, or with greater reliability than visual markings? Besides, how many millions of miles of road would…

"I don't fully understand why more effort is not put into a hardware solution, where roads are simply marked up for self-driving vehicles, e.g. magnets lining the lanes or something like that."

Volvo is plugging for magnets in roads in Sweden, so they can find lanes in the snow. It might happen, because it can also be used for snowplow guidance. In heavy-snow areas, posts, poles, and even over-road arrows (Japan uses this in Hokkaido) are placed to provide guidance. It's not intended to replace vision and LIDAR, just as additional guidance hints for bad conditions.

Re: Tesla Autopilot

#309

Post by pferde » Sat, Jun 17, 2017, 7:51 PM UTC

TeMPOraL wrote: post #223

RobertoG wrote: post #213

Earlier quoted context omitted.

That doesn't sound as an insurmountable problem. Humans don't see elephants suddenly because a prior is telling them that an elephant is improbable in that context. Something like that in a computer system shouldn't be above the current capabilities.

I agree it shouldn't be above current capabilities. But I'm yet to see anyone doing something like this. And I'm definitely wary about taking the results of toying with "deep learning" and saying we've can put that on a car and expect good results - which is an impression I sometimes get in articles about those topics.

Also, this will stop working the day an elephant escapes from a ZOO and manages to get onto a highway. All the autopilots will declare the elephant's presence as impossible, and will happily crash into it.

Re: Tesla Autopilot

#310

Post by lttlrck » Sat, Jun 17, 2017, 8:13 PM UTC

kaeluka wrote: post #179

PakG1 wrote: post #169

Earlier quoted context omitted.

If the brain is just a computer, its machine learning algorithms for image recognition at a busy intersection are believably currently more accurate than any image processing software run on any computer that Tesla puts in its cars.

There are ways in which current machine learning is better than your brain -- tracking many objects at the same time is one of them. Sure, it's worse in many other ways.

The ability to track multiple objects doesn't necessarily mean it's any good at integrating a solution. My camera can track multiple faces and smiles - that doesn't mean it can take better photos.