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

Tesla's self driving algorithm's overlay [video]

tesla.com

Post reply on HN
Print view View original

31–40 of 658 posts

Re: Tesla's self driving algorithm's overlay [video]

#31

Post by tamersalama »

calebegg wrote: post #19
dylan604 wrote: post #2

I have often wondered about this, so I do find this interesting. Of all of the info presented, one question I have is how does the AI decide when to go at a 4-way stop? In real life, I'm am constantly amazed at how confusing a 4-way stop is to humans. Not that I ever had any doubt into how complicated real-time video analysis could be, this just makes my appreciation of the complexity of the problem that much more qu…

The proper rules[1] of a 4 way stop are probably pretty straightforward to encode, and probably easier for a computer to apply than a human, but the real issue is that you can't trust the other drivers (or AIs) to understand/follow them consistently. So the interesting part is how these kinds of systems can almost instantly react when another driver starts to go, and let them go. In NYC, where I live now, the de fact…

Wouldn't the data decide what the rule is? I'm guessing if in NYC, a more aggressive driving style is the norm - the models and the pipeline should be capable of adjusting to that.

Re: Tesla's self driving algorithm's overlay [video]

#32

Post by winternett »

jrockway wrote: post #8
dylan604 wrote: post #2

I have often wondered about this, so I do find this interesting. Of all of the info presented, one question I have is how does the AI decide when to go at a 4-way stop? In real life, I'm am constantly amazed at how confusing a 4-way stop is to humans. Not that I ever had any doubt into how complicated real-time video analysis could be, this just makes my appreciation of the complexity of the problem that much more qu…

Google had to program their car to stop treating 4 way stops exactly as the law required, and instead pretend to be a little aggressive: https://www.nytimes.com/2015/09/02/technology/personaltech/g...

Unless you're driving in a place known for courtesy like Canada or Hawaii ಠ_ಠ... People often stop late and won't move until you go first...

Re: Tesla's self driving algorithm's overlay [video]

#33

Post by Erlich_Bachman »

jfengel wrote: post #25
yarg wrote: post #18

Interesting, but is it just me or does it seem overly jumpy?

The "vision fps" runs around 12 to 20, so yeah, that's gonna seem kinda jumpy. The display fps is slightly higher, which contributes to a juddering feeling.

I think the more interesting/dangerous jumping is when the perception engine fails to consistently classify/find objects in the scene, between adjacent frames, not the specific fps of the process. This video seems to display some of such inter-frame jumpiness.

Re: Tesla's self driving algorithm's overlay [video]

#34

Post by anchpop »

Traster wrote: post #26
yarg wrote: post #18

Interesting, but is it just me or does it seem overly jumpy?

One of the real challenges of these systems is that even a very good system only needs to lose confidence in some object for a very short period of time for the system to lose confidence in its navigation and return control to the user. The easy way to get around that issue is to categorize objects and then just ignore them out of the context you expect them to appear in -- which is how Tesla managed to kill a pedest…

> which is how Tesla managed to kill a pedestrian walking their bicycle across the road.

That was Uber, just so you know

Re: Tesla's self driving algorithm's overlay [video]

#35

Post by bryanlarsen »

winternett wrote: post #13
dylan604 wrote: post #2

I have often wondered about this, so I do find this interesting. Of all of the info presented, one question I have is how does the AI decide when to go at a 4-way stop? In real life, I'm am constantly amazed at how confusing a 4-way stop is to humans. Not that I ever had any doubt into how complicated real-time video analysis could be, this just makes my appreciation of the complexity of the problem that much more qu…

The system isn't AI based... It's currently based on static programming. This is why a development team would have to think of every possible scenario that could happen on roads to make self driving cars really work. You'd have to ask all kinds of wild questions too like: "What if kids played a prank and re-painted road lanes on a highway at 50MPH?" "What if a sand storm happened?" "What would the car do if a tire bl…

This is much less true than it used to be with the current rewrite of the autopilot software:

https://cleantechnica.com/2020/01/31/timestamped-guide-to-pa...

Re: Tesla's self driving algorithm's overlay [video]

#36

Post by zionic »

Traster wrote: post #26
yarg wrote: post #18

Interesting, but is it just me or does it seem overly jumpy?

One of the real challenges of these systems is that even a very good system only needs to lose confidence in some object for a very short period of time for the system to lose confidence in its navigation and return control to the user. The easy way to get around that issue is to categorize objects and then just ignore them out of the context you expect them to appear in -- which is how Tesla managed to kill a pedest…

Wasn't that uber?

Re: Tesla's self driving algorithm's overlay [video]

#37

Post by IceSentry »

thedance wrote: post #30

I wonder why they would let the public see this. To the critical eye it looks like it barely works. It loses its mind right at the beginning, around 0:06-0:07, veers to the right for no reason and then rolls through a stop sign without stopping. It spends the rest of the video hunting left and right like a drunk.

The video is clearly sped up and it looks like it did wait at the stop sign in the first part, it just didn't wait long.

Re: Tesla's self driving algorithm's overlay [video]

#39

Post by Erlich_Bachman »

tjoff wrote: post #24
modeless wrote: post #16

Earlier quoted context omitted.

Tesla doesn't use lidar. They have always used radar, but radar can't always tell the difference between a stationary metal sign near/over the road and a stalled car in the middle of the lane, so for stationary objects they need the cameras. This is why every adaptive cruise control system (not just Tesla's) has a warning that it may not detect stationary objects. https://arstechnica.com/cars/2018/06/why-emergency-br…

Though only(?) Tesla pretends that their adaptive cruise control is full blown self-driving.

Source?

If you simply refer to it being called "autopilot", cmon that's not too serious. The word "autopilot" does not automatically mean that it is full self-driving. None of the Tesla drivers or potential Tesla buyers realistically think that it has level 5 self-driving yet.

UPD: The buy page literally says:

"The currently enabled features require active driver supervision and do not make the vehicle autonomous. The activation and use of these features are dependent on achieving reliability far in excess of human drivers as demonstrated by billions of miles of experience, as well as regulatory approval, which may take longer in some jurisdictions. As these self-driving features evolve, your car will be continuously upgraded through over-the-air software updates."

Re: Tesla's self driving algorithm's overlay [video]

#40

Post by baddox »

winternett wrote: post #13
dylan604 wrote: post #2

I have often wondered about this, so I do find this interesting. Of all of the info presented, one question I have is how does the AI decide when to go at a 4-way stop? In real life, I'm am constantly amazed at how confusing a 4-way stop is to humans. Not that I ever had any doubt into how complicated real-time video analysis could be, this just makes my appreciation of the complexity of the problem that much more qu…

The system isn't AI based... It's currently based on static programming. This is why a development team would have to think of every possible scenario that could happen on roads to make self driving cars really work. You'd have to ask all kinds of wild questions too like: "What if kids played a prank and re-painted road lanes on a highway at 50MPH?" "What if a sand storm happened?" "What would the car do if a tire bl…

> The system isn't AI based... It's currently based on static programming. This is why a development team would have to think of every possible scenario that could happen on roads to make self driving cars really work.

I'm not really sure what this dichotomy is that you're describing. It certainly looks like they're using computer vision to detect the bounding boxes of cars, and the field of computer vision is widely described as being either a subset of artificial intelligence or a cross-disciplinary approach combining artificial intelligence with a handful of other fields.

> You'd have to ask all kinds of wild questions too like:

> "What if kids played a prank and re-painted road lanes on a highway at 50MPH?"

This sort of thing actually happens with real humans, and the legal system has to (and does) handle it. In the 1990s three people removed a stop sign as a prank and were sentenced to 15 years in prison after a human driver drove into the intersection and hit another vehicle, killing three teenagers. https://www.nytimes.com/1997/06/21/us/3-are-sentenced-to-15-.... The fact that it's possible for humans to illegally modify road markings and end up killing people is a challenge and a tragedy, but it's not anything new or particularly game-changing for self-driving cars.

> "What if a sand storm happened?"

That sounds like one of the easiest possible problems. What do humans do when they suddenly have nearly zero visibility on a road? In most places I assume they are supposed to (and do) pull over to the side of the road and stop. I've been in rain that is so heavy that all the nearby cars on the highway had to pull over.

> "What would the car do if a tire blows out at 55MPH?"

Again, that's another thing that happens a lot, and probably causes a lot of injuries and deaths. Again, I'm not minimizing that loss, but it's not some huge "gotcha" for self-driving cars. In this particular example, I would expect self-driving cars to be vastly better than most human drivers in this situation at maintaining control while pulling over and stopping.

Post reply on HN