Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision • Hacker News Board

Re: Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision

#121

Post by valine » Wed, Oct 05, 2022, 4:16 AM UTC

bearjaws wrote: post #101

This will absolutely not work, I have FSD and it messes up distance of large well defined objects, think about how this will work with a concrete wall, or curbs that it can probably no longer see. When I pull into my garage sometimes it recognizes my shelf as a car ON FSD....

The output of the “occupancy network” isn’t displayed to the user right now. It doesn’t do classification, it’s just raw voxels.

The real bummer is that without ultra sonics the car can’t see the ground in front of it. Hopefully tesla adds a bumper camera.

Re: Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision

#122

Post by valine » Wed, Oct 05, 2022, 4:18 AM UTC

atonse wrote: post #43

I have had a model 3 for four years and the autopilot has steadily gotten worse. In summer 2019 we went on a road trip that was 10 hours of total driving (each way), where I actually drove for maybe 30 mins total. It was flawless and downright magical. Since then we often have the car slam brakes out of the blue (once waking up my sleeping family and causing both kids to cry), and a few other times. I have lost trust…

Phantom braking is much improved on the FSD branch even during highway driving.

Went from 2022.16 to beta 10.69 and it was night and day difference. Haven’t had a single phantom brake in weeks.

Re: Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision

#123

Post by valine » Wed, Oct 05, 2022, 4:20 AM UTC

modeless wrote: post #27

This would potentially work... if the cameras could see the places where the ultrasonic sensors were. But they can't! There are big blind spots near the bumpers. I guess they are planning to just have the car fill in the blind spots by remembering what it saw from other perspectives? But that only works when the car is moving and can't account for small obstacles that can move unpredictably, like animals or toddlers.…

I assume these new Teslas will have a bumper camera. No way they’re planning to rely on memory.

Re: Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision

#124

Post by JumpCrisscross » Wed, Oct 05, 2022, 4:21 AM UTC

petilon wrote: post #117

kadoban wrote: post #108

Earlier quoted context omitted.

Your wording, especially the "Not true" puts it in your own voice. Not to mention, just repeating Musk's statement in the context you did (as a response to someone explicitly disagreeing already) implies that you agree with it.

It is not true that the decision is not driven by engineering; we know that because Musk has been anti-LiDAR and anti-radar from the beginning.

> is not true that the decision is not driven by engineering; we know that because Musk has been anti-LiDAR and anti-radar from the beginning

This shows some level of consistency. Not the source of a viewpoint. (Counterfactual: they had radar, and now they don't.)

Re: Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision

#125

Post by cma » Wed, Oct 05, 2022, 4:22 AM UTC

aeternum wrote: post #42

STRML wrote: post #22

There are multiple tells that this move, just like the removal of radar, is supply-chain and cost-driven and not actually driven by engineering. If this were a planned move, the software would already be ready to replace it. It is not. Cars without radar still aren't at parity with the car that have it, although they "fixed" this a few weeks back by simply turning off the radar on the older cars. The parking sensors…

With the removal of radar, they showed some pretty convincing data that the radar was too noisy to be useful, especially with discriminating things like highway overpasses vs. stopped cars. They showed that vision could already outperform radar. With these parking sensors it's different. They have no current alternative and it will cause a pretty significant loss of functionality. Disappointing move.

More data shouldn't actually hurt, it can be use as bayesian prior on the camera data when the vision stuff is uncertain if nothing else.

Re: Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision

#126

Post by nicbou » Wed, Oct 05, 2022, 4:23 AM UTC

sxates wrote: post #12

Cars delivered today without USS will not have: "Park Assist: alerts you of surrounding objects when the vehicle is traveling This is the most basic feature that almost every car has had for years - but not your $60k Model Y. Why can't they wait to remove sensors until they've achieved feature parity with the vision only system? This seems crazy. I don't really understand the push to do everything through the cameras…

Pardon me for being out of touch, but cars park themselves now?

That's pretty neat

Re: Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision

#127

Post by jjcon » Wed, Oct 05, 2022, 4:25 AM UTC

paulryanrogers wrote: post #97

jjcon wrote: post #85

Earlier quoted context omitted.

>an catch up to and exceed the visual processing capabilities of vertebrates with their millions of years of evolution I mean tons of technology outperforms humans by a mile... plenty of other computer vision systems already outperform people so not sure why Tesla would be exempt here due to 'evolution'.

Because driving isn't some narrow task. It has a lot of variability in conditions. Human brain is very adaptable, yet we require 16+ years of training before they can take the wheel.

I'm not disagreeing that the task is difficult but this topic isn't about general driving - this is about replacing ultrasonic sensors with visual systems. Evolutionary arguments are meaningless here since we outperform evolution all the time even with hand engineered visual systems, let alone ML derived ones.

Re: Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision

#128

Post by bink » Wed, Oct 05, 2022, 4:26 AM UTC

eclipxe wrote: post #111

googlryas wrote: post #58

Earlier quoted context omitted.

Yeah - there's an interior, driving-facing camera(at least in the model Y), which I suspect has no real purpose other than to send video after a crash to Tesla, so they can say "look, the driver wasn't staring at the road, not our fault autopilot crashed them". I would cover it up, but I'm afraid that it will look incriminating if I ever am in an accident as to why I did it.

The camera ensures you are paying attention with using Autopilot or FSD. For example if you pick up your phone, it will alert you to pay attention and eventually shut off.

I own a 2019 model 3 and the last I heard was that they couldn't use those cameras for monitoring a driver's attention because they were intended for monitoring the cabin when you "rented out" your FSD vehicle, so they aren't aimed at the driver. Have they changed the orientation since then?

Re: Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision

#129

Post by pengaru » Wed, Oct 05, 2022, 4:28 AM UTC

STRML wrote: post #22

There are multiple tells that this move, just like the removal of radar, is supply-chain and cost-driven and not actually driven by engineering. If this were a planned move, the software would already be ready to replace it. It is not. Cars without radar still aren't at parity with the car that have it, although they "fixed" this a few weeks back by simply turning off the radar on the older cars. The parking sensors…

> downright dishonest to characterize it as some kind of leap forward

Does anyone expect anything else from Tesla at this point?

Re: Tesla Vision Update: Replacing Ultrasonic Sensors with Tesla Vision

#130

Post by hackerlight » Wed, Oct 05, 2022, 4:29 AM UTC

atonse wrote: post #43

I have had a model 3 for four years and the autopilot has steadily gotten worse. In summer 2019 we went on a road trip that was 10 hours of total driving (each way), where I actually drove for maybe 30 mins total. It was flawless and downright magical. Since then we often have the car slam brakes out of the blue (once waking up my sleeping family and causing both kids to cry), and a few other times. I have lost trust…

This could just mean it's safer now.

You've experienced many false positives (braking going off for no reason), which is not a surprise, because they're lower cost than false negatives (braking not going off when needed), so if you work in Tesla AI you're going to accept lots of them in exchange for a tiny reduction in false negatives.

But maybe 1 in 1000 people will get to experience the true positive (braking going off when needed) that would have otherwise been a false negative, and their life was saved as a result of the updates, unbeknown to them.