[KennyBlanken]

No? There are numerous clips where Telsas in "full self driving" mode pull the equivalent maneuver of a teenager going "OH SHIT I WANT TO GO THERE" and veering very violently.

The phantom braking problem is likely just one of the many symptoms of Musk's insistence on relying on optical systems instead of more expensive sensors.

[gzer0]

Expense was part of the equation initially, however, through economies of scale, we eventually would have been able to reach a feasible price point. Cost has nothing to do with why Tesla is pursuing an optical-only system.

To get rid of the dependency on the radar sensor for autopilot, we generated over 10 billion labels across two and a half million clips. To do this we had to scale our offline neural networks and our simulation engine across 1000s of GPUs, and just a little bit shy of 20,000 CPU cores. We also included over 2000 actual autopilot full self driving computers in the loop with our simulation engine. And that's the smallest compute cluster.

[meheleventyone]

Those are very large numbers for something that doesn’t work very well.

[atleta]

So what's the point then? You said it's not expenses and then you explain how you think it caused you extra trouble/work/development effort. But what's the reason?

[stefan_]

That must be why complaints about phantom braking have gone through the roof since the switch away from radar.

[outworlder]

> The phantom braking problem is likely just one of the many symptoms of Musk's insistence on relying on optical systems instead of more expensive sensors.

Based on what? How would 'expensive' sensors help?

[bluGill]

We know that in some situations expensive sensors can get data that optical cannot. What we don't know is if any of the above is enough extra data.

What we do know is there are times when humans are bad drivers, and other times when humans continue when they shouldn't relying on luck. (Ie driving in snow storms with low visibility)

[Spooky23]

Consider your human eyeball. It works really well, but you can get into trouble in certain light or visual conditions.

Technology exists (radar, lidar) that doesn’t have the same limitations as visual. (They have their own issues of course)