Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register

Tesla’s next major milestone: no driver input required on the highway

This site may earn commission on affiliate links.
Yeah, I took a big step back, thanks for the advice. Waymo system is estimated at $8’500 or less, and Velodyne’s latest VLS-128 is at $12’000 or less for volume. Not sure exaggerating prices by 2’500% makes you look neutral...

lol ok you went too far and i'll have to add you to my ignore list.

I will however clarify a few things for other readers.
The 200k $ cost for the Google car are estimates from industry analysts for the entire car, not a single LIDAR sensor.
Second point, to simplify the conversation. How does it matter what sensor is used to acquire 3D data and wouldn't you want an all weather solution plus maybe something that doesn't cost an arm and a leg? You can choose between cams, radar and LIDAR but LIDAR in its current state is the absolute worst choice. It's as simple as that, you need 3D data and you make a rational choice on how to get that data but LIDAR today is not that.
 
Last edited:
  • Funny
Reactions: BinaryField
A laser based system should be able to ultimately outperform a camera system or the human eye in fog. You can look at the public work done at MIT, and can be sure that Waymo and others are well beyond what is in the public domain.

The cost of the Waymo system today deson't seem particularly relevant. They are properly solving the computer science problem first and then figuring out to deliver the system on at scale. It makes no sense to deliver hardware when the solution is unknown.
 
I'm confused. This statement seems to contradict your entire first post, which is largely based on comments/promises that Elon Musk has made about the progress of AD based solely on his 'gut'.

You're skeptical of any pronouncements based on a subjective impression (everything EM says/promises), but you think autonomous driving is just a few easy incremental steps away from where we are now, and might happen in 2018?

I don’t think full autonomy might happen in 2018. The completion of the planned Enhanced Autopilot feature set might.

The build of Enhanced Autopilot that is Level 2 autonomous with no driver input from highway onramp to offramp is something that Tesla has working at least sometimes right now in what sounds like an early developer version. It’s not a question of developing something new from scratch; it’s the roadmap from early dev version to shippable product.

I don’t know how long it will take Tesla to release the build it’s testing internally. But if it does launch it anytime soon, I think that is a very exciting sign for the timeline of full autonomy.
 
  • Like
  • Funny
Reactions: BigD0g and EinSV
I see little chance that Tesla will have a user agreement , in the next several years , that goes beyond level 2.

The liability beyond level 2 for Tesla is enormous. The AP being responsible for killing people is an enormous change. There is little upside for Tesla to claim level 3 in current cars. Tesla would need a gigafactory of litigators to claim level 3.
 
lol ok you went too far and i'll have to add you to my ignore list.

I will however clarify a few things for other readers.
The 200k $ cost for the Google car are estimates from industry analysts for the entire car, not a single LIDAR sensor.
Second point, to simplify the conversation. How does it matter what sensor is used to acquire 3D data and wouldn't you want an all weather solution plus maybe something that doesn't cost an arm and a leg? You can choose between cams, radar and LIDAR but LIDAR in its current state is the absolute worst choice. It's as simple as that, you need 3D data and you make a rational choice on how to get that data but LIDAR today is not that.

if that’s how you deal with people who disagree with you, no problem for me!

Don’t tell me you want an all weather solution and then talk about the virtues of cameras... . As for costing an arm and a leg, if 8k of hardware or less makes FSD possible, I’m in. This is the same dynamic that made electrical cars possible thanks to Tesla: focus on the high end market first, democratize once you know what to shoot for. But using the M3 as a lead in that strategy is putting the constraints ahead of any workable solution. Google has the highest number of reported FSD miles with super low disengagement rate. That, we know. As for Tesla, the only thing I know for sure is that their marketing video is artistic work, that AP as it stands is a useless L2 system (I hate sharing responsibility of my life with a lunatic system), and EAP and FSD still have to be released. Oh, as for LIDAR and snow, have you ever seen what happens to the cameras when you drive in snow for a while? They quickly get blinded by residues.
 
  • Like
Reactions: BinaryField
The ability to handle highway lane merged into the lane you are traveling in, or merge you into a adjacent lane would be a big deal. If I am unable to change lanes and there’s a merge in on my lane I alway kill AP because it’s behavior is erratic.