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

AP accidents

This site may earn commission on affiliate links.
That's terrifying, I hope there was no one near that truck!
Does TACC not use radar returns from stationary objects at all?
How I imagine NNs:
1640131562508.png
 
  • Funny
Reactions: israndy and EVNow
Well. What do you expect? It's just too dark! I am not sure if human drivers could respond timely in darkness either!
Sandy Munro is a big proponent of integrating FLIR cameras (infrared) for autonomous driving cars, and this is a pretty good example of a situation where a FLIR camera would have seen the disabled car in the lane ahead.
 
Yes, but at high speed, we need long-range. Headlights are too short for range. By the time I see an obstacle shining by the bright headlight, it would be too late to avoid a collision.
The video doesn't do justice to human eye dynamic range and resolution. The car and junk around it are visible with plenty of time to take evasive maneuvers. Don't drive faster than your headlights.
 
The video doesn't do justice to human eye dynamic range and resolution. The car and junk around it are visible with plenty of time to take evasive maneuvers. Don't drive faster than your headlights.
Yes, very concerning. What do you suggest Tesla do - just completely abandon AP/FSD and return all the money or close down the company ?
 
Last edited:
  • Funny
Reactions: lUtriaNt
We only have apologists or concern trolls here ;)

Sometimes I'll play the role of the devil's advocate to keep the conversation interesting.

This is what this thread is, to me... since there are like 8-10 other threads in this subforum on the first page or two that this could have been posted in, rather than a new thread created...but that doesnt bring the same visability for "discussion".
 
Last edited:
Yes, but at high speed, we need long-range. Headlights are too short for range. By the time I see an obstacle shining by the bright headlight, it would be too late to avoid a collision.
v2x, my man. v2x. if we just admit that its a great thing to have and put some manpower behind making it interoperable and useful, think of it as beacons that can announce presence and NOT require vision or radar. just radio waves!

every layer helps. but I find lots of resistance toward v2x and tesla does not have any plans for it. its not on its, [cough..] radar.
 
  • Funny
Reactions: Daniel in SD
Yes, very concerning. What do you suggest Tesla do - just completely abandon AP/FSD and return all the money or close down the company ?
More nags! I haven't seen anyone here blaming Tesla for the collision. I blame all the people complaining about phantom braking. :p
I'm a little bit disturbed that some people think it's ok to drive when their eyesight is equivalent to a low dynamic range recompressed twitter video...
 
This is what this thread is, to me... since there are like 8-10 other threads in this subforum on the first page or two that this could have been posted in, rather than a new thread created...but that doesnt bring the same visability for "discussion".
Yes, if these concern-trolls post this in the investor section/thread, they would be banned in 3 .. 2 .. 1.
 
The video doesn't do justice to human eye dynamic range and resolution. The car and junk around it are visible with plenty of time to take evasive maneuvers. Don't drive faster than your headlights.

So what we can learn from the statement?

1) Machine vision (video) is not as good as humans': What's the point here? Should we use Tesla Vision or not?

2) Since the car and junk are not invisible because, once within the range of headlights, the machine should pick those clues up and do an evasive maneuver?

3) AP/FSD should slow down to be as safe as the reaction time within the headlights' range?