failed to distinguish the white side of a turning tractor-trailer
The car expected ALL tractor-trailers to be painted white?
“he went so fast through my trailer I didn’t see him.”
Through my trailer?
he died and snapped a telephone pole a quarter mile down the road
A quarter mile down the road, so, what killed the driver?
Everything you’ve mentioned, and more make this suspect as hell.
The moment a Tesla touches anything else it will stop. A 1/4 mile away ? Not likely. A collision with a trailer sent the car THROUGH the trailer, still operating under it’s own power ? The driver was dead at that point ? Or when it went through the pole (Snapped it?) This is all VERY suspect.
“The car expected ALL tractor-trailers to be painted white?”
What the author of this article should have explained is that the software mkstakenly concluded that the cameras were overexposed due to sunlight bombarding the camera’s sensors. The data you’d receive in that situation is similar to viewing “all white”.
Also, if the car’s cameras were too close, the system wouldn’t be able to perceive depth ... It also would be able to perceive depth if there wasn’t much texture on the truck (sounds like this was the case since the sides were plain white).
What bothers me is that this “blind” condition should have automatically triggered a vehicle slow down and alert the driver to take over (duh! Really? ... :-) ) This exact condition I described is one that should be tested to hell and back and then some ... It’s a well known corner case test.
I develop image processing applications for a living. A project I started to work on in 2010 is just now being deployed. The testing it went through was quite rigorous. Even now, the product is in limited release and won’t be in general release for a couple more years. We didn’t have a 10th of the variables that Tesla had when developing automated driving.
I dont care how brilliant their engineers are ... there is no way they’ve done enough real world testing if the information in this article is true and a crash occurs under these conditions. Testing is *everything* when it comes to autonomous vehicles. Sadly, that’s where corners are usually cut these days.
Car passed under trailer and the top of the car was sheared off, along with some of the occupant. Didn’t see that coming did he?
Poorest writing EVER!
Let’s write this right... A trucker at an uncontrolled intersection missed that there was an oncoming car with its daytime headlights on, and turned in front of it. Neither the Tesla driver nor the Tesla braked before crashing into the trailer, shearing off the top of the car. The car came to rest when it impacted with a telephone pole further down the road.
The trucker who missed the oncoming traffic before he blocked the road could still somehow identify the sounds of a Harry Pottery movie over the sounds of a cat impacting the trailer and most of the car continuing under the trailer and out the other side.
The only significant change from the age old story of a negligent trucker who blocked traffic with his rig is that the Tesla cameras could not detect the trailer across the lanes of traffic which it falsely identified as an unimportant horizon.
My question is didn’t the systems recognize the cab turning across the path before interpreting the white trailer as empty space and apply the brakes and alerting the driver?