Utah Model S data release

[Bmac]

What confuses me about the release of data on the Utah Tesla model S crash is that the autopilot did not detect an object directly in front. I realize a standing object like a parked car can be confusing but one would think autopilot would react much faster than the human did.

 

[kingjamez]

The car was going too fast. At 45mph and above AP in it's current form can't detect stopped objects.
TACC works great when you have flowing traffic, but go from 60mph to a dead stopped object and it won't see it.

-Jim

 

[Bmac]

ok, that's interesting. thanks.

 

[Tam]

...detect...

Please read the explanation at:

Why Tesla's Autopilot Can't See a Stopped Firetruck

This has been an ongoing problem with RADAR that is still haunting us.

To help the RADAR out, others have added LIDAR that can detect and measure a stationary obstacle in 3 dimensions.

Tesla goes a different route with TeslaVsion to help out the RADAR but it is not activated yet.

So, keep expecting more of this scenario to happen while technology will get some help down the line!

 

[jsmay311]

I found some details here:
Tesla driver who crashed into truck on Autopilot got a citation as Tesla releases logs and the NHTSA investigates

Tesla has now obtained the data logs from the car, which the South Jordan Police Department shared in a report:

• The driver engaged Autosteer and Traffic Aware Cruise Control on multiple occasions during this drive cycle. She repeatedly cancelled and then re-engaged these features, and regularly adjusted the vehicle’s cruising speed.
• Drivers are repeatedly advised Autopilot features do not make Tesla vehicles “autonomous” and that the driver absolutely must remain vigilant with their eyes on the road, hands on the wheel and they must be prepared to take any and all action necessary to avoid hazards on the road.
• The vehicle registered more than a dozen instances of her hands being off the steering wheel in this drive cycle. On two such occasions, she had her hands off the wheel for more than one minute each time and her hands came back on only after a visual alert was provided. Each time she put her hands back on the wheel, she took them back off the wheel after a few seconds.
• About 1 minute and 22 seconds before the crash, she re-enabled Autosteer and Cruise Control, and then, within two seconds, took her hands off the steering wheel again. She did not touch the steering wheel for the next 80 seconds until the crash happened; this is consistent with her admission that she was looking at her phone at the time.
• The vehicle was traveling at about 60 mph when the crash happened. This is the speed the driver selected.
• The driver manually pressed the vehicle brake pedal fractions of a second prior to the crash.
• Contrary to the proper use of Autopilot, the driver did not pay attention to the road at all times, did not keep her hands on the steering wheel, and she used it on a street with no center median and with stoplight controlled intersections.

Every time it says "she had her hands off the wheel", wouldn't it be more accurate to say that "her hands weren't detected on the wheel"?

I've only driven a Model 3 and not a Model S, but there were LOTS of times when my hand(s) were on the wheel but the car didn't detect it because I wasn't tugging hard enough on the wheel.

 

[Tam]

..."her hands weren't detected on the wheel"...

Correct!

Hands on wheel don't count if there's not enough torque so the driver can feel how the automation is doing.

Without knowing how the automation is turning the wheel, the manually correction might be too late!

 

[Electroman]

There is another thread on the same topic: Blog - Tesla Releases Data on Utah Autopilot Crash