Blog NTSB Releases Preliminary Report on Autopilot Crash

The U.S. National Transportation Safety Board issued a preliminary report on a fatal March 23 crash involving a Tesla Model X using Autopilot near Mountain View, Calif.

Investigators leveraged data pulled from the car’s computer that shows the driver’s hands were on the steering wheel for just 34 seconds during the minute before impact.

Data also showed that the Model X sped up to 71 miles per hour just before hitting a highway barrier. Tesla issued a release in March that included most of the info in the report. Tesla said “the driver had received several visual and one audible hands-on warning earlier in the drive” and the driver had about five seconds and 150 meters of unobstructed view of the concrete…but the vehicle logs show that no action was taken.”

The NTSB report said the crash remains under investigation, with the intent of issuing safety recommendations to prevent similar crashes. No pre-crash braking or evasive steering movement was detected, according to the report.

“Tesla Autopilot does not prevent all accidents — such a standard would be impossible — but it makes them much less likely to occur,” Tesla wrote in its March post. “It unequivocally makes the world safer for the vehicle occupants, pedestrians and cyclists.”

Read the full report here.

 

[mongo]

The way I worded it makes it seem like the sampling rate is somehow relevant. It doesn't matter how many times a second it's sampled because the sensor itself isn't really even designed to detect hands at the wheel.

It's designed to detect torque. As you said it's meant for electrical power steering where it's necessary to determine where the driver wants to go.

Most of the time it senses my hand not because I'm applying torque, but I'm resting my hand at the wheel while it's doing minor correction.

What's funny is Tesla is changing the hold steering wheel message to something else to help educate drivers that it's actually detecting torque. So the drivers apply torque versus just holding.

But, what they report still reads as if the sensor somehow knows if someone is holding the wheel on a per second basis.

Gotcha.
I'd say there are two aspects to it:
Passive attention detection: which it is not great at. If it registers hands detected then the driver is definitely hands on (or using defeat device), but the false negative rate is high. If AP worked perfectly, this system would never detect two handed drivers since the steering inputs would always match.

Active attention detection/ Driver interaction: if the driver instigates a maneuver other than what AP is trying to do, that will definitely register. First as hands on wheel, then as AP kicking off.

So in cases where there is a crash and there are no hands-detected data points in the moments before, it does not mean the driver's hands were not on the wheel, but it does mean the driver did not apply a steering correction before the impending collision for whatever reason.

 

[Peteski]

Gotcha.
I'd say there are two aspects to it:
Passive attention detection: which it is not great at. If it registers hands detected then the driver is definitely hands on (or using defeat device), but the false negative rate is high. If AP worked perfectly, this system would never detect two handed drivers since the steering inputs would always match.

Active attention detection/ Driver interaction: if the driver instigates a maneuver other than what AP is trying to do, that will definitely register. First as hands on wheel, then as AP kicking off.

So in cases where there is a crash and there are no hands-detected data points in the moments before, it does not mean the driver's hands were not on the wheel, but it does mean the driver did not apply a steering correction before the impending collision for whatever reason.

I think this is a good summary. Although I think passive detection of two hands on the wheel depends on whether or not the driver is trying to steer along with AP or just holding the wheel. If I just hold the wheel with two hands and lightly resist any auto-steering then the sensor registers my resistance. But if I'm driving in a straight line with 2 hands on the wheel I get more nags because there is no steering input from AP and no resistance torque from my hands. So one-handed works best for avoiding nags, but not the best solution for safety.

I think what the system needs is both torque sensing for the active hand detection (i.e. in over-riding AP etc) and touch sensors for passive hand detection, so a 2-handed hold is not penalised like it currently is!