Got to this question late. We had this happen [1] during our first unmanned run completely unintentionally. We were testing our 1st gen emergency and diagnostics systems, and the truck ground to a halt a few minutes into the test. Our teleoperation center lost complete power (freak outage, no weather or anything) so the teleop station disconnected, even though our UPS was still working along. We've made a few changes to support this case a bit more, but the broad strokes worked in that case. Long story short, the truck will stop itself. There are many different ways we try to do that more safely depending on road conditions, and those are outlined in the VSSA linked elsewhere.

Link below is a dramatized account of the events, couldn't find anything less editorialized, sorry!

[1] https://www.caranddriver.com/news/a19177797/self-driving-tru...

I would love an answer to this, as I believe this is why this approach is fundamentally flawed and why others are not pursuing it.

Page 8 of this PDF has a table of failure modes:

https://uploads-ssl.webflow.com/599d39e79f59ae00017e2107/5c1...

Thanks for the link. This basically says in that scenario (which I did not see specifically mentioned in my admittedly cursory glance) is to just hit the brakes...and then since there's nobody in the truck and there's no wireless signal it's just stuck there until someone goes there in person or the cell signal comes back up.

What if signal is lost while the truck is performing an unprotected left turn, in front of oncoming traffic with right of way? Braking in that situation will not be safe.

... during lane change? ... on highway?

The pdf is pretty helpful! Outside of total system failure, it will try to find a shoulder, and if it can't do that it will gradually come to a stop inside its lane.

In such an instance, “controlled stop” means that the system has the capability to control both steering and braking, so that the system can continue to ensure it is not leaving the lane as it brakesand is not hitting objects in the lane ahead. “Immediate stop” is the final fallback mechanism for the extremely improbable occurrence that everything in the system is failing.

That was the paragraph I found interesting. It seems to me in the worst case scenario from what I can tell it just slams the brakes and hopes for the best. It would be interesting to hear a response of what the truck would do in a jamming situation. I assume since it would not lose it cameras and other sensors it would slow down and pull over.

Sounds like the beginning of the next reboot of Fast and the Furious in ten years.

I'd trust a stupid autonomous system to be safer than a driver who loses consciousness during one of those situations. You just need to make sure that the system doesn't break down completely more often than human drivers have a heart attack at the wheel.

I feel like losing cell signal is more common than having a heart attack.

I feel there are good mitigating options here:

- they could use vehicle-mounted transceivers with much better antennas

- they could use redundant transceivers on different networks

- they could map out routes with best signal. Remember this is last mile only, so it's not a huge area. Instead of going the shortest way a la Waze, optimize the route for best signal.

It is not just loosing cell signal completely, but even smaller latency increase can make teleoperation much less reliable.

Should it be performing turns in front of traffic coming that doesn't have time to stop?

> ... during lane change?

Apart from being more in the way, how does this differ from having to stop within a lane?

> ... on highway?

The article says its automated driving on the highway.

Handwaving this question says it all really.