Hacker News Reader

Comment by smogcutter | Hacker News Reader

This seems like an obvious thing to do: if you’re trying to test the AI, remove complicating, possibly contradictory OEM systems.

But compare with the other discussion currently on the front page, where users point out system subsumption is a basic safety principle. You need a safety system to fall back on if the AI fails (as it will, at least at this stage). It seems grossly negligent if Uber didn’t re-implement collision avoidance at a lower level.

Edit: link to discussion I’m thinking of https://news.ycombinator.com/item?id=16681611

View on HN

Why is "car's built-in system took control" harder to handle than "human safety driver took control"? Seems like they are exactly the same: "external system took control".

I would imagine it's easier to hook into human operated controls than to car's internal systems. Just put some sensors on steering wheel, pedals, handbrake and couple of others and you will know when someone uses them. If they are used, give up control of the car (or the specific system that was controlled).

Getting information that some automated system initiated some operation is almost certainly harder. System only knows that the car is not behaving as expected, but it doesn't know what caused it. You could probably figure out how to determine if something like collision avoidance was triggered (large shifts in expected vs actual outcomes), but in case of something like ABS you could end up with two systems fighting for the control over brakes in emergency situation.

Integrating the two systems must be fiddly, sure, but fundamentally not hard and fairly easy to test.

Compared to all the other aspects of making a self-driving car, which are genuinely very, very hard and require groundbreaking technology, it seems incredibly lazy and negligent not to get this bit right.

The auto-brake systems in all cars will activate the same brake-is-on switch as the human operator. Often, it's just a switch on the brake pedal assembly. Trivial to tap into it.

If the switch state changes from closed to open, [driver|AEB] have intervened and Uber's system should relinquish control of that sub-system.

> If the switch state changes from closed to open, [driver|AEB] have intervened and Uber's system should relinquish control of that sub-system.

No, both cases are fundamentally different. If a human driver has intervened, the system should expect the human wants to take over all subsystems: braking, steering, accelerating. If the AEB has intervened, the system should expect it will take over only the braking, and only for a limited amount of time; it shouldn't relinquish control (and doesn't have to, since a properly-designed AEB will be an override of the braking control), and should be ready to take over immediately after it releases (and probably bring the car to a safe stop as soon as it has control back).

That is, the self-driving system must know whether the command came from the human driver, or from another system.

Steering input sensed, give up steering control. Brake input sensed, give up brake control.

I'm not convinced the two should be linked in any way, human driver or AEB or whatever else. If the human is taking evasive action, the auto-drive is getting input from all the available sensors.

This shouldn't be that hard (relative to the other challenges being faced).

The human knows to take over complete control. Not just brakes, but also steering, indicators etc.

The auto braking system doesn't do steering, nor indicators. So, you can't treat those the same.

Hard to claim complete control if the car is hitting the brakes for you.

Does not seem obvious to me at all. First thought I had when hearing of the accident was "how come Volvo didn't break, they advertised the tech quite a bit few years back?"

Sure, because as a responsible person you’re more interested in safety than training a neural net.

Reply on news.ycombinator.com