A lot of new cars come equipped with emergency braking systems, including affordable cars like Hondas. There has not been an increase in accidents due to these systems, nor has there been an epidemic of cars autonomously slamming on their brakes on the freeway for no reason. So I tend to think the manufacturers got the engineering and safety trade-offs right for those cars.
The big difference is that people who drive those cars do not generally expect that their cars are self-driving. Tesla owners do seem to expect that, and consequently the decisions made about trade-offs for, say, automatic braking in a Honda Accord are not the right decisions for a Tesla Model S.
The bottom line is this: if people think their cars can drive themselves, the cars really need to be able to do that or there are going to be crashes.
Now, most cars will do this these days, and do it using the same sensors they need to trigger air bag deployment even without ACC.
I don't know of any study that tries to estimate the effects of doing it earlier like the Audi with ACC does (IE no study tries to evaluate whether the ones without ACC sensors have achieved the optimal amount of pre-tension in the time they have, which would make pre-tensioning them earlier like the ACC systems do pointless)
I suspect that it's too difficult for the systems to accurately determine whether an upcoming object is actually in the lane. It's not uncommon to pass stationary vehicles parked on the side of the road. If you're approaching those vehicles along a curve, they might seem like they're in the road to a radar sensor even when they're not. I can see why it's a hard problem: attempting to detect these probably leads to too many false positives.
Still, you would think that there would be some threshold where the car decides, "Hey, this stationary obstacle is right in front of me. I should slow down"
You could imagine a next generation self-driving system that uses the combination of data from multiple sensors as well as maps to detect plausible obstacles. The mapping data could tell the vehicle when it should expect to turn. Maybe the vehicle could integrate imaging information from both radar and stereo cameras, to detect where the lane is, and which obstacles are in the lane.
Are there good existing techniques in the computer vision community for synthesizing data from multiple imaging sensors, like radar and stereo cameras and LIDAR? I'm imagining dumping all this data into an algorithm, getting back a 3D reconstruction of probable objects around me, along with metadata describing their velocity, confidence of the assessment, and all that.
> Still, you would think that there would be some threshold where the car decides, "Hey, this stationary obstacle is right in front of me. I should slow down"
From the article:
> When a car is moving at low speeds, slamming on the brakes isn't a big risk. A car traveling at 20mph can afford to wait until an object is quite close before slamming on the brakes, making unnecessary stops unlikely. Short stopping distances also mean that a car slamming on the brakes at 20mph is unlikely to get rear-ended.
But the calculation changes for a car traveling at 70mph. In this case, preventing a crash requires slamming on the brakes while the car is still far away from a potential obstacle. That makes it more likely that the car will misunderstand the situation—for example, wrongly interpreting an object that's merely near the road as being in the road. Sudden braking at high speed can startle the driver, leading to erratic driving behavior. And it also creates a danger that the car behind won't stop in time, leading to a rear-end collision.
So...dont brake suddenly. Decelerate, buy some time to collect and analyze more data and if the end result still appears to be a collision, then brake hard.
If a human driver started hallucinating behind the wheel, we would expect them to do the same, not maintain speed (or accelerate!) through the supposed object in their path.
This tech was supposed to be safer and more convenient than human driving, not a simulation of the decision-making abilities of a 12-year-old playing Grand Theft Auto.
> So...dont brake suddenly. Decelerate, buy some time to collect and analyze more data and if the end result still appears to be a collision, then brake hard.
This requires the automated brake computers to be connected to the autonomous cruise computers. According to the article, in most cars, these computers are separate systems.
It's like if one person operated the brake pedal, another operated the gas, and a third steering the car. When one hallucinates, the others might not realize right away.
This is exactly what previous generation AI in the 80's and 90's were criticized for: the systems built were too 'brittle'.
They worked well for the narrow domains they were programmed for but they couldn't deal with novel situations and had no way to generalize. It is not clear we can engineer our way out of this by just adding new rules.
Proponents of early symbolic AI systems (expert systems) said we just need to be patient and add more rules and at some critical point the system would reach the singularity. One such project has been going on for 34 years! https://en.wikipedia.org/wiki/Cyc
> Still, you would think that there would be some threshold where the car decides, "Hey, this stationary obstacle is right in front of me. I should slow down"
I think there is, it's just that by the time it reaches that threshold, the distance to obstacle is less than the stopping distance for the car at 60+ mph. A human making that judgment might steer around the obstacle, but AEB systems don't have that option.
> I suspect that it's too difficult for the systems to accurately determine whether an upcoming object is actually in the lane. It's not uncommon to pass stationary vehicles parked on the side of the road. If you're approaching those vehicles along a curve, they might seem like they're in the road to a radar sensor even when they're not. I can see why it's a hard problem: attempting to detect these probably leads to too many false positives.
This dilemma is only really bad for a passive system. For a system that's actively steering, it can make a committed decision to curve, so that even if it misjudged the obstacle it still won't crash.
It doesn't hurt to slow down for a predicted near-miss either, as you get close to it.
> Still, you would think that there would be some threshold where the car decides, "Hey, this stationary obstacle is right in front of me. I should slow down"
Yeah. There's a big difference between "obstacle might be in the way" and "obstacle is definitely in the way".
Sure, slamming in the brakes is a bad idea. This doesn't mean the system can't start to slow down or change the direction of the car.