Live data from Hacker News

Why emergency braking systems sometimes hit parked cars and lane dividers

arstechnica.com

101–110 of 244 posts

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#101
post #2

This article and many others like it are written as if one ought to be ashamed for thinking self driving cars should not routinely smash into stationary objects on their paths or kill people: This isn't the only recent case where Autopilot steered a Tesla vehicle directly into a stationary object—though thankfully the others didn't get anyone killed. Back in January, firefighters in Culver City, California, said that…

I think Timothy B. Lee, the author of the article, was caught up in the early hype about "self-driving" cars, obviously before he (or many others) had a good understanding of the technology. He's covered the field extensively. Now that the limitations of the technology are becoming more clear, it seems to me he's trying to negotiate the very narrow border between keeping his original enthusiasm up, and not spreading…

Timothy B. Lee here. You are correct, except that I think it's a mistake to treat ADAS systems as "self-driving cars." I'm bullish on true self-driving car projects like Waymo and Cruise. I think ADAS systems have a lot of problems that have become more clear to me as I've covered them in more depth.

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#102

Earlier quoted context omitted.

The key thing seems to be that the automatic breaking system has a group of systems each designed to satisfy multiple constraints and these systems aren't particularly well integrated. This seems like how I would imagine a "dumb" system would be designed. One would imagine a "artificial intelligence" (of any sort at all) would find a way to smoothly integrate all these system. The problem is end-to-end neural nets or…

I would generally prefer smarter (more error prone) systems to be surrounded by dumber systems. So the break pedal overrides everything, then you'd have a run of the mill radar breaking system, regular lane following system, and only after that (and maybe even further back) the more advanced self driving-ish stuff. It's weird that it isn't designed that way, since that's the way automated systems in factories and the…

So the break pedal overrides everything, then you'd have a run of the mill radar breaking system, regular lane following system, and only after that (and maybe even further back) the more advanced self driving-ish stuff

The problem the article points out is that there's no safe, dumb response to radar seeing something stopped right in front of a car going 70 mpg.

If anything, the systems the article describes are a lot like what you describe - a bunch of semi-separate systems each of which can do something if it can be sure that something is safe and which do nothing otherwise.

The problem seems to be that given enough no-easy-answer situations, you wind-up with a false sense of security.

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#103
Am I the only one who thinks the fault primarily lies with the driver? He trusted his life in equipment he didn't adequately understand and/or put to much faith in. This is not to say that Tesla and others shouldn't learn from this and try to improve their systems and driver education, of course. But drivers should also understand how their cars work, and respect their limitations.

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#104
post #47

It's currently illegal to say that something can cure cancer, and this is because a lot of people just don't understand to the details of fighting cancer to really know what a cure means. Perhaps we need to regulate how driver assistance is sold so that people don't accidentally think they can just keep their eyes off the road?

The only irresponsible car company has been Tesla (and Uber). All the other companies positioned their adaptive systems correctly and very conservatively. Tesla came out and downright asserted their system was autonomous[1]. Predictably, they have since had to scale that back significantly.

[1]https://www.tesla.com/en_CA/videos/autopilot-self-driving-ha...

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#105

>> So the people designing the next generation of autonomous driving systems are going to need a fundamental philosophical shift. Instead of treating cruise control, lane-keeping, and emergency braking as distinct systems, advanced driver assistance systems need to become integrated systems with a sophisticated understanding of the car's surroundings. My understanding was that self-driving systems are trained end-to-…

"braking"!

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#106

Earlier quoted context omitted.

>> It sounds like “Autopilot” has no world model (or an extremely basic one) It should be noted that no AI system has anything like that. A model of the entire world is beyond current technological capabilities.

I believe the meaning in this context is just a model saying what objects are nearby, where they are, how large they are, and what their velocity vectors are, and maybe guesses as to what kind of object (car, truck, pedestrian, lamppost, etc.) they are.

The thing is that a bunch of data with something like objects and velocities isn't a world model. "How Large" a given thing is, is only one of a multitude of questions.

I think we humans are so good at just passively keeping track of everything in our environment we forget how difficult it is "keep a world model" from what one sees.

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#107
post #49

Earlier quoted context omitted.

Seems like something that will be most enjoyed post-retirement, a godsend for American seniors who don't live in cities with good mass-transit.

I'm sure all the seniors love riding public transit.

In parts of the UK, seniors get free travel on buses. That’s very popular. Even where it’s not free, buses can be great for older people who aren’t able or confident to drive (due to mobility, eyesight, etc).

If your buses aren’t popular with old people, you have bad buses.

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#108
post #47

It's currently illegal to say that something can cure cancer, and this is because a lot of people just don't understand to the details of fighting cancer to really know what a cure means. Perhaps we need to regulate how driver assistance is sold so that people don't accidentally think they can just keep their eyes off the road?

The only irresponsible car company has been Tesla (and Uber). All the other companies positioned their adaptive systems correctly and very conservatively. Tesla came out and downright asserted their system was autonomous[1]. Predictably, they have since had to scale that back significantly. [1] https://www.tesla.com/en_CA/videos/autopilot-self-driving-ha...

They have also been asked to rename the "Autopilot" feature..

https://www.forbes.com/sites/bertelschmitt/2016/10/14/german...

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#109

Earlier quoted context omitted.

That very much depends on where you live. It's generally a lot better in Europe for a variety of reasons: historical, political and geographical. I use public transit quite a bit here in Vancouver but my limited experience of it in SF gives me some appreciation why people might not want to use it there.

People smell better in Europe? When people trot out their arguments against public transportation they always refer to the inefficiencies and completely ignore the human element. No one wants to be crammed in a small space with a bunch of strangers every day.

Like... an office?

Re: Why emergency braking systems sometimes hit parked cars and lane dividers

#110
post #56

Earlier quoted context omitted.

Insurance companies which have hard data will lower your rates if your car has autopilot. I am sure they base that on hard data I don't have. If you have better data than I would love to see it. But, IMO using ballpark numbers is much better than simply having a bad feeling about something. These cars are not going to fail the same way people do. Computers really fuck up in broad daylight, people get drunk and drive…

Unless you've seen something different than I have, it is one insurer offering a small discount in the UK. Nobody in the US. The data is too sparse at this moment for an insurer to take much of a risk. Especially with recent Tesla missteps with autopilot updates.

I hadn’t heard about that UK insurer.

I wonder if it’s mainly another way of getting access to telemetry data? Insurers definitely do give you a discount if you install a recording device. I assume that lets them filter out some bogus insurance claims. (Or maybe people just drive better when they know the insurance company is watching!)

Post reply on HN