Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

fuelarc.com

Post reply on HN
Print view View original

331–340 of 449 posts

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#331

Post by ndsipa_pomu »

kjkjadksj wrote: post #208
ModernMech wrote: post #181

Earlier quoted context omitted.

I'm a roboticist who had learned from researchers involved in the 2007 DARPA urban challenge. The key takeaway from that event was that every single car that finished the race was equipped with the 3D velodyne LIDAR. It was that technology that enabled driverless cars to work as a concept. Why? Because it provided information that people had to infer, and that you couldn't easily get from camera. So absent the human…

I mean what does lidar do but tell you distance? A rangefinder optic from 1940 can also tell you distance with two little offset windows purely optically and accurately. Millions of rolls of films shot on this principle of optical distance finding. And yet, this is no good now, because IMO its musks idea and thats enough to poison it among the armchair engineers than any other reason. Telling to this point is how eve…

The important thing about LIDAR is not so much that it is reporting a distance, but that it is reporting distances to actual objects. Cameras don't distinguish objects and so there has to be a lot of processing to try to tease out the objects from the background and this appears to be what's causing issues with Teslas.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#332

Post by Spooky23 »

vitus wrote: post #297
Spooky23 wrote: post #271

Earlier quoted context omitted.

The Elon magic is getting people to bikeshed bullshit like this and ignore the bigger issues. You don’t gouge out your ears because you hear something walking around at night that doesn’t appear to be accurate. As a human, your executive function makes judgements based on context and what you know. Your eyesight is degraded in the dark, so your brain pays more attention to unexpected sound. The argument for lidar, so…

What? I was responding to the specific claim that two independent sensors always make your failure rates go down. Not that any particular source of sensor data is strictly inferior. I agree that optimizing for vehicle cost and shipping shoddy software at the expense of human lives is the wrong tradeoff, and having different sensors that provide more coverage of situations is generally preferable if you can afford it.…

If you’re Tesla, the answer is going to treat it as a driver assistance tech… turn off the automatic feature and throw an alarm. Hopefully the driver has time to reorient, if not, his problem.

If you’re Waymo, you’ve built in a higher standard of sensor and diagnostics, at the expense of the aesthetic.

That’s always been the issue with Tesla… they push 99% solutions for 99.99% problems.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#333

Post by luckylion »

scarface_74 wrote: post #168
luckylion wrote: post #109

Earlier quoted context omitted.

But isn't that also because it's new? Plenty of people die in work accidents because equipment malfunctions, but unless it's a specific type of equipment blowing up at alarming rates, nobody asks to pause e.g. all power-drills. I believe that has been pretty much figured out, and insurance companies offer policies that cover it. Sure, they are usually not "intelligent", but are auto-pilots in cars?

The people who die in workplace accidents are only affecting them. It’s completely different if an autonomous vehicle injured someone else. Also dangerous workplaces are carefully controlled access environments where only the people that work there are in danger. Imagine if airplane fatalities happen even 1% as often as car fatalities? Right now the ratio is around 770:1 per passenger mile.

I assume that airplanes would have to offer much more value for that to be accepted, but they are mostly a luxury while cars are a necessity - life as we know it in much of the Western world would come to a screeching halt without cars, but it continues mostly unchanged without planes.

I don't think I agree that workplace accidents are that different. It's not primarily the workers who die who benefit from those machines that kill them - I'd say the workers _are_ someone else.

It's just that we've gotten used to that, and we feel like the number is steady and low enough that it's easily outweighed by the gigantic benefits we get from industrialization. My assumption is that it's the same way for cars and car-related deaths, but we haven't extended it to self-driving cars yet.

Individually, everybody sees the benefit, but once integration of FSD hits the commercial side and consumer prices are being reduced as a direct consequence, deaths become work-place accidents. Like a truck with a human driver killing an "innocent" pedestrian - it's accepted because we really want the trucks.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#334

Post by stephc_int13 »

xbmcuser wrote: post #22

The point I soured on Musk was when he ditched radar/lidar and tried to go with camera's alone. This made me realize he is not the genius he is made out to be but instead he is a fraud/charlatan and over the years his statements on different topics have only hardened that belief. Why the fuck would you want ai cars to be the same as humans you should want them to be many times better and radarr/lidar sonarr type tech…

I fully agree on this.

Computer Vision has turned out to be a very tough nut to crack and that should have been visible from anyone doing serious work in the field since at least 15 years ago.

In any case, any safety critical system should be build with redundancy in mind, with several sub systems working independently.

Using more and better sensors is only a problem when building a cost sensitive system, not a safety critical one, and very often those sensors are expensive because they are niche, that can be mediated with mass scale.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#335

Post by sudosysgen »

pfannkuchen wrote: post #77
xbmcuser wrote: post #22

The point I soured on Musk was when he ditched radar/lidar and tried to go with camera's alone. This made me realize he is not the genius he is made out to be but instead he is a fraud/charlatan and over the years his statements on different topics have only hardened that belief. Why the fuck would you want ai cars to be the same as humans you should want them to be many times better and radarr/lidar sonarr type tech…

You do want them to be better than humans, but vision quality is not really a major source of human accidents. Accidents are typically caused by driving technique, inattention, or a failure to accurately model the behavior of other drivers. Put another way - would giving humans superhuman vision significantly reduce the accident rate? The issue here is that the vision based system failed to even match human capabilit…

Human eyes are in many ways far superior to reasonably priced vision sensors. This isn't giving humans superhuman vision, it's changing the tradeoffs human vision has (without changing the cognitive process that it coevolved with to begin, and which is the most important part of why we get into accidents).

There is no affordable vision system that's as good as human vision in key situations. LiDAR+vision is the only way to actually get superhuman vision. The issue isn't the choice of vision system, it's to choose vision itself, and besides the lesson from the human sensory system is to have sensors that go well with your processing system, which again would mean LiDAR.

If humans could integrate a LiDAR-like system where we could be warned of approaching objects from any angle and accurately gauge the speed and distance of multiple objects simultaneously, we would surely be better drivers.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#336

Post by bumby »

smallmancontrov wrote: post #311
bumby wrote: post #289

Earlier quoted context omitted.

If Tesla is Level 2, that link doesn’t support the OPs point about “all” incidents, but rather only those involved in a fatality, hospital treatment, airbag deployment, or towed vehicle. Am I reading that link correctly?

The problem with "all" incidents is that reporting bias drowns the whole thing in noise. I clipped a curb the other year and didn't report it to anyone -- am I messing up the statistics? In contrast, hospitalizations and bodies are concrete enough to all but eliminate reporting bias. Of course, at first this just substitutes one type of problem for another because even shitty drivers have to drive many lifetimes of d…

It almost belies a need for some sort of standardized testing as well. Self-reporting seems like a weak point that can be gamed.

To your point about luddites, that’s why I think it’s erroneous to use “as good as a human” as the metric. It will need to be much better than a human but those people reluctantly trust it enough to hand over control.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#337

Post by maximilianthe1 »

larvaetron wrote: post #164
Retric wrote: post #146

Earlier quoted context omitted.

Cars unlike aircraft don’t need to move forward to maintain safety. If the lidar normally has very good uptime but happens to break, you need to safely come to a complete stop and that’s basically it. Trusting vision systems for 30 seconds or even 30 minutes over the lifetime of a car is very different than trusting them for 30,000 hours. So for edge cases sure, add a “this is an emergency drive to a hospital without…

> Cars unlike aircraft don’t need to move forward to maintain safety. They do if they're crossing railroad tracks.

In case of self-drive malfunction you still have a gas pedal under a human's foot

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#338

Post by gruez »

NoTeslaThrow wrote: post #167
gruez wrote: post #131

Earlier quoted context omitted.

It's pretty obvious from the context of the thread that "vision quality" refers to LIDAR vs cameras, and that human vision is good enough, not that being legally blind doesn't somehow doesn't affect driving quality.

Human vision isn't good enough, though. Otherwise why not just drive the car yourself?

>Human vision isn't good enough, though.

Maybe if your standard is "scheduled commercial passenger flights" level of safety.

>Otherwise why not just drive the car yourself?

There's plenty of reasons why humans can be more dangerous outside of vision quality. For instance, being distracted, poor reaction times, or not being able to monitor all angles simultaneously.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#339

Post by sudosysgen »

Workaccount2 wrote: post #145
xbmcuser wrote: post #22

The point I soured on Musk was when he ditched radar/lidar and tried to go with camera's alone. This made me realize he is not the genius he is made out to be but instead he is a fraud/charlatan and over the years his statements on different topics have only hardened that belief. Why the fuck would you want ai cars to be the same as humans you should want them to be many times better and radarr/lidar sonarr type tech…

It's because the sensor suite for lidar is expensive and HD cameras are basically a commodity at this point. So if your goal is to pump out $20k self driving cars, then you need cameras to be good enough. So the logic becomes "If humans can do it, so can cameras, otherwise we have no product, no promise."

I wish this myth would die. Anyone who picks up a camera would know that it isn't true, there are many things even very expensive cameras can't do that humans can. Specifically, the mix of high acuity when needed but wide angle, low-light movement performance, and tracking fast objects is something that only a camera system in the tens of thousands of dollars can do, and those are all relevant to driving.

Re: Self-Driving Teslas Are Fatally Rear-Ending Motorcyclists More Than Any Other

#340

Post by ben_w »

triplesec wrote: post #295
ben_w wrote: post #273

Earlier quoted context omitted.

Enumerating all the narrow edge cases has proven surprisingly difficult.

but train tracks is not that kind of edge case, tbh, it's so vanishingly situational

"Train tracks" are a subset of all the edge cases in the set "car can't just stop and stay stopped and that's safe".
Post reply on HN