Live data from Hacker News

Waymo CEO explains why Tesla’s camera-only self-driving falls short

electrek.co

71–80 of 100 posts

Re: Waymo CEO explains why Tesla’s camera-only self-driving falls short

#71
post #44

Earlier quoted context omitted.

I wish I were as rich as Elon but alas I'm just an ordinary person who appreciates more than one company competing to deploy autonomous driving technology. Appreciate the vitriol though, it tells me a lot about you as a person.

Excuse me did you just call me a highly corrosive acid made from sulfur dioxide? Reported. edit: I also want to point out that the fanboys conflate documented evidence in wikipedia of things EM has said with vitriol. It's like when people get banned on social media for hate speech for quoting something the POTUS said.

[dead]

Re: Waymo CEO explains why Tesla’s camera-only self-driving falls short

#72
post #47

I've been a Electrek reader for almost a decade. It's interesting to see its editor Fred Lambert from super pro-Telsa/Musk when fighting EV vs. ICE cars to anti-Telsa/Musk when Musk got into politics. Of course Musk knew multi-modality would win true Level 4 autonomous driving. It was a calculated tradeoff to work on vision first when LiDAR (components cost 10s of thousands and unreliable for continuous functioning)…

I'm hoping Tesla reincorporate Lidar (and Radar) because it will mean that they are able to put reality ahead of politics.

Musk being who he is, however, I'm not holding my breath for that outcome.

Re: Waymo CEO explains why Tesla’s camera-only self-driving falls short

#73

Earlier quoted context omitted.

> Self driving cars need to be 10x the average driver. Why? So long as they're insured and their owners can be held criminally liable for injuries just as a human driver would be, why does the bar have to be higher?

Because driving risk is far from evenly distributed. If a self-driving car drives like an average human driver, for responsible drivers, this would mean incurring more risk by getting into one. A huge portion of the risk of human drivers is due to confounding human factors like negligence, distraction, medical issues, fatigue, etc. Responsible drivers can take most of these factors into their own hands -- not driving…

We don't measure aggregate risk by discarding a part of the population, even if it's the poorer-performing part.

Even today, you cannot fully avoid this risk: when you get into a vehicle driven by a stranger, you don't know a priori whether the driver is excellent or average. Ideally customer feedback weeds out poor drivers and reduces accident rates, but I'm not privy to data that would prove or disprove whether that actually happens - especially because new drivers join the pool every day.

Re: Waymo CEO explains why Tesla’s camera-only self-driving falls short

#74

Personal experience, but my Tesla Model 3 drives most trips from start to finish. If I have to intervene, it's usually because other drivers aren't letting it into a lane and I have to get aggressive. Friends I know in Dallas and Austin (simpler, friendlier streets than where I live) say they don't drive at all anymore. Maybe it's not good enough for a robotaxi service yet, but the rate of progress since my first Tes…

Will the Tesla handle getting stuck behind a double parked car without your intervention?

Re: Waymo CEO explains why Tesla’s camera-only self-driving falls short

#75

Personal experience, but my Tesla Model 3 drives most trips from start to finish. If I have to intervene, it's usually because other drivers aren't letting it into a lane and I have to get aggressive. Friends I know in Dallas and Austin (simpler, friendlier streets than where I live) say they don't drive at all anymore. Maybe it's not good enough for a robotaxi service yet, but the rate of progress since my first Tes…

Will the Tesla handle getting stuck behind a double parked car without your intervention?

Usually yes. I was very surprised it also goes through confusing road works in my area without intervention. That requires driving on the wrong side of the road, without lines, over some of these metal plates. It waits for opposite traffic that has the right of way and then drives through the section like a human would do.

Re: Waymo CEO explains why Tesla’s camera-only self-driving falls short

#76
post #29
post #20

Earlier quoted context omitted.

Do you have any conception of how massively, incomprehensibly, extremely superior our sensory system is to any kind of camera-based computer vision we can make?

In terms of dynamic range and color space? Yes absolutely. But for driving you don't really need a huge color space and for dynamic range you can just use separate cameras for daytime and nighttime.

You're again thinking in terms of image sensors, which is not representative of what your body is able to do. For example, your brain processes signals from all your senses combined, which allows prioritisation of things that trigger multiple senses at once. It also applies pattern matching against millions of years of evolution's worth of information about danger.

But much more importantly, there is all sorts of post-processing happening that is so weird and complex and really a little decoupled from the raw visual information that it's futile to try and compare that to any digital operation you're thinking of in terms of cameras: If you were to look at a still captured from your eyes, you'd see an upside-down image that's only sharp in the very center of the image, blurry and desaturated pretty much everywhere else, grossly so in the corners, with several big black or blurry spots all over.

From that perspective, eyes are awful really. Yet still, your brain manages to turn the stereoscopic vision into a spatial representation, calculate the movement and keep track of other objects relative to you, fill in areas you can't actually see, detect things moving in your peripherals, highlight things of importance, and so much more.

Re: Waymo CEO explains why Tesla’s camera-only self-driving falls short

#77
post #47

I've been a Electrek reader for almost a decade. It's interesting to see its editor Fred Lambert from super pro-Telsa/Musk when fighting EV vs. ICE cars to anti-Telsa/Musk when Musk got into politics. Of course Musk knew multi-modality would win true Level 4 autonomous driving. It was a calculated tradeoff to work on vision first when LiDAR (components cost 10s of thousands and unreliable for continuous functioning)…

Tesla did not make Lidar affordable. They don't even use lidar. They also did not make lithium batteries affordable. Panasonic and CATL did that. Tesla was simply the first to exploit that bew affordability.

He did not say that Tesla made the LiDAR afforadable though.

Re: Waymo CEO explains why Tesla’s camera-only self-driving falls short

#78

Earlier quoted context omitted.

We already have those results. It’s why Waymo is doing millions of paid rides per month while Tesla is LARPing a robotaxi service that’s basically doing zero fully autonomous rides, as far as anyone can tell.

Tesla is manufacturing thousands of robotaxis a month. LARP or not, I'd be very surprised if none of the robotaxis are put to use.

How is that a good thing? They’re manufacturing thousands of vehicles that are reliant upon software and regulatory approval that they don’t have. They can’t even get their existing vehicles to work for Robotaxi, but they’re going to start building thousands of vehicles without steering wheels? OK.

Re: Waymo CEO explains why Tesla’s camera-only self-driving falls short

#79

Earlier quoted context omitted.

Because driving risk is far from evenly distributed. If a self-driving car drives like an average human driver, for responsible drivers, this would mean incurring more risk by getting into one. A huge portion of the risk of human drivers is due to confounding human factors like negligence, distraction, medical issues, fatigue, etc. Responsible drivers can take most of these factors into their own hands -- not driving…

We don't measure aggregate risk by discarding a part of the population, even if it's the poorer-performing part. Even today, you cannot fully avoid this risk: when you get into a vehicle driven by a stranger, you don't know a priori whether the driver is excellent or average. Ideally customer feedback weeds out poor drivers and reduces accident rates, but I'm not privy to data that would prove or disprove whether tha…

We absolutely can and do mitigate these risks when getting into vehicles driven by strangers: professional drivers typically have higher standards for driving history, and people can physically observe whether a friend/etc is drunk/distracted/etc.

But besides that, the people who are in the socioeconomic demographic to buy an expensive self driving car overlap with the demographic that have lower driving risk. For them, the self-driving car is more dangerous than driving themselves.

Re: Waymo CEO explains why Tesla’s camera-only self-driving falls short

#80

Personal experience, but my Tesla Model 3 drives most trips from start to finish. If I have to intervene, it's usually because other drivers aren't letting it into a lane and I have to get aggressive. Friends I know in Dallas and Austin (simpler, friendlier streets than where I live) say they don't drive at all anymore. Maybe it's not good enough for a robotaxi service yet, but the rate of progress since my first Tes…

Tried FSD once. It was very confused about a traffic circle, cruised up to it & slammed on the brakes. Got rear ended (at low speed). The incomplete, miscategorizing and glitching display of other vehicles and obstacles does not give me confidence that the car is able to correctly identify what’s around it, let alone drive accordingly. Even the lane departure warnings are 90% false positives (but I’d rather be warned…

How long ago was it that you tried FSD? My car (HW4) had a lot difficulty like this in the early days of FSD 11 but over the past thirty months it's gone from "good at highway driving, not very good at navigating city streets and it might try to kill me" to "nearly perfect at everything". Over the past six months, most of my interventions have been to avoid it automatically parking in handicap spaces and minor navigation issues when I know there's a quicker/better route. Since FSD 14.2, I've done 23k miles with 94% of that on Full Self Driving. Longest streak was 930 miles where it took me on a road trip out of state and then back home and I never touched the wheel; it handled parking at chargers and diners, navigating strange destinations (small towns, back roads), avoiding two deer that I almost certainly would have hit, and managed to keep 85mph while navigating traffic during rush-hour in Chicago. I've never owned a product, much less a vehicle, that got so much better over time.
Post reply on HN