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

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

electrek.co

Post reply on HN
Print view View original

91–100 of 100 posts

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

#91

Post by kube-system »

otterley wrote: post #87
kube-system wrote: post #79

Earlier quoted context omitted.

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 th…

That suggests the comparative bar should be "professional driver," which is perhaps somewhat higher than "average driver" (1.5x? 2x?) but not 10x higher.

That sounds reasonable for a practical general regulatory standard.

For a personal standard, it is reasonable that an individual purchaser may use their own risk profile as that standard... as many of the risks involved are not random but can be controlled through choice or are inherently personal. For example, about half of all traffic deaths are due to drowsy or drunk driving.

Accident risk for any given driver is highly distributed. For someone making a marginal choice to purchase a car, the choice they are faced with is choosing between the safety profile of a self-driving car and their own personal risk profile.

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

#92

Post by FireBeyond »

m348e912 wrote: post #70
senordevnyc wrote: post #16

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.

They manufactured thousands of CyberTrucks a month too. Then had to have SpaceX buy millions of dollars worth, while there's a huge amount of inventory gathering dust in storage.

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

#93

Post by parl_match »

FeloniousHam wrote: post #90
parl_match wrote: post #86

Earlier quoted context omitted.

it's very advanced adas. it is useful but you said "FSD" which stands for FULL Self Driving. You didn't say FSDS, or FSD Beta, or "Tesla's Level 2" self driving. It is NOT a FULL self driving solution yet. They are lying and you are repeating their lies.

Since we're into semantics and definitions, "FULL Self Driving" does not appear as a formal, defined standard. It is a brand. What's more, it is not a lie. The vehicle "fully" self drives (for me about 95% of the time).

"fully" "about 95% of the time"

folks you can't make this stuff up

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

#94

Post by m348e912 »

senordevnyc wrote: post #78
m348e912 wrote: post #70

Earlier quoted context omitted.

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.

Where did I say it was a good thing (or even a bad thing)? I was just making an observation, and yet downvoted for doing so.

Tesla is making a huge bet on robotaxi, it’s quite possible it will come to fruition.

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

#95

Post by senordevnyc »

m348e912 wrote: post #94
senordevnyc wrote: post #78

Earlier quoted context omitted.

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.

Where did I say it was a good thing (or even a bad thing)? I was just making an observation, and yet downvoted for doing so. Tesla is making a huge bet on robotaxi, it’s quite possible it will come to fruition.

I upvoted you, fwiw.

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

#96

Post by questionableans »

tharant wrote: post #80
questionableans wrote: post #54

Earlier quoted context omitted.

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 naviga…

I’m glad to hear it’s gotten better. This was a couple of years ago, when they were pushing the free trials. It’s an earlier Model 3, and I barely drive it.

I’m clearly not a typical driver. I love keeping the camera views all on screen for situational awareness. I don’t use cruise control and rarely use GPS navigation, even back when I used to drive cross country in previous cars. I guess I just got used to memorizing entire routes in my long distance biking days. Google Maps Street View really helps me understand exactly where I’ll be going.

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

#97

Post by questionableans »

marlow_congdon wrote: post #89
questionableans wrote: post #54

Earlier quoted context omitted.

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…

I’m also wondering when this was. I had similar experiences with my first Tesla (2022) and stopped paying for FSD except when I had road trips (then cancel again after). I’ve only felt comfortable using it by default in the past year.

Yeah, the car is significantly older than that, and I last tried the FSD trial a couple years ago.

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

#98

Post by ls612 »

9dev wrote: post #76
ls612 wrote: post #29

Earlier quoted context omitted.

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 po…

What senses do you need for driving besides sight and sound? All of the rest of this is just saying "the human brain has a well trained model for objects moving around in meatspace", the replication of which is literally the research project that all autonomous driving companies are trying to solve.

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

#99

Post by ls612 »

tqi wrote: post #81
ls612 wrote: post #60

Earlier quoted context omitted.

Even the average human ends up with about 1 fatality every 100 million miles and 1 serious injury every 10 million miles. The typical person will drive somewhere in the six figures of miles in their lifetime.

What's your point?

To point out that even your average human with 2 Mk. 1 eyeballs is not that awful at driving. We can absolutely do better with computers but the baseline is reasonably high.

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

#100

Post by sagarm »

xnx wrote: post #63
devy wrote: 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)…

The general approach to pioneering work like self-driving is: 1) Make it work 2) Make it right 3) Make it cheap For no good reason, Elon tried to solve step 3 before the other two. This is extra strange since SpaceX has done much better at pioneering work.

Tesla had to sell cars that can't self drive. They couldn't afford to add tens of thousands to the cost for slightly improved ADAS.
Post reply on HN