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

Welcoming our first riders in San Francisco

blog.waymo.com

Post reply on HN
Print view View original

411–420 of 691 posts

Re: Welcoming our first riders in San Francisco

#411

Post by throwawaygh »

gibsonf1 wrote: post #330

You cannot predict the future with patterns from the past, regardless of how many patterns you crunch - the world is always changing. ML can just never solve FSD - conceptual understanding and causality is needed to achieve human level driving capability. We instantly classify things conceptually from our perception, instantly understand how those things may behave, and then learn the specifics of what that thing is…

> Autonomous driving efforts need a major pivot to start working with concepts, causality, and the integrated space time model of the world we humans use.

Dear god, no. I don't know what you think AV companies are doing past the perception layer, but they would be pivoting away from controls and planning -- you know, stuff that actually works outside of neurips/iclr/&c fantasy land.

Re: Welcoming our first riders in San Francisco

#412

Post by greesil »

seanmcdirmid wrote: post #360
sandworm101 wrote: post #235

Earlier quoted context omitted.

Middle steps: (1) Board members use product to travel to board meetings. (2) Board members use product as replacement for personal vehicles. (3) Board members demand pay increases. Back in 1999 the Chinese government announced that airline execs would be airborne at the changeover as reassurance that aircraft were safe from Y2K. Like or hate them, the incentive logic was sound. https://www.wired.com/1999/01/y2k-in-ch…

> Middle steps: (1) Board members use product to travel to board meetings. (2) Board members use product as replacement for personal vehicles. (3) Board members demand pay increases. How do you know board members aren't already using Waymo product heavily? It still doesn't mean they can go straight from board members using Waymo without backup drivers to arbitrary customers using Waymo without backup drivers.

Possibly to drive between their various houses?

Re: Welcoming our first riders in San Francisco

#413

Post by spywaregorilla »

MontyCarloHall wrote: post #59

“All rides in the program will have an autonomous specialist on board for now” This tells me that we’re still a long way from full level 4 (and certainly level 5) autonomy in a busy city like San Francisco. The edge cases requiring immediate human attention are still too frequent for the human safety driver to be remote, as is the case in Phoenix. Also, just a reminder that Waymo in Phoenix is nowhere close to being…

> ability to drive autonomously everywhere with zero human oversight with a safety record equivalent to the median human driver

I think this statement is off the mark. Comparing to a human is hard. Not many accidents happen because people are bad at driving. Driving is honestly pretty easy. They happen because people are distracted, tired, drunk, or perhaps just an asshole driving recklessly for thrills or for speed.

A self driving car might be a lot "worse" than the average human driver but could still be a huge improvement in terms of expected safety record for driving overall.

They don't need to be better than humans, they just need to be not shit 100% of the time unlike humans.

Re: Welcoming our first riders in San Francisco

#414

Post by ducttapecrown »

robterrell wrote: post #365
sshine wrote: post #346

Earlier quoted context omitted.

While controversial, we tolerate a great deal of casualties caused by human drivers without trying to illegalise those. While we can (and should) hold autonomous vehicle developers to a much, much higher standard than we hold human drivers, it is precisely because of excellence.

We actually do "illegalise" casualties by human drivers.

I'm sure the grand poster meant banning human driving entirely in order to prevent human driving casualties.

Re: Welcoming our first riders in San Francisco

#415

Post by InTheArena »

ancientworldnow wrote: post #265
leesec wrote: post #236

Earlier quoted context omitted.

"If Google can't do it with its massive resources and sensors don't ever expect a Tesla to perform better than this." 10 years ago this might have read: "If General Motors can't do it with its massive resources and sensors don't ever expect a Tesla to perform better than this."

Of course this ignores that super cruise is considered safer and better on the same tasks that it's allowed to do as Tesla FSD by third party analysts. The difference is GM is less willing to allow it to be enabled for dangerous beta driving unlike Tesla which clearly doesn't care about consistency or safety.

And when you look into thoose reports - the only reason they rank Super Cruise higher is because it can only be used on a very limited number of roads, and uses a camera to detect awareness.

FSD uses a camera, and works on all roads - and is dramatically better then supercruise.

source - test drove both, bought the tesla because of how impressed I was with supercruise.

Re: Welcoming our first riders in San Francisco

#416

Post by TulliusCicero »

MontyCarloHall wrote: post #59

“All rides in the program will have an autonomous specialist on board for now” This tells me that we’re still a long way from full level 4 (and certainly level 5) autonomy in a busy city like San Francisco. The edge cases requiring immediate human attention are still too frequent for the human safety driver to be remote, as is the case in Phoenix. Also, just a reminder that Waymo in Phoenix is nowhere close to being…

> human safety driver to be remote, as is the case in Phoenix.

It's not a remote human safety driver, it's more like a remote human safety coach.

The difference is giving high level directions vs directly driving the car. They don't remotely drive the car because that would obviously be super dangerous w/r/t connection stability/latency.

Re: Welcoming our first riders in San Francisco

#418

Post by noneeeed »

sterlind wrote: post #390
exdsq wrote: post #164

Earlier quoted context omitted.

I recently lived in Oxford where they have a few self-driving car trials (notably Oxbotica) that essentially just went round and round the station because of how awkward some of the junctions were. If we want to really test self-driving cars, introduce them to Milton Keynes 'Magic Roundabout' https://www.google.com/search?q=milton+keynes+magic+roundabo...

Apparently Brits hate the Magic Roundabout, but it seems so shiny.. just the idea of a roundabout of roundabouts where the inner flow of traffic is reversed is really pretty. I'm sure it's one of those things that looks great in traffic flow simulations but falls apart when panicked drivers are trying to deal with each other and the unconventional traffic patterns.

I don't think most people in the UK who express an opinion on it have ever actually used it.

I used to live round the corner from the magic roundabout. It's actually fine. The best analogy I have for it is juggling, if I concentrate too much and overthink it I drop the balls. If you over-think the magic roundabout it can seem intimidating, but when you're actually there it makes much more sense and you just go with the flow. You're not dealing with the whole system in one go, most people just take it one roundabout at a time.

One of the reasons it seems to work is that people take it easy, everyone is paying attention to what they are doing, and most people take it at a sensible speed.

Re: Welcoming our first riders in San Francisco

#419

Post by grlass »

hammock wrote: post #148
MontyCarloHall wrote: post #59

“All rides in the program will have an autonomous specialist on board for now” This tells me that we’re still a long way from full level 4 (and certainly level 5) autonomy in a busy city like San Francisco. The edge cases requiring immediate human attention are still too frequent for the human safety driver to be remote, as is the case in Phoenix. Also, just a reminder that Waymo in Phoenix is nowhere close to being…

>“All rides in the program will have an autonomous specialist on board for now” This tells me that we’re still a long way Did you expect something different? I can't really see a boardroom writing a roadmap that goes straight from test rides (no passengers) with a backup driver onboard to actual rides with passengers - no backup driver onboard with no in-between steps.

The book Halting State by Charlie Stross (2007) [1] had an interesting self driving car model, where it was autonomous on simple roads like highways/motorways, and a human driver took over remotely for more complex city streets.

Of course the book showed some failure modes for that, but I wonder if network coverage and latency, as well as "backup driver response time" could be considered good enough, perhaps this sort of model could have an acceptable risk trade-off.

[1] https://en.wikipedia.org/wiki/Halting_State

Re: Welcoming our first riders in San Francisco

#420

Post by spywaregorilla »

nradov wrote: post #92
ra7 wrote: post #19

It's fantastic to see Waymo's progress. SF is a real nightmare to drive. If they can nail it there, that's 2/2 for busy, urban street driving (SF) and "boring" suburban driving (Chandler, AZ). They've been quietly very confident of their tech, but this is a real test. Tangentially, I've also noticed that Waymo has picked up pace ever since the recent leadership changes. They are publishing more blog posts, offering m…

SF is hardly a nightmare to drive. Try Boston during a winter storm.

Try a southern state that has never seen snow before but got half an inch and is losing its collective mind.
Post reply on HN