Earlier quoted context omitted.
How so? Here are the facts: 1. TCI writes a letter to Google saying that they should layoff employees. 2. A few weeks later, Google lays off employees. 3. Literally the day the Google layoffs are announced, TCI writes a letter to Google saying "I have appreciated our recent dialogue concerning Alphabet's cost base. I am encouraged to see that you are now taking some action to right size Alphabet's cost base and under…
As unilateral self-aggrandizing.
Waymo One doubles service area in Phoenix, continues growing in SF
341–350 of 520 posts
Re: Waymo One doubles service area in Phoenix, continues growing in SF
#342Earlier quoted context omitted.
I think the overlooked part is "seamlessly integrate". Signal to noise ratio is important, and it is not trivial to "just add sensors". I think the analogy of "too many cooks in the kitchen" applies here.
I think the keyword you’re looking for is ‘sensor fusion’, which apparently is only a problem for Tesla because the others have figured it out years ago. Perhaps there is a talent gap at Tesla or an unwillingness to invest in it. They generally avoid having to do anything that’s hard and try to look for shortcuts. Case in point: the whole radar removal and reintroduction flip flop. It seems like they don’t believe th…
Re: Waymo One doubles service area in Phoenix, continues growing in SF
#343Earlier quoted context omitted.
A hopefully not-too-annoying reminder that this isn’t a future that is sustainable or desirable to live in compared with alternatives. It’s really just better than the automotive hellscape you are used to. Phoenix is one of the most car-centric places to live in the country. The only reason anyone needs a service like this is because of the area’s complete failure in urban planning. Car-focused infrastructure is incr…
What you’re saying is probably true, but are you proposing razing Phoenix and rebuilding it as a less car-focused place? My sense is that that proposal wouldn’t be too popular with the people whose homes you’re tearing down, nor would necessarily the change in lifestyle they would be forced to undergo (after I’m sure what would be decades of rebuilding…).
When we talk about razing and rebuilding, it’s notable that this has already happened in our history. That’s how we have interstate highways cutting through urban areas and the destruction of the passenger rail network which was effectively razed and replaced by highways. Many big box stores and parking lots replace buildings that were destroyed (see before and after photos of downtown Houston, for example).
Most American cities outside of the coasts wouldn’t even exist without a railroad network that largely no longer exists.
These are all conscious choices and there’s no such thing as being stuck with cars-only infrastructure forever. The defeatism of saying that we are stuck with cars-only is a lie. After all, interstates regularly need billions of dollars of periodic investment just to keep them functional. Many states continually decide to do things like add lanes and enhanced interchanges at eye-watering costs that aren’t too dissimilar from the cost of adding new rail service.
For example, what if instead of spending $20 Billion in today’s dollars on the big dig in Boston, the elevated highway was simply demolished and the rest of the insane costs that were sunk into an underground highway went into expanding the commuter rail network and making a better rail connection to Logan airport (the blue line already nearly goes there with a short airport bus transfer, which could be further improved). That would reduce traffic in downtown Boston rather than expanding traffic by adding lanes and making driving more attractive than alternatives. This is already one of America’s most walkable cities but the highway was moved underground rather than removed.
$20 billion is so much money that entire new commuter rail lines could have been built for that price.
Re: Waymo One doubles service area in Phoenix, continues growing in SF
#344Earlier quoted context omitted.
Not only that. Tesla thought they could do it (better!) with an inferior sensor suite.
The argument was more that to do it generally you need vision to work, lidar will always be a narrow solution and redundant when you have vision. It might end up that solving the narrow city problem with high res maps is valuable enough to tackle anyway, but it could still be true that will never solve the general case. Of course, it could be true that Tesla was be unable to solve it also. Though at some point attach…
Re: Waymo One doubles service area in Phoenix, continues growing in SF
#345Earlier quoted context omitted.
Just because humans can generally do it without lidar and other sensors, does not mean that lidar and other sensors, would not improve human driving, if we could somehow integrate them seamlessly (and well reduce their price). A car equipped with more sensors, will always be better at handling more situations, than the one without them, no matter how "smart" their drivers become.
> A car equipped with more sensors, will always be better at handling more situations Yes, integrating seamlessly is the hard part. For Tesla, they found the increased sensor fusion complexity made the overall system less reliable, which was what informed their attempt at vision only. Karpathy went into this on Lex Fridman's podcast. Only with better sensor fusion algorithms that worst case the overall system perform…
Re: Waymo One doubles service area in Phoenix, continues growing in SF
#346Earlier quoted context omitted.
Good public mass transit presumably involves cops kicking out the smelly homeless people, right? I don't think that would fly in most places these days though, it isn't humane. Yet it's the only way to make public transit tolerable.
A better idea might be to provide the homeless with a better standard of living, therefore making them nicer to be around on public transport
Re: Waymo One doubles service area in Phoenix, continues growing in SF
#347Earlier quoted context omitted.
I think the overlooked part is "seamlessly integrate". Signal to noise ratio is important, and it is not trivial to "just add sensors". I think the analogy of "too many cooks in the kitchen" applies here.
Yeah, adding sensors can sometimes make things worse.
Re: Waymo One doubles service area in Phoenix, continues growing in SF
#348Earlier quoted context omitted.
> A car equipped with more sensors, will always be better at handling more situations Yes, integrating seamlessly is the hard part. For Tesla, they found the increased sensor fusion complexity made the overall system less reliable, which was what informed their attempt at vision only. Karpathy went into this on Lex Fridman's podcast. Only with better sensor fusion algorithms that worst case the overall system perform…
This is retroactive justification for using low-cost sensors. There's a chance they get lucky and pull it off with only cameras, but the chance of Tesla doing that is much less likely than Waymo getting their sooner with more sensors (or even even the Waymo driver achieving it with only vision if they chose. Using a full suite of sensors gives Waymo much better training data if they ever chose to use vision-only.
It's possible the lidar approach only really works with up to date high resolution maps and without that you end up in a local max you can't really escape with that approach.
That's been Tesla's argument up to this point anyway and I don't think the success in cities really proves things either way.
It may not matter since robotaxis in cities is still worth a lot and highway driving is mostly a solved problem.
True full self driving though will probably require solving vision - in that case I think the argument that lidar is a local max could very well be true.
Re: Waymo One doubles service area in Phoenix, continues growing in SF
#349Earlier quoted context omitted.
The argument was more that to do it generally you need vision to work, lidar will always be a narrow solution and redundant when you have vision. It might end up that solving the narrow city problem with high res maps is valuable enough to tackle anyway, but it could still be true that will never solve the general case. Of course, it could be true that Tesla was be unable to solve it also. Though at some point attach…
Birds fly by eating bugs and flapping wings, but that doesn't mean we should build planes that way. Tesla is stubbornly handicapping itself by cheaping-out on sensors because they think they can hail-mary yolo themselves all the way full self driving.
High resolution mapping works for localized solutions, but not in the general case.
I'm glad both groups are working on different approaches, it'll be better for us in the long run imo.
Re: Waymo One doubles service area in Phoenix, continues growing in SF
#350Earlier quoted context omitted.
Yeah, adding sensors can sometimes make things worse.
Example? There are plenty of examples where mistakes that Tesla's cameras make (being blinded by the sun, having trouble with emergency vehicles) are no problem for systems with more sensors.
Specifically this is the relevant part: https://youtu.be/g6bOwQdCJrc?t=1370
They removed radar because it was making things worse.