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

Waymo robotaxis are now giving rides on freeways in LA, SF and Phoenix

techcrunch.com

Post reply on HN
Print view View original

171–180 of 456 posts

Re: Waymo robotaxis are now giving rides on freeways in LA, SF and Phoenix

#171

Post by QuercusMax »

crazygringo wrote: post #144
jeffbee wrote: post #85

Earlier quoted context omitted.

My hot take is that anyone who would take a taxi from JFK to Manhattan, along the most well-served transit corridor on the continent, is probably a psycho and we shouldn't ask for their input on transportation topics.

You do realize that public transportation doesn't provide luggage carts? That you can't take those out of the airport? If you're traveling with a family or group, it really is often going to be much easier to take an XL Uber than deal with turnstiles and transfers and stairs and everything.

So what you're saying is if you're not in a big group or traveling with family, you absolutely SHOULD take public transportation.

Re: Waymo robotaxis are now giving rides on freeways in LA, SF and Phoenix

#172

Post by embedding-shape »

GloamingNiblets wrote: post #118
xnx wrote: post #39

Earlier quoted context omitted.

Highways are on average a much more structured and consistent environment, but every single weird thing (pedestrians, animals, debris, flooding) that occurs on streets also happens on highways. When you're doing as many trips and miles as Waymo, once-in-a-lifetime exceptions happen every day. On highways the kinetic energy is much greater (Waymo's reaction time is superhuman, but the car can't brake any harder.) and…

I don't have any specific knowledge about Waymo's stack, but I can confidently say Waymo's reaction time is likely poorer than an attentive human. By the time sensor data makes it through the perception stack, prediction/planning stack, and back to the controls stack, you're likely looking at >500ms. Waymos have the advantage of consistency though (they never text and drive).

> but I can confidently say [...] you're likely looking at >500ms

That sounds outrageous if true. Very strange to acknowledge you don't actually have any specific knowledge about this thing before doing a grand claim, not just "confidently", but also label it as such.

They've been publishing some stuff around latency (https://waymo.com/search?q=latency) but I'm not finding any concrete numbers, but I'd be very surprised if it was higher than the reaction time for a human, which seems to be around 400-600ms typically.

Re: Waymo robotaxis are now giving rides on freeways in LA, SF and Phoenix

#173

Post by crazygringo »

GloamingNiblets wrote: post #118
xnx wrote: post #39

Earlier quoted context omitted.

Highways are on average a much more structured and consistent environment, but every single weird thing (pedestrians, animals, debris, flooding) that occurs on streets also happens on highways. When you're doing as many trips and miles as Waymo, once-in-a-lifetime exceptions happen every day. On highways the kinetic energy is much greater (Waymo's reaction time is superhuman, but the car can't brake any harder.) and…

I don't have any specific knowledge about Waymo's stack, but I can confidently say Waymo's reaction time is likely poorer than an attentive human. By the time sensor data makes it through the perception stack, prediction/planning stack, and back to the controls stack, you're likely looking at >500ms. Waymos have the advantage of consistency though (they never text and drive).

What gives you that confidence?

You're quite wrong. It tends to be more like 100–200 ms, which is generally significantly faster than a human's reaction.

People have lots of fears about self-driving cars, but their reaction time shouldn't be on the list.

Re: Waymo robotaxis are now giving rides on freeways in LA, SF and Phoenix

#174

Post by overfeed »

GloamingNiblets wrote: post #118
xnx wrote: post #39

Earlier quoted context omitted.

Highways are on average a much more structured and consistent environment, but every single weird thing (pedestrians, animals, debris, flooding) that occurs on streets also happens on highways. When you're doing as many trips and miles as Waymo, once-in-a-lifetime exceptions happen every day. On highways the kinetic energy is much greater (Waymo's reaction time is superhuman, but the car can't brake any harder.) and…

I don't have any specific knowledge about Waymo's stack, but I can confidently say Waymo's reaction time is likely poorer than an attentive human. By the time sensor data makes it through the perception stack, prediction/planning stack, and back to the controls stack, you're likely looking at >500ms. Waymos have the advantage of consistency though (they never text and drive).

Waymo "sees" further - including behind cars - and has persistent 360-degree awareness, wheres humans have to settle for time-division of the fovea and are limited to line-of-sight from driver's seat. Humans only have an advantage if the event is visible from the cabin, and they were already looking at it (i.e. it's in front of them) for every other scenario, Waymo has better perception + reaction times. "They just came out of nowhere" happens less for Waymo vehicles with their current sensor suite.

Re: Waymo robotaxis are now giving rides on freeways in LA, SF and Phoenix

#175

Post by threatofrain »

izzydata wrote: post #25
brokencode wrote: post #23

Earlier quoted context omitted.

Waymo continues to improve every year, but dumb drivers never will.

It is probably possible to get drivers to improve if the incentives were there or if they had no choice due to external factors. I bet it would be cheaper than money spent on self driving tech too. Or public transit on a track.

But the incentives are there. The knowledge is even there. What's left is the sum of all values.

Re: Waymo robotaxis are now giving rides on freeways in LA, SF and Phoenix

#176

Post by crazygringo »

QuercusMax wrote: post #171
crazygringo wrote: post #144

Earlier quoted context omitted.

You do realize that public transportation doesn't provide luggage carts? That you can't take those out of the airport? If you're traveling with a family or group, it really is often going to be much easier to take an XL Uber than deal with turnstiles and transfers and stairs and everything.

So what you're saying is if you're not in a big group or traveling with family, you absolutely SHOULD take public transportation.

...no? Maybe re-read the first half.

I've come from abroad with two large checked bags, a carry-on, and a backpack. You think I'm trying to take all that through the subway?

Obviously, yeah if you're traveling solo with a carry-on, most people take public transportation.

Or not, if it's 1 am and you don't want to be waiting 20 minutes for each connection.

Also, if you're a tourist new to the city after a long flight, the last thing you want to do is figure out the massively complicated transit system. Just having someone take you straight to your hotel where you can shower and sleep and deal with jet lag can be an important priority.

Re: Waymo robotaxis are now giving rides on freeways in LA, SF and Phoenix

#178

Post by toast0 »

circuit10 wrote: post #132
toast0 wrote: post #106

Earlier quoted context omitted.

The slow lane and passing lane dichotomy makes sense in a rural highway with two lanes in your direction. It makes less sense in an urban environment with 5 or more lanes in your direction. Vehicles will be traveling at varying speeds in all lanes, ideally with a monotonic gradient, but it just doesn't happen, and it's unlikely to. In California, large trucks generally have a lower speed limit (however many trucks ar…

Isn’t the situation you’re describing where speeds vary due to queues going to be in heavy traffic where cars aren’t getting close to the speed limit anyway? (also it’s kind of amazing that 5 parallel lanes is considered normal in the US… I think the most I’ve ever personally seen in the UK is 4 and that’s only on very major routes, and we don’t have any exits on the wrong side of the motorway)

> Isn’t the situation you’re describing where speeds vary due to queues going to be in heavy traffic where cars aren’t getting close to the speed limit anyway?

Not necessarily. I've seen things like the left two lanes at free flow (speed limit or above) and the right two lanes at full congestion (~ 10 mph), and the middle lane(s) somewhere in between. But then you also have sometimes where the left lane is only doing 60 for some reason, but the next two lanes are at or above the speed limits. It's a complex system.

Wrong side exits for interchanges between highways are common, depending on site details and relative flows. When there's congestion on a left exit, you then get situations where the right lanes are flowing faster than the left lanes (sometimes much faster). I don't think interchanges as left exits are necessarily awful.

Wrong side exits to surface streets have been discouraged for new construction for quite some time, but there's a fair number of "legacy exits" in some areas. They're not so bad when there's only two lanes in your direction; but when there's been highway expansion, it can get pretty hard to use. And inevitably rebuilding to current standards would causes a lot of confusion and delay, it's postponed. My exemplar of the worst left exits, the Milwaukee Zoo Interchange, was rebuilt in 2012-2022 and I can't find pictures of what it was before, but you had a sizable interchange with right and left exits to other highways, combined with several surface street exits and entrances on both sides, and I think two through lanes. It was a mess.

Re: Waymo robotaxis are now giving rides on freeways in LA, SF and Phoenix

#179

Post by treis »

ericmcer wrote: post #60
prismatix wrote: post #42

Earlier quoted context omitted.

I had a similar experience. A few months ago, I was in the city for a weekend and took Waymo for most of my rides. The one time I chose to use Lyft/Uber, the driver floored it before we even had a chance to shut the door or get buckled! The rest of the time we took Waymo. I rarely use ride-sharing but other experiences include having been in a FSD Tesla Uber where the driver wasn't paying attention to the road the en…

It must be interesting being an Uber driver right now and literally watching the robots that will replace you driving around with you. This has been a 15+ year process and will probably take a few more years. I don't feel too bad if they didn't manage to pivot in that time period.

It's interesting that we're on the cusp of a major change in our world and no one is really talking about it. Self driving cars will have a profound impact on society. Everything from real estate to logistics will be impacted.

Re: Waymo robotaxis are now giving rides on freeways in LA, SF and Phoenix

#180

Post by bcrosby95 »

Night_Thastus wrote: post #114
LZ_Khan wrote: post #83

Earlier quoted context omitted.

Waymo is overly conservative last time I checked. Driving the speed limit basically means getting to your destination twice as slow.

"Twice as slow" is not even slightly accurate. If you're driving 45 in a 40, that may sound like 12% faster, but once you add traffic, lights, stop signs, turns, etc - you'll find that the 12% all but evaporates. Even if you're really pushing it and going 15 over, at most speeds and for most typical commutes, it saves very little. Most of the time speeding ends up saving on the order of seconds on ~30 minutes or shor…

Yeah, I chuckle a bit when the person who blew by me on the freeway at 80mph is just 2 cars ahead of me at the offramp stop light.
Post reply on HN