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

Cruise is opening driverless cars to the public in San Francisco

getcruise.com

Post reply on HN
Print view View original

301–310 of 652 posts

Re: Cruise is opening driverless cars to the public in San Francisco

#301

Post by skulk »

desertraven wrote: post #270
dang wrote: post #182

Earlier quoted context omitted.

HN's criterion is whether a post is intellectually interesting, or more precisely whether it can support an intellectually interesting discussion. What's nice about that is you can decide it by looking at the article itself, and the thread—you don't need to know nebulous things like the intentions behind the post. I'd say the current post clears the bar fairly easily. Here are a couple of past explanations about this…

Thanks for the response dang. Someone below has brought to my attention that my comment doesn’t sit within within the guidelines - might it be best for me to edit it with something relevant to the article? Out of curiosity, and regardless of this case, how do you deal with artificial manipulation of sentiment on HN? Nudging the views of one of the most active developer communities in the world has value if you were a…

I've seen dang post this link when something like this question is asked: https://hn.algolia.com/?sort=byDate&dateRange=all&type=comme...

Re: Cruise is opening driverless cars to the public in San Francisco

#302

Post by xp84 »

ghaff wrote: post #178
yupper32 wrote: post #152

Earlier quoted context omitted.

> I think Karpathy will be fired this year if his team can't achieve at least L4. Ah so Karpathy will be fired this year. Because they're not reaching L4. FSD isn't even L3 yet.

I do expect at least some companies will hit L4 within the decade(?) but it's going to be under limited conditions that won't include urban driving. Which could actually be a very useful capability but isn't the "don't own a car" future that some really are focused on. ------ Level 4 _ High Automation System capability: The car can operate without human input or oversight but only under select conditions defined by f…

> "driver might manage all driving duties on surface streets then become a passenger as the car enters a highway."

This is the kind of setup I can't wrap my head around. The car might "require" you to take over when you exit the highway, but it can't exactly "make" you. If you fall asleep on the freeway and the car isn't willing/able to drive at the end of your journey, or in edge cases if you were to pass out, etc. what does it do when it gets to your designated exit, or to the final exit of a designated highway? Are there going to be a bunch of cars all stacked up with flashers on the shoulder by every off-ramp waiting for their people to wake up / quit playing on their phones and engage manual mode?

Re: Cruise is opening driverless cars to the public in San Francisco

#303

Post by cblconfederate »

dont__panic wrote: post #201
kfarr wrote: post #174

Earlier quoted context omitted.

Can confirm from personal experience in crosswalks with self driving cars: cruise is the most timid (read safest!) of the self driving cars being tested in SF IMHO. Cruise will proactively alter trajectory (such as deceleration) for pedestrians and cyclists at a noticeably earlier threshold than Waymo. This is much more pleasant for everyone surrounding the vehicle as it clearly expresses that you have been recognize…

Urban bicyclist here. I don't life in SF, but I'm really curious how current autonomous vehicles behave around cars. If you're biking down a one-way street with little room, do most autonomous vehicles just wait behind you? Do they try to pass? What kind of follow distance would they give a bicyclist who "dominates" the lane because it's too narrow to let a car pass safely?

are there narrow streets in america?

Re: Cruise is opening driverless cars to the public in San Francisco

#304

Post by KerrAvon »

LegitShady wrote: post #205
walrus01 wrote: post #8

Based on this image: https://images.ctfassets.net/95kuvdv8zn1v/6h1C7lPC79OLOlddEE... They and their VC backers are clearly betting on the concept that radars + lidar + imaging will be the ultimate successful solution in full self driving cars, as a completely opposite design and engineering philosophy from Tesla attempting to do "full self driving" with camera sensors and categorical rejection of lidar. It is interes…

In Lex fridmans interview with George Hotz, hots talks about why he thinks radar AI is a non starter and predicted that even though Tesla was still adamant about using their radar, they would eventually realize they only needed cameras. Hotz is the founder of comma.ai which is doing open source (I think?) Company.

What were his reasons? Searching the web reveals lots of machismo and assorted hero worship, but no actual solid technical arguments. Nobody in the field seems to think a vision-only solution is practical, other than Tesla, who are also not providing solid technical arguments that I can find.

This IEEE item seems to summarize the situation well.

https://spectrum.ieee.org/tesla-places-big-bet-vision-only-s...

Re: Cruise is opening driverless cars to the public in San Francisco

#306

Post by ironman1478 »

julienb_sea wrote: post #253
JaimeThompson wrote: post #237

Earlier quoted context omitted.

How does one take into account lack of maintenance by the end user in a strict 100% liability situation?

This problem should be solvable in software. The car can simply refuse to operate in a situation where maintenance is required.

How do you know maintenance is required in a completely automated fashion?

Re: Cruise is opening driverless cars to the public in San Francisco

#307

Post by mensetmanusman »

kvogt wrote: post #93
walrus01 wrote: post #8

Based on this image: https://images.ctfassets.net/95kuvdv8zn1v/6h1C7lPC79OLOlddEE... They and their VC backers are clearly betting on the concept that radars + lidar + imaging will be the ultimate successful solution in full self driving cars, as a completely opposite design and engineering philosophy from Tesla attempting to do "full self driving" with camera sensors and categorical rejection of lidar. It is interes…

Cruise CEO here. Our strategy has been to solve the challenges needed to operate driverless robotaxis on a well-equipped vehicle, then aggressively drive the cost down. Many OEMs are doing this in reverse order. They're trying to squeeze orders of magnitude of performance gains out of really low-cost hardware. Today it's unclear what strategy will win. In a few years our next generation of low-cost compute and sensin…

I’m assuming well equipped means more capable data processing and bandwidth needs, is this the case?

If so, do you have a sense for how many orders of magnitude more bits of data your sensors are acquiring versus Tesla?

Re: Cruise is opening driverless cars to the public in San Francisco

#308

Post by gpas »

more_corn wrote: post #94
modzu wrote: post #46

Earlier quoted context omitted.

nobody owns a car because its cheaper than other forms of transit. and if you want to be cheauferred around by an ai instead of taking a bus, you will pay for it.

People own cars for convenience. In the US public transit is impossible. A self driving service can be as convenient or even more convenient compared to owning a car. (No registration, oil change, insurance, fueling, parking, maintenance chores) I’m a car guy and I see the appeal.

> In the US public transit is impossible

No sarcasm. Why it's impossible to have public transit like every other country in the world but it's possible to pour tons of money on driverless cars development?

Re: Cruise is opening driverless cars to the public in San Francisco

#309

Post by mensetmanusman »

walrus01 wrote: post #134
user3939382 wrote: post #127

Earlier quoted context omitted.

My conclusion from years of self-driving, LIDAR, etc. research is that managing medium to heavy precipitation reliably might be impossible. Visual algorithms run into the same problem as human brains, and the size of e.g. rain drops interferes with the frequencies employed by radio techniques. Is anyone aware of any strategies that give us hope in solving this problem?

I know next to nothing about lidar engineering but 60GHz band radars can still function out to several hundred meters in rain. It is significantly attenuated as the rain rate (in mm/hour) increases, but it takes a lot of rain to make it completely useless.

This depends on how powerful your antenna are, $200 wigig transmitters will struggle with much range over those distances.

Re: Cruise is opening driverless cars to the public in San Francisco

#310

Post by postmeta »

ddlutz wrote: post #92
borski wrote: post #22

Earlier quoted context omitted.

As you’ll note in the comments on that thread though, FSD has a lot more issues than just that; particularly with stationary objects and at night.

I don't have FSD enabled on my Model 3, but I have the FSD visualization preview. I'd be terrified of FSD at night. During the day I don't see it have any issues registering cars and other obstacles, but during night it barely detects anything.

Seems fairly good at night in 10.9 https://www.youtube.com/watch?v=01QowBvtraE
Post reply on HN