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

Beginning fully autonomous operations with the 6th-generation Waymo driver

waymo.com

Post reply on HN
Print view View original

201–210 of 425 posts

Re: Beginning fully autonomous operations with the 6th-generation Waymo driver

#201

Post by rhubarbtree »

jacquesm wrote: post #70
youarentrightjr wrote: post #12

Earlier quoted context omitted.

According to Elon, "sensor ambiguity" is a danger to the process [1], and therefore only a single type of sensor is allowed. (Conveniently ignores that there can be ambiguity/disagreement between two instances of the same type of sensor) The fact that people still trust him on literally anything boggles my mind. [1] https://x.com/elonmusk/status/1959831831668228450

Sensor fusion allows you to resolve that ambiguity, I wonder if Elon is really as in touch with this as you would expect. No single sensor is perfect, they all have their problematic areas and a good sensor fusion scheme allows you to have your sensors reinforce each other in such a way that each operates as close as possible to their area of strength. No single sensor can ever give you that kind of resilience. Sure,…

Last time I checked I relied entirely on vision to drive autonomously.

Re: Beginning fully autonomous operations with the 6th-generation Waymo driver

#202

Post by vortegne »

rhubarbtree wrote: post #199
qwerpy wrote: post #114

Earlier quoted context omitted.

I hope this prods Tesla to up their game. I love my Teslas but if Waymo’s approach is shown to be truly better then I’d happily switch to a car that used their tech. For now I have no choice but to stick with the self-driving that’s available for personal cars. Hopefully Waymo works on licensing their tech for other manufacturers and expanding their geographical coverage.

Tesla’s approach is smarter than Waymo. Maybe Tesla won’t win, perhaps a Chinese firm, but the winner will follow a vision based system and not a micro-mapping LIDAR system. “Vision is all you need.”

Any evidence for this claim?

Re: Beginning fully autonomous operations with the 6th-generation Waymo driver

#203

Post by hvb2 »

disillusioned wrote: post #197
coffeemug wrote: post #179

Earlier quoted context omitted.

That's fascinating, I didn't know that! What are some example cities/towns where this is common?

Coronado Island, near San Diego, California, for one. Sun City, Arizona, though these are golf communities/mega-master-planned communities. Coronado is a better example of a mixed vehicle environment with golf carts bopping around all the time on the same streets.

Coronado isn't a good example. Or at least not one that scales, that's a VERY affluent neighborhood.

The golf cart isn't a replacement for a car, it's one you have on the side. I would argue that its partially because they're easier to park in a very touristy environment

Re: Beginning fully autonomous operations with the 6th-generation Waymo driver

#204

Post by rhubarbtree »

xnx wrote: post #15
youarentrightjr wrote: post #12

Earlier quoted context omitted.

According to Elon, "sensor ambiguity" is a danger to the process [1], and therefore only a single type of sensor is allowed. (Conveniently ignores that there can be ambiguity/disagreement between two instances of the same type of sensor) The fact that people still trust him on literally anything boggles my mind. [1] https://x.com/elonmusk/status/1959831831668228450

Truly. I don't understand why Tesla fans think camera/lidar fusion is unsolvable but camera/camera fusion is a non-issue.

Unsure if you’re trolling, but you haven’t listened to what Tesla are actually saying.

Having more sensors is complicating the matter, but yes sure you can do that if you want to. But just using vision simplifies training a huge amount. The more you think about it, the stronger this argument is. Synthesising data is a lot easier if you’re dealing with one fairly homogenous input.

But the real point is that cameras are cheap, so you can stick them in many many vehicles and gather vast amounts of data for training. This is why Waymo will lose - either to Tesla or more likely a Chinese car manufacturer.

I do not like Elon because I do not think nazi salutes or racism are cool, but I do think Tesla are correct here. Waymo wins for a while, then it dies.

Re: Beginning fully autonomous operations with the 6th-generation Waymo driver

#205

Post by KellyCriterion »

bonsai_spool wrote: post #164
coffeemug wrote: post #157

Earlier quoted context omitted.

From an execution standpoint you can't work on experimental mobility due to path dependence. How are they going to convince municipal governments to open golf cart lanes? That would require solving two problems (autonomy and overcoming path dependence), and solving just one is hard enough. Once they saturate the market as it is with autonomous driving, then everything will change and opportunities to experiment will…

In the Midwest, golf carts are exactly what people use to get around in small towns. It's not unreasonable that neighborhoods might be closed to large vehicles and use other forms of transit within their boundaries.

Cool! I thought this is more a thing of elderly care centers. I like the drivingfeeling of golf carts, so I would clearly do this as well if it would be allowed on public streets. Though on most streets with all these SUV around, it will feel unsafe for me.

Re: Beginning fully autonomous operations with the 6th-generation Waymo driver

#206

Post by rhubarbtree »

vortegne wrote: post #202
rhubarbtree wrote: post #199

Earlier quoted context omitted.

Tesla’s approach is smarter than Waymo. Maybe Tesla won’t win, perhaps a Chinese firm, but the winner will follow a vision based system and not a micro-mapping LIDAR system. “Vision is all you need.”

Any evidence for this claim?

I don’t think you need evidence to understand it. I’d recommend listening to Andrej Karpathy talk about it.

But I note that human drivers do not rely on LIDAR or radar or a high res map of the road.

Re: Beginning fully autonomous operations with the 6th-generation Waymo driver

#207

Post by zoenolan »

coffeemug wrote: post #179
bonsai_spool wrote: post #164

Earlier quoted context omitted.

In the Midwest, golf carts are exactly what people use to get around in small towns. It's not unreasonable that neighborhoods might be closed to large vehicles and use other forms of transit within their boundaries.

That's fascinating, I didn't know that! What are some example cities/towns where this is common?

Tom Scott visits Peachtree City, Georgia

https://youtu.be/pcVGqtmd2wM

Re: Beginning fully autonomous operations with the 6th-generation Waymo driver

#208

Post by dboreham »

jasonwatkinspdx wrote: post #194
coffeemug wrote: post #179

Earlier quoted context omitted.

That's fascinating, I didn't know that! What are some example cities/towns where this is common?

Grew up in the midwest and still visit... never seen it. Doesn't even pass the sniff test vs the weather.

I've seen it in North Dakota fwiw, summer only obviously. Loads of them in Palm Springs also.

Re: Beginning fully autonomous operations with the 6th-generation Waymo driver

#209

Post by youarentrightjr »

torginus wrote: post #200
_diyar wrote: post #29

Earlier quoted context omitted.

I fully agree with your first point: Musk has shown tremendous ability to manage companies to become unicorns. He's clearly skilled in this domain. However, if you think about this for 2 seconds with even a rudimentary understanding of sensor fusion, more hardware is always better (ofc with diminishing marginal value). But ~10y ago, when Tesla was in a financial pinch, Musk decided to scrap as much hardware as possib…

I'm an EE, I have worked with things like sensor fusion professionally. In short sensor fusion depends on what sensors you have and how you combine them, especially if two sensors' outputs tend to disagree - which one is wrong and to what extent, and how a piece of noise gets reflected in each sensors' outputs, to avoid double counting errors and coming up with unjustifyably confident results. This field is extremely…

> I'm an EE, I have worked with things like sensor fusion professionally. In short sensor fusion depends on what sensors you have and how you combine them, especially if two sensors' outputs tend to disagree - which one is wrong and to what extent, and how a piece of noise gets reflected in each sensors' outputs, to avoid double counting errors and coming up with unjustifyably confident results.

> This field is extremely complex, it's often better to pick a sensor and stick with it rather than trying to figure out how to piece together data from very dissimilar sources.

Whether sensor fusion makes sense is a highly domain specific question. Guidance like "pick a sensor and stick with it" might have been correct for the projects you've worked on, but there's no reason to think this translates well to other domains.

For what it's worth, sensor fusion is extremely common in SLAM type applications.

Re: Beginning fully autonomous operations with the 6th-generation Waymo driver

#210

Post by red75prime »

UltraSane wrote: post #183
testing22321 wrote: post #180

Earlier quoted context omitted.

> and there won't be, for years, if ever. That is a lot of confidence. Do you work in the autonomous vehicle space? What makes you so certain?

Because camera only simply won't be reliable enough with current technology.

Try to find a single ablation study of a sensor suite. Waymo is in a good position to do such a study and the corporation would have benefited from showing that vision-only systems aren't viable (by demonstrating the corporation's good will to maintain public safety and by making it harder for vision-only competitors), but no such study from them.

I guess they understand that computer vision is a fast-moving target and their paper might become obsolete the next day.

Post reply on HN