Live data from Hacker News

Waymo One: The next step on our self-driving journey

medium.com

171–175 of 175 posts

Re: Waymo One: The next step on our self-driving journey

#171

I hope they roll this out in Miami soon. Miami has some of the laxest AV regulations in the country. Also would happily pay to not drive in this mess every day.

I could be wrong, but a city with daily monsoon-like downpours part of the year and famously aggressive human drivers is probably not going to be an early adopter for AV tech.

Ford and Argo have a huge facility here already. Their theory if they can make it work in Miami with our terrible drivers, they can make it work anywhere. You can already get postmates and dominos delivered by Ford AV.

Re: Waymo One: The next step on our self-driving journey

#172
post #75

Earlier quoted context omitted.

About the speed of a sprinting human, unsurprisingly.

The average human cannot sprint that fast. I'd peg the average person sprinting closer to half that (obviously there's a lot of variance, but I think only the top 1% of athletes could run 30 kph even for 5 seconds). For a frame of reference, try to run at the top speed of a treadmill (most max out at 15 mph, and most people can't go that fast - at least not at the gym).

Average human (not a child or pregnant) before cities (ie., when human morphology evolved)? Quite likely I would guess.

Re: Waymo One: The next step on our self-driving journey

#173
post #133

Earlier quoted context omitted.

I think so much of it is just a scale issue. I grew up in a mid-sized suburb in the Northwest just a couple decades ago. Most road were only 2, or maximum 4 lanes. The idea of driving around without your headlights on in the dark would be unfathomable. And if you did, you'd get honked at, flashed, and presumably at some point within 5 or 10 minutes, a police officer would see you and stop you. That area's gotten bigg…

IIRC the #1 reason people get pulled over for drunk driving is because they don't have their headlights on, the police for sure are on the lookout for that. In Arizona you pretty much have to make the cops do their job unless they think they can get you for a DUI then they'll pull you over for the slightest infraction. The things I've seen people do when there's a cop right next to me at an intersection and not get s…

Yeah, the problem is, in the winter, no headlights during the early evening hours, no big deal. 3am, they're out for blood if you don't have your lights on, for sure.

Re: Waymo One: The next step on our self-driving journey

#174

I know this is a heated debate, but it's interesting to see the divergent approaches that are being taken to achieve self driving. In one corner, it's lidar-based, equipping vehicles produced by other companies, organically and incrementally growing the navigation technology. In the other, it's video-based with now 100s of thousands of vehicles feeding data to a massive neural net. Each has very well thought-out argu…

While I own a TM3 I have little faith in their full self driving solution and did not opt for that. I did take the enhanced auto pilot and recent additions show how much more work it will take. An example would be that it now shows different vehicle types and even pedestrians near you yet when all surround objects are obviously not moving it still has them moving on the display. It still has issues with certain bridg…

Perhaps that blowup pilot from Airplane?

Re: Waymo One: The next step on our self-driving journey

#175
post #45

I know this is a heated debate, but it's interesting to see the divergent approaches that are being taken to achieve self driving. In one corner, it's lidar-based, equipping vehicles produced by other companies, organically and incrementally growing the navigation technology. In the other, it's video-based with now 100s of thousands of vehicles feeding data to a massive neural net. Each has very well thought-out argu…

Curious; If you train a neural net to drive a car with X number of samples, and the car does something erratic, how do you determine which data item introduced the erratic behavior and how do you go about untraining that behavior?

It's simple, you retrain the model several times removing one sample at a time (leave-one-out cross-validation), until the erratic behavior disappears. You repeat until there are no more instances of erratic behavior. Sorry couldn't resist the attempt at humor, but also consider it as an argument by contradiction that what you are asking is not possible. It's like asking which lesson caused me to hit a forehand over the tramlines. The answer is the one I didn't have time for.
Post reply on HN