261–270 of 340 posts
Earlier quoted context omitted.
But it doesn't have to be perfect, just has better than human drivers. That doesn't seem too difficult.
I think you’re underestimating the ability of even bad drivers to accurately process and react to new information while driving.
Earlier quoted context omitted.
Or most people. If it is actually blizzard conditions, one should have a very serious reason to be on the road. If not, stay at home instead of driving. Snow days are called for schools. Maybe work in general also?
I think this is very regional. I have never had a snow day in my entire life because we get snow several months per year. I think the "snow day" phenomenon happens in cities where snow is rare enough that there is no infrastructure in place to take care of it (having that would be more expensive than just accepting everything stops a couple of days per year) AND not every car has winter tyres. After 60cm snow on one…
> The cluster of sensors, bolted underneath a chassis like a skid plate, can scan 10 feet beneath the ground to reveal soil, water, roots, and rocks. Once WaveSense has scanned an entire roadway, it creates a map of the subsurface strata that can determine the location of a vehicle within a few centimeters. nononono! Even assuming you can create sufficient map data as soon as there is any kind of roadworks - or even…
If I then drive the road and there's been some changes (traffic cones, lane closures, heavier traffic than normal, dark so I need to watch out for animals more closely....) I adjust my speed for the circumstances
I don't see why gathering surface information would be any different. Gather info, compare to previous fleet-gathered info, adjust driving to compensate. Seems reasonable to me (as ONE source of info for decision-making). And as fleet size increases, info gets gathered more quickly - look at how quickly google maps can inform you of traffic slowdowns in busy urban areas.
https://thelastdriverlicenseholder.com/2018/09/14/waymo-plan...
> The cluster of sensors, bolted underneath a chassis like a skid plate, can scan 10 feet beneath the ground to reveal soil, water, roots, and rocks. Once WaveSense has scanned an entire roadway, it creates a map of the subsurface strata that can determine the location of a vehicle within a few centimeters. nononono! Even assuming you can create sufficient map data as soon as there is any kind of roadworks - or even…
Maybe they don't really care about the product. Maybe the execs only care about making money, so they'll find funding for anything - whether it will pan out or not.
Self-driving cars are hot and for now there's a lot of money available. I think things will cool down when the hard part starts - like when they really do have to figure out how to make them drive in less than ideal conditions.
> Waymo, widely seen as leading the self-driving vanguard, says it has made progress teaching its software to better filter out “noise” from precipitation. The last Waymo leak claims that it is more than just 'progress', but that 'rain is solved', incidentally: https://thelastdriverlicenseholder.com/2018/09/14/waymo-plan...
From that article: > Also snow seems to be solvable, as there will probably similar patterns that the sensors get in their signals. Real snow is not just a software problem. Fancy rear facing sensors near bumper? I hope they function through a couple inches of frozen muddy spray. Front windshield? Sometimes needs scraping. Lidar on roof? Does it work through the big heap of snow on it?
Though I'm sure SV's real solution to this is to have perfect weather (ie. "can't reproduce; closing bug").
Honestly, it seems like a more workable solution would be to improve the roadways with built-in beacons to indicate where a road is, and where it isn't. The cars would work only on the improved infrastructure, but they would work. I suppose there is a danger of nefarious actors spoofing beacons to make you drive off a bridge, but it seems far-fetched.
Earlier quoted context omitted.
From that article: > Also snow seems to be solvable, as there will probably similar patterns that the sensors get in their signals. Real snow is not just a software problem. Fancy rear facing sensors near bumper? I hope they function through a couple inches of frozen muddy spray. Front windshield? Sometimes needs scraping. Lidar on roof? Does it work through the big heap of snow on it?
I have a hunch that as cars get more sophisticated, they also need to have more sophisticated treatment. The reason I leave my car out to have a foot of snow on it is because it works anyway. If the car wouldn't actually work without the windscreen clear and sensors ice-free, I would either use a garage every night or have a less sophisticated car. And I suspect that once autonomous vehicles get good enough, people w…
But I guess when it's your product; you change your mind.
*This is not an attack to alkonaut.
Earlier quoted context omitted.
I’m not an expert in self driving car engineering. I have some experience with ML but not in a significant professional way. What I have is a decade of professional experience building all kinds of software and a skeptical eye. You have a problem that is unconstrained, with infinite variables, where even a simple mistake can have catastrophic outcomes. Society itself may object to self driving cars for a ton of reaso…
But it doesn't have to be perfect, just has better than human drivers. That doesn't seem too difficult.
It may not even be possible to solve without something radical like banning human drivers or inserting electronic nodes directly into our roads and infrastructure to aid autonomous vehicles. The existence of human drivers might make the problem simply impossible to solve in a way acceptable to society.