We take into account long-term trends in weather and traffic conditions like road works, school holidays, and recurring traffic patterns.
The drivers' sat navs also (IIRC) have live traffic, which can send them down different _roads_ in response to things like accidents causing traffic jams.
Of course, there are limits to our ability to respond quickly to changes in traffic conditions for simple logistical reasons - many drivers' vans are loaded once at the start of an 8-hour shift, and we can't predict traffic accidents 8 hours before they happen!
Certain other competing concerns are balanced with a 'cost function' which has been tuned empirically.
In worst cases the road turns from a 2 lane road to a 1.5-1.8 lane road when there's enough snow on the banks. Multi-lane motorways turn from 4 lanes to 2-8-3.5 lanes. Humans have trouble navigating that, dunno how any FSD system would manage it in our lifetime.
When the first snowstorm hits it never ceases to surprise me how the dynamics of the road change - not just the friction, but the number of lanes and where they go all change as people give their best guess, which over the next 2000 cards becomes codified. If you have self-driving cars following the old lanes you're going to have accidents.
because if the terrain is dangerous to drive on (with all that snow, probably yes), the driver will likely judge much better than anything you could do remotely with current technology on whether to risk moving ahead or not
Sure, it was able to handle this trip once during ideal conditions. What happens when road conditions become tricky? Will the AI be able to navigate a lane closure that forces it to drive on the shoulder due to an accident? How about adverse weather conditions?
People are bad drivers. Every winter at the first snowfall there are tonnes of accidents because folks forgot to adjust following distances.
The promise of an AI driver is that there will never be a second accident of the same type. The only question is how fast the learning rate can ramp up.
I think you are missing the most important part here. These cars are always online and share data between them. They have a detailed map of every street and every road bump and every road pole/sign that can be used for navigation. Even if everything is in snow and the camera/lidar is frozen and can't see anything, these cars know exactly where they are and where the road is from predictive navigation based on speed, direction, road shape/bumps from previous data that was collected from 1000s of passes before that on that very same road. At first AI cars will probably avoid certain areas that have not been mapped. Each car will signal any unexpected road blocks, data will be sent realtime to a human operator who will script a walkthrough in seconds. Such as "ok, you are legitimately stuck in traffic right now, just wait" or "ok, there is a crashed car ahead of you so the right-turning lane is closed, move into the left lane and you can turn right from here as an exception". There will be humans like ATC in all cases.
Police and emergency services will just coordinate with the "ATC" to pre-script routes differently depending on the situation.
In theory, as storage costs approach 0, computers get faster and and vision becomes more sophisticated, road conditions shouldn't matter too much.
These cars are going to be scanning constantly in nice weather, it shouldn't be a stretch to then figure out relative position with GPS and then use the distance to 'known' trees / signs / landmarks from previous trips to determine lane position.
I'm sure there are barren areas where this would be tough (I've driven I-80 through snowy Nebraska about a dozen times en route to ski vacations in Colorado) but "stay between the snow banks" should be a decent start for autonomous driving.
Furthermore, you don't just blindly follow marked lanes (even if you knew exactly where they are) in a snowstorm. You may follow tracks left by other vehicles, deal with the fact that two lanes in cities often effectively constrict to one, etc.
No, lots of people don't do a great job whether it's because they're driving too fast, not leaving enough room, or slamming on the brakes. But there's a huge amount of judgment and situational awareness needed in bad weather--especially snow.
Certainly, autonomous systems can (and almost certainly will) be restricted to certain roads/types of roads in certain weather conditions and still be useful driving aids. But as soon as you restrict systems to only working some of the time, you've effectively closed off any use that doesn't allow for having a competent driver behind the wheel at all times.
Those all sound like more or less the same problem: traffic.
Why don't some of the teams impress me and try driving somewhere with black ice, strong crosswinds and blowing snow. If their systems can't drive in negative environmental conditions, they will be largely worthless in many locales.
Bad weather and unexpected obstacles like pedestrians are actually trivial to handle. Remember that an autopilot's "visual" perception isn't limited to the visible-light range like ours is.
Poorly-maintained roads are the problem that would give me nightmares if I worked on these. Lane markers that might have been perfectly usable when the database was compiled may be too worn out or obscured by snow, leaves, or who-knows-what else to be usable later. How can you design a system to fail safely when every input source is independently fallible? And how can we redesign the auto insurance industry to make it possible to try?
A good many people stay off the road anyhow during poor weather, and those who do go out usually stay on familiar routes, such as to work or their favorite grocery store.
If self-driving cars/buses stick to a subset of streets and don't go out in big storms, they can still be widely useful. Set up (require) a universal network/database of road conditions on the main streets that all self-driving vehicles can tap into. If a problem arises, it then only directly affects the first bot-vehicle that encounters it instead of all of them that use the road. It's internet-like packet switching.
Thus, bots may get "confused" easier than humans, but they can also take advantage of automation to work around confusing areas. The upsides of automation thus counter the down-sides.
The biggest cost of taxis and buses is the driver. If you remove that, then "hitching a ride" is a lot more affordable to those who can't or don't drive.
24/7/365 seems overly optimistic, weather alone will most likely cut out many of those trips. Depending on the type of collision avoidance technology used may further limit night time operation.
It depends on the climate where you live though, right? Where I am there's plenty of congestion. There's also plenty of rain, snow, slush, and road construction. The snow removal and construction really take a toll on the lane markings, so detectable lane markings isn't a guarantee either.
Weather is probably one of the easier problems to tackle. Sure, performance will be worse in a snowstorm, but that's true of humans too. Waymo has already showed they can filter out snowflakes. Maybe it wouldn't work in white-out conditions, but in that case, again, humans also can't really drive.
The more complex things that can happen in urban areas though, yeah that's hard. All kinds of weird shit can happen that takes social understanding to know how to deal with. Right now it looks like for those situations Waymo is relying on remote "coaches" that tell the cars what to do at a high level (guidance, but not directly control).
People also do really poorly in edge cases. Don't forget self driving cars are going to quickly have billions of road miles worth of data.
There are plenty of videos of autonomous cars is highly chaotic road conditions, but that's all old hat. Weather is an issue, but weather is also forecastable. Even if you only get rid of truckers in areas stay above freezing that's still a massive change.
The drivers' sat navs also (IIRC) have live traffic, which can send them down different _roads_ in response to things like accidents causing traffic jams.
Of course, there are limits to our ability to respond quickly to changes in traffic conditions for simple logistical reasons - many drivers' vans are loaded once at the start of an 8-hour shift, and we can't predict traffic accidents 8 hours before they happen!
Certain other competing concerns are balanced with a 'cost function' which has been tuned empirically.
reply