The biggest problem human drivers have in winter weather is simply driving too fast. Self-driving cars won't get impatient and will presumably never exceed safe speeds for given conditions.
Having lived nearly my whole life in Michigan, I think this grossly oversimplifies the problem. I'm sure my Canadian friends will agree. This assumes there's some clear algorithm for determining a "safe" speed. There's not.
Even in highway driving you can lose traction in an instant if you hit a patch of black ice. Autonomous vehicles will need to be able to recover from a complete loss of traction safely. This isn't trivial - in fact it's probably the most complicated bit of driving I tend to do. Once you are sliding and your steering wheel becomes more of a suggestion than a command, the entire act of driving becomes a process of trying to coax the car off the road using a combination of steering, brakes, and even occasionally gas. I think it's possible for a computer to do this - but you can't avoid all slides just by driving slowly.
Then there's the plethora of other winter fun you run into with a vehicle: getting stuck (happens all the time on city streets) and all the techniques to get unstuck, going too slow and losing your momentum (and thus traction), having every indication you have traction and then discovering you actually don't (it's very easy to be driving at a "safe" speed and still slide through an intersection), white out conditions where you are guessing where the lane is... etc...
To be clear, I believe most of these conditions could eventually be handled by computers. I also believe a lot of people drive too fast in/on snow. However, winter driving is in no way simple. It's a problem domain unto itself, and one I've seen relatively little work being done on.
You may be correct that relatively little work is being done in this area, however I think you overstate the difficulty.
Winter driving is really no different from any other kind of driving in which the driver exceeds the limits of the vehicle's available traction. The methods of recovery are mostly well-known; the problem is more often the driver's inability to implement them in a timely manner.
Constant input from wheel speed and accelerometer sensor arrays, coupled with the vehicle's ability to individually brake/slow wheels (which also gives the vehicle the ability to accelerate individual wheels independently!) means that it could be a far easier 'problem' for self-driving cars to solve than it is for humans.
Again, if they're working on it :) But there's already been decades of work put into ABS, traction/stability control, etc.
> Winter driving is really no different from any other kind of driving in which the driver exceeds the limits of the vehicle's available traction.
I actually agree with this statement. The problem is that, in good conditions, low traction events are rare, and often caused by catastrophic conditions. In winter driving it's practically the norm, once you leave well traveled roadways.
I think AI could be trained to drive a car that only occasionally has full traction, and probably more effectively than a person given enough time. But again - it's like you said - someone needs to be addressing this case directly.
I use to live in an area that got heavy snow and had an all wheel drive vehicle (a WRX). I have lost control in the snow, even driving slowly in 2nd gear, under 30kph. For a human at least, your reactions need to be pretty automatic: point the wheels where you want to go and .. and this only applies to AWD/4x4: don't break. You don't really want to accelerate much, but you don't want to lose power to the wheels. Keep calm and the car will straighten.
It comes down to balancing, and we know we can build machines that can balance. Segways, bipedal robots, etc. So we have some of the tech and algorithms to do this in other applications, but applying it to autonomous vehicles will be its own beast.
I think such acts of control are one of the things where computers are naturally better than humans. We have a lot of experience in automatically controlling dynamic systems. Winter conditions are more of a problem because they might interfere with the sensors (e.g. radars and snow don't play together very well).
On the other hand a computer-controlled vehicle, possibly electric with 4-wheel drive, would have millisecond control over all those inputs (steering/brakes/acceleration)
I don't disagree. But without exception every winter slide-off I've witnessed first hand has been caused by excessive speed. You're driving along on a snow-covered interstate highway, someone in a BMW or 4x4 flies past you because "I have all wheel drive" starts to fishtail, overcorrects, spins out, and ends up backwards and stuck on the median.
Respectfully, I think this amounts to bias more than anything. It's a lot easier to believe that the slide-offs are caused by bad driving - and most probably are. But some are unavoidable.
I have to agree as well. I've only had two winter driving accidents, both of them just me and one of them was unavoidable: I was travelling at very low speed down a plowed street and found a long streak of ice. I've been in plenty of winter skids and am decent and correcting them but I had 0 traction and essentially skated at 5mph into a telephone pole (which seemed safer than the cross street I was drifting toward).
I'm not sure how a self-driving car would have fixed that. I certainly believe one could but it would require a ton of learning beforehand and conditions vary widely in storms. I suppose with all-wheel drive and some selective application of the wheels in reverse it might have stopped the car before any damage was done, but how to handle situations where the AI can't stop the car before an incident and has to minimize the damage? That feels like a lawsuit waiting to happen in the US.
The biggest problem computer drivers have in winter weather is not being able to see lane markers. Humans are (for now) still better at figuring out where the lane is. Presumably this problem can be solved with improvements in maps, cameras, and image recognition algorithms.
Humans do an unbelievably bad job at this, too, like all other tasks behind the wheel. Humans essentially just follow the tracks of the last car, creating ad hoc lanes. Computers can do this just as well.
On the other hand, humans also have the common sense not to (e.g.) follow the tracks of a car that has spun off the road.
I'd expect logic at that level might be more difficult to train for than the relatively low-level visual task of identifying and following tracks. But I guess existing self-driving systems already need to work at that level to predict the actions of other cars and pedestrians, so presumably the current data-driven training techniques would also handle it OK? (Assuming a lack of pranksters with shovels...)
What happen when you are the first on the road with no tracks to follow from previous cars and suddenly it turns into a blizzard/zero visibility? I am guessing the car can pull over and turn on emergency flasher...I don't know but to me I believe a Human will always have to take over at some point because you never know what mother nature will throw at you, keep in mind I am talking about a future where we aim for 100% autonomous car.
Having lived through many such blizzards, there are two things that humans do:
The smart ones pull over and turn on the emergency flasher. Then they check to make sure they have lots of gas, blankets and water, just as they prepared.
The dumb ones slow down to 45 mph and stare into the white blankness looking for clues about curves.
Exactly! Every question about how a computer-driven car will handle exceptional situations encountered by humans shares the same answer: the computer won't have got itself into the situation in the first place. Humans might drive a car into a whiteout blizzard, but that only serves to demonstrate the urgency of cutting humans out of the loop.
Just to provide a counter point, in my experience, the biggest problem I face in winter weather is other drivers. I know when I hit a patch of black ice and have difficulty stopping that the oversized van behind me is going to have more difficulty stopping, and I have the instinct to quickly turn instead of waiting on the red light. I also know that cars have difficulty stopping on a steep hill and I may wait before going through an intersection. Both of these experiences have happened in the past year for me.
This may seem like a straw-man argument, I don't intend it to be. I think self-driving cars will be on the whole better drivers, but these are also situations that I see as being extremely difficult for a computer to identify to the level a human driver is capable of.
Agreed. I don't think the problem in winter driving is the speed. It's anticipating what the hazards are and how to avoid them.
You - and the other drivers on the road - have less control at all speeds and are always much closer to the limit of traction. Driving on winter roads is a lot like racing a car on a track with other drivers - everyone is near the limit of traction and a hazard can present itself very quickly. Having the right reaction at the right time helps, but planning ahead is more important. Daily driving in summer months is benign in comparison.
> Driving on winter roads is a lot like racing a car on a track with other drivers - everyone is near the limit of traction and a hazard can present itself very quickly