Interesting as something to explore, but I'm curious if a network of self-driving cars can be optimized to recognize and avoid these situations altogether.
We can try. In theory, each self-driving vehicle doesn't have to drive in isolation; they can be networked together and take advantage of each other's sensors and other sensors permanently installed as part of the road infrastructure.
That would increase the chance a particular vehicle could avoid an accident which it couldn't, on its own, anticipate.
And this is the 'hard bit' about self driving cars. If they are too passive and cautious human drivers will exploit them, if they assume the other cars will follow the rules, they will hit them.No amount of LIDAR magic and deep learning can fix that problem yet.
I asked this question before and received no answers, so I'll ask again: Is there a source that details the specific issues that self-driving cars could face, and potential methods of solving them?
Yes, but for self-driving cars, the problem seems more surmountable. We already have cars that can drive in real traffic without intervention a large % of the time. There are plenty of edge cases, but they don't seem insurmountable.
This is the thing that scares me the most. If the self driving cars need to cooperate for maximum efficiency what if there are some cars that don't do it and exploit that?
I've had a few harrowing driving experiences and fortunately, no serious crashes. The difficult driving experiences where just so rare that I would be surprised if a self-driving vehicle would know what to do.
* I once had a car driving way above the speed limit approach me from the rear, it passed me by jumping the curb driving on grass and sidewalk and swerving back onto the street in front of me.
* Another time I was driving back to a rental house in the Aspen area and the snowstorm had gotten bad enough to completely cover and obscure the road on the hillside I was driving on. My wheels went off the road, fortunately on the side away from the drop off and I was driving slowly, but then I couldn't get back on the road without using enough power that I feared I would swerve off the road on down the hill. This required a bit of puzzle solving before I could safely get back on the road.
* I've had bad GPS data that kept me circling my destination without every getting me there.
I just think that such unusual situations are going to be difficult for autonomous cars to understand very soon.
Is this going to be inherent and unavoidable for the machine learning based self driving cars? Perhaps self driving is never going to become a reality, just because of the problems like this (unless/until the road infrastructure supports them explicitly).
Packing more self-driving cars onto roads is an appealing notion, but I don't think it holds up to scrutiny. Even if a computer detects hazards instantly and continuously negotiates with and anticipates the movement of other vehicles, the physics of moving cars remain the same. Safe stopping distances won't be dramatically different. Road surfaces, stray animals, mechanical failures, and any number of other hazards don't care who or what is driving a car.
I'd like to see an architectural overview of a self-driving car. What are the most challenging systems? I can imagine that the most challenging part is the computer-vision system for detecting the road, and the radar system for detecting other vehicles and pedestrians. Given this information, finding a path from A to B without collisions seems not so difficult in comparison.
I find it very curious that the article doesn’t mention self driving vehicles. To me that is an example for a daring risk undertaken mostly by VCs.
The upside is huge. If we can make a robotic system which can safely pilot a vehicle on our existing roads, and make it commercialy viable that will reshape how transportation is done, how cities are built, and how people live.
Is it risky? Oh yeah. Everyone knows that computers are full of faults, sensors are crappy, hardware breaks all the time and every software is a pile of bugs. These are given, and unlikely to just change on their own. Can we, despite all the above engineer a system which provides superhuman level of driving safety, yet it costs less than a driver on the local minimal wage? This is the premise of a self-driving car.
Follow on question: is it possible to get there from here without antagonising the public with accidents? If a restaurant gives food poisoning to folks on the other side of town that won’t affect your restaurant’s business. Any self driving accident happening anywhere on the earth have the potential to ratchet up the scrutiny on every other companies. ( Think of something Hindenburg disaster equivalent.)
I believe the answer is yes we can, it takes carefull engineering and a lot of work but it can be done without needing to invent general artificial inteligence. VCs seems to agree with me because they are positively pumping money into companies in this field. What is that if not risk taking?
It seems like a good intermediate solution to this problem would be for autonomous vehicles to simply know when it's not possible for them to drive safely, and to require manual control in those scenarios.
Im skeptical you can do real autonomous driving without context. In DC, we have roads that flow one direction part of the day and another direction the other part. We've got roads that will be shut down unpredictably when there is a diplomatic event. We've got constant construction, where a two lane road might be reduced to one lane with a human holding a sign or using hand signals to usher cars through on their turns. How does a self-driving car handle that without understanding context?
I'm wondering how this is going to be different than self-driving, where we can get 90% of the way there, but the last 10% is notoriously difficult with not nearly enough edge cases represented in the data
Safe self driving cars without some kind of outside coordination with either the road or other vehicles is an impossibility. It's impossible to do this safely on a mass scale without the road infrastructure made for it.
this is quite an academic exercise since a decade of intensive research hasn't brought us close to working self-driving cars, much less 1x safe self-driving cars, much less 5x safe, nor is there any clear path to resolving this open research problem.
We already have autonomous self driving solution to that here.
It uses all-electric vehicles and they even have a convoy mode where each car follows the lead vehicle closely to maximize the number of passengers and minimize wind resistance.
The guidance system is pretty primitive - it's all done in hardware with steel wheels on steel rails - but it makes it relatively difficult for it to go off-the-rails.
reply