Since when the belief that "a silver bullet exists for computer science research" becomes a thing?
Unreasonable Ineffectiveness of Machine Learning in Computer Systems Research
51–60 of 105 posts
Re: Unreasonable Ineffectiveness of Machine Learning in Computer Systems Research
#52Earlier quoted context omitted.
> none of us in the automobile or IT industries are close to achieving true Level 5 autonomy - Gill Pratt, Toyota Research Institute http://spectrum.ieee.org/cars-that-think/transportation/self... > It will be 25 years before self-driving cars take off in America - Bill Gurley, Uber investor http://www.cnbc.com/2017/04/06/bill-gurley-uber-investor-sel...
Is that industry consensus? Also, I think closed-access freeways are very well mapped, is level 5 needed to disrupt the trucking industry, or will level 4 do?
Yeah, my guess is that for trucking, we'll be looking at two drivers per N trucks, moving as a convoy. (Two drivers means one can sleep, and the convoy never needs to take long breaks.) You have to have someone there to take over if a truck goes down half way between Boise and East Nowhere. All the better if they can keep an eye on the monitoring systems for the convoy; taking over driving the lead truck will presumably also be an option for as long as it needs to be.
Re: Unreasonable Ineffectiveness of Machine Learning in Computer Systems Research
#53Earlier quoted context omitted.
One of the lessons of these first steps toward autonomous driving is: if you have a big array of sensors, and plenty of on board computing, then many driving problems, especially in semi controlled circumstances, like open highways, are within our grasp now. The sensors and computing are expensive now - especially lidar. But that's an engineering problem, as you suggest.
The problems in automated driving are not in controlled and normal circumstances but in all the edge cases and exceptions.
Just don't forget that the competition isn't a perfect driver, but a human one. That's a much lower bar.
Re: Unreasonable Ineffectiveness of Machine Learning in Computer Systems Research
#54Earlier quoted context omitted.
Trucks driving autonomously on the interstate and being picked up by a human operator near city limits doesn't seem that far away. The trick will be to balance competition and the need to be first to market with the risk of accidents, because every negative PR hit for self-driving cars sets back the entire field politically.
This is an interesting idea. It has parallels with harbor pilots who guide ships through harbors and other hazardous waterways. Edit to add: Taking the idea a bit further, why not have remote drivers who can handle these problematic bits?
Regarding remote drivers: probably for the same reason we don't have remote harbour pilots.
Re: Unreasonable Ineffectiveness of Machine Learning in Computer Systems Research
#55Earlier quoted context omitted.
Trucks driving autonomously on the interstate and being picked up by a human operator near city limits doesn't seem that far away. The trick will be to balance competition and the need to be first to market with the risk of accidents, because every negative PR hit for self-driving cars sets back the entire field politically.
This is an interesting idea. It has parallels with harbor pilots who guide ships through harbors and other hazardous waterways. Edit to add: Taking the idea a bit further, why not have remote drivers who can handle these problematic bits?
Can't remember the name of the start-up, but there are people working on remote truck driving.
Re: Unreasonable Ineffectiveness of Machine Learning in Computer Systems Research
#56Earlier quoted context omitted.
This is an interesting idea. It has parallels with harbor pilots who guide ships through harbors and other hazardous waterways. Edit to add: Taking the idea a bit further, why not have remote drivers who can handle these problematic bits?
Regarding remote drivers: probably for the same reason we don't have remote harbour pilots.
Do you have a specific reason in mind? I have no experience in this area, so my own speculations are just that. One practical issue may be lag. Connectivity would also of course be very important.
There are historical reasons as well, but given we're discussing new technology (automated trucking), there are plenty of things that will change as a result and may not have much sway going forward.
Re: Unreasonable Ineffectiveness of Machine Learning in Computer Systems Research
#57Earlier quoted context omitted.
The problems in automated driving are not in controlled and normal circumstances but in all the edge cases and exceptions.
Just don't forget that the competition isn't a perfect driver, but a human one. That's a much lower bar.
It's not that much lower. In all the Lyft/Uber/Taxi rides I've taken, not once has the driver ever crashed or disengaged. Humans go around 100 million miles per fatality, if I recall correctly. The bar isn't perfection, I agree, but humanity is still a high hurdle (especially when we cost as little as $7/hr).
Re: Unreasonable Ineffectiveness of Machine Learning in Computer Systems Research
#58The perceptron scheme for branch prediction (full paper) [1] probably works because it uses far more memory for branch history than the usual approaches. It's not doing a better job with comparable resources.
Re: Unreasonable Ineffectiveness of Machine Learning in Computer Systems Research
#59Earlier quoted context omitted.
> but we are still decades (or more) away from full level-5 autonomy that would make drivers behind the wheel unnecessary. Do you have a citation for that? I often see this asserted, and I see many assertions the other way. Whenever I personally see self-driving cars in the wild, I'm astounded at their effectiveness on uncontrolled access roads. What makes you think controlled access roads will be much more difficult…
> none of us in the automobile or IT industries are close to achieving true Level 5 autonomy - Gill Pratt, Toyota Research Institute http://spectrum.ieee.org/cars-that-think/transportation/self... > It will be 25 years before self-driving cars take off in America - Bill Gurley, Uber investor http://www.cnbc.com/2017/04/06/bill-gurley-uber-investor-sel...
Pratt has to say that because Toyota is so far behind. He was hired to build up a self-driving group within Toyota.
Re: Unreasonable Ineffectiveness of Machine Learning in Computer Systems Research
#60> Driverless long-haul trucks are apparently just a few years away, and the main worry now is not so much the safety of these trucks but the specter of unemployment facing millions of people currently employed as truck drivers. No, no they're not. We have some lane tracking in good weather etc., but we are still decades (or more) away from full level-5 autonomy that would make drivers behind the wheel unnecessary. Bu…
> but we are still decades (or more) away from full level-5 autonomy Decades? Are you really sure? This assumption seems quite uninformed to me. The Grand Challenge was 12 years ago, from then we evolved from Level 1 to Level 3. Back then there was no data, computing power wasn't available as today, chips (&sensors) can be designed an built within a few months or even less these days for far less money. Machine Learn…
The auto industry seems to think that 2020-2021 will be the year self-driving cars become commercial products. Product plans are being made on that basis. At least freeway driving will be supported.