I don’t oppose public transport at all and the US has a lot to improve in this area. But e.g. East Asia and Europe have plenty of rails, and people still want to drive their own cars, and there are still an unbelievable number of accidents.
We should require that every traffic participant gets a sensor, and connect all in a (local) network, instead of only relying on machine learning and its vulnerability to the unpredictable situations where accidents occur. Pure autonomous self driving won’t be the final answer here.
Please correct me if I’m not up to date here, but to my last knowledge self driving car machine learning lacks the most important data, that of dangerous situations. I’m surprised that Uber considered it ready for roll out.
Germany here, we don't actually have "plenty" of rails for public transport, we love our Autobahn (no general speed limit!) and our cars, yet our vehicle fatality rates are among the lowest in the world (half that of the US).
The reason that fatalities are 10x higher in Asia is that people drive (and walk!) like lunatics and vehicle fatalities are just shrugged off.
Just be more orderly is basically what I am saying. Also eat more sauerkraut - it's healthy!
I’m not sure who is downvoting this, but there are 1.74 people killed per billion KM on the Autobahn. This compares with 1.16 in the U.K. and 3.38 in the U.S.
Having driven about 2000KM on the Autobahn as a tourist the lane etiquette on the Autobahn is the best I’ve ever seen, and I’ve driven through the U.S. (both East and West coast) and much of Europe. It’s no surprise to me that the Germans can drive on de-restricted roads and have the one of the lowest number of deaths (HIGHWAYS ONLY) in the world.
We can’t even standardize on a format across browsers without severe inconsistencies and bugs, yet you expect vehicles of all types and pedestrians to cooperate in a network? That’s not even taking into account the outliers who refuse to conform (or worse, those who try to hack it).
Every car has plenty of communication and localization systems today. Nearly every pedestrian carries an electronic device with potential for exact localization. It makes no sense to not use that data, and solely rely on still-not-perfect computer vision. The optimal system will necessarily be a combination of both.
As for standardisation, maybe realizing what an enormous number of fatal and many more forever life-altering accidents we currently consider normal will finally get people off their backsides. I wish somebody would start a media project revealing how insane the current situation is..
Wanting/needing something to work and it actually working is two entirely different things. Again, refer to my point about browsers. Happy to give a lot more examples if that's what is necessary.
We should require that every traffic participant gets a sensor, and connect all in a (local) network, instead of only relying on machine learning and its vulnerability to the unpredictable situations where accidents occur. Pure autonomous self driving won’t be the final answer here.
Please correct me if I’m not up to date here, but to my last knowledge self driving car machine learning lacks the most important data, that of dangerous situations. I’m surprised that Uber considered it ready for roll out.