Hacker News Reader

Comment by Dolimiter | Hacker News Reader

The technology is not nearly ready. Not in a city. It's like flying drone delivery. Easy to demonstrate in a single controlled setting, but nearly impossible to actually implement in the real world.

View on HN

It's not really like flying drone delivery. Flying drone delivery is far simpler and far closer than general use self-driving automobiles.

Actually landing UAVs is far harder than automatically parking a car. The driving vs flying after take off is what is easier. Landing and take off.. nope.

Note that drone could mean a car in this case. UAV being an unmanned aerial vehicule.

With a modest infrastructure of marked landing pads on roofs, I think UAV landings are easier than automated car parking. If you're expecting delivery UAVs to fly under the tree line along sidewalks and yards to land directly on a residential porch, then yes, that's extremely difficult. But I highly doubt that this is a remotely feasible plan within a decade or so.

It's hard for me to even imagine how a self-driving car could manage somewhere like large swaths of Manhattan where a certain amount of, umm, aggression is needed to make any forward progress. Though it will likely happen some day (probably multiple decades from now).

As it is, I'd even settle for voice control on my phone that could reliably understand me.

> a certain amount of, umm, aggression is needed to make any forward progress

They added a slight "aggression" back in 2011, if other cars aren't letting it out it starts pushing forwards a bit:

> Sometimes, however, the car has to be more "aggressive." When going through a four-way intersection, for example, it yields to other vehicles based on road rules; but if other cars don't reciprocate, it advances a bit to show to the other drivers its intention. Without programming that kind of behavior, Urmson said, it would be impossible for the robot car to drive in the real world.

http://spectrum.ieee.org/automaton/robotics/artificial-intel...

I really don't understand why people think small behavioural differences like that require decades of work. Things that humans find difficult and stressful are likely to be the things that are significantly easier when you have a reaction time measured in milliseconds and full 360 degree vision.

I hope you're right but the very uneven progress of AI generally--especially when it involves real world interfaces--makes me skeptical. As I wrote elsewhere, even voice recognition is very much still a mixed bag.

But voice recognition is something we take many years to learn, even when are brains are highly plastic. I find it hard to understand people when they speak often. We disambiguate heavily based on context and expectation, very complex issues.

Oh, I fully agree. The fact that it's been the subject of so much research and remains only very incompletely solved demonstrates just how difficult a problem it is. I'm just saying that navigating a potentially dangerous machine through a physical world populated with erratic human beings is also very complex and difficult--albeit probably far less so in some contexts (limited access highways in good weather) than others (Manhattan, Boston).

Reply on news.ycombinator.com