Hacker News new | past | comments | ask | show | jobs | submit login

I'd say that using "base stations" or "turrets" like in airports wouldn't make a autonomous-self-driving technology.

I guess I prefer a fully independent car capable of driving anywhere without the help 3rd party devices.

Ok maybe just gps.




I think the more important goal than being completely autonomous is killing and maiming as few people as possible. Cars depend on a lot of immobile "base stations" like gas and charging stations, traffic lights, drive through fast food restaurants, and the roads themselves. Until cars can refine their own petroleum or generate their own electricity, replicate their own fast food, and pave their own roads [1], they're never going to be purely autonomous.

My question is how much do a bunch of cars an intersection all using LIDAR at the same time interfere with each other? Would it make sense for them to wirelessly share their models, and share an even better model made possible by high resolution LIDAR placed on poles like street lights? Then approaching cars could see around corners, and know about otherwise invisible oncoming traffic.

I'm not suggesting that every intersection and long stretch of road through the desert should be festooned with LIDAR base stations. But how about starting with every busy intersection on Market street, for example?

[1] https://www.youtube.com/watch?v=8hG7-AQfbjE


Wait you don't want your car to send all the inputs to Amazon or Googlefor processing in their data center, and just her responses back? "We see you are driving by a McDonald's. Your route has been updated to include a burger and fries!"




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: