I don’t need self driving cars that can navigate alleys in Florence, Italy and also parkways in New England. Here is what we really need: put transponders into the roadway on freeways and use those for navigation and lane positioning. Then you would be responsible for getting onto the freeway and getting off the exit but can take a nap between. This would be something that would be do e by the DOT, supported by all car makers, and benefit everyone. LIDAR could be used for obstacle detection but not for navigation. And whoever figures out how to do the transponders and land a government contract and get at least one major car manufacturer on board would make bank.

▲

hedora 5 days ago | parent | next [-]

We live in an area with sort of challenging roads, and I strongly disagree.

There’s an increasing number of drivers that can barely drive on the freeways. When they hit our area they cannot even stay on their side of the road, slow down for blind curves (when they’re on the wrong side of the road!), maintain 50% the normal speed of other drivers, etc. I won’t order uber or lyft anymore because I inevitably get one of these people as my driver (and then watch them struggle on straight stretches of freeway).

Imagine how much worse this will get when they start exclusively using lane keeping on easy roads. It’ll go from “oh my god I have to work the round wheel thingy and the foot levers at the same time!” to “I’ve never steered this car at speeds above 11”.

I’d much rather self driving focused on driving safely on challenging roads so that these people don’t immediately flip their cars (not an exaggeration; this is a regular occurrence!) when the driver assistance disables itself on our residential street.

I don’t think addressing this use case is particularly hard (basically no pedestrians, there’s a double yellow line, the computer should be able to compute stopping distance and visibility distance around blind curves, typical speeds are 25mph, suicidal deer aren’t going to be the computer’s fault anyway), but there’s not much money in it. However, if you can’t drive our road, you certainly cannot handle unexpected stuff in the city.

▲

IgorPartola 5 days ago | parent [-]

You describe it as challenging but it sounds like realistically it is just badly designed roads. But fixing that aside, nothing really stops you from outfitting secondary roads with transponders in principle. In practice, it is easier to start with freeways because (a) they are much more uniform, (b) the impact of an accident at freeways speeds is much more deadly, (c) no pedestrians, bicycles, etc., and (d) the federal government has control over the freeways (it is a complex relationship but ultimately the feds have a say) which means they can mandate installing the transponders and pay for it. Once the system functions there it can be expanded until every driveway and parking spot is outlined.

	▲	hedora 4 days ago \| parent [-]
		They’re badly designed (outskirts of Silicon Valley). So is the electricity and internet, so the transponders placed in shady spots would need something like a 30 day battery backup and network other than wired, cell, wisp or starlink. Vision based systems would be more than adequate. Lidar or (god forbid) ultrasonic chirps would easily lead to superhuman safety and speeds. I’m skeptical of transponder or network based systems. What happens during a natural disaster? Do the 10% of cars that lack drivers or steering wheels just stop and block the evacuation routes? That’d kill a lot of people in very graphic / high profile ways.

▲

heeton 5 days ago | parent | prev | next [-]

We already have transponders on freeways. They’re technically passive reflectors, but they reflect a high proportion of incident EM waves, in the visible spectrum, and exist between lanes on every major road in the US. Also known as white paint.

▲

gilbetron 5 days ago | parent | prev | next [-]

Following roads and lane markers and signs and signals is the "easy" part of autonomous driving. You could do everything you say and it wouldn't result in something that is any better than the current state of the art. Dealing with others on the road is the main problem (weather comes in close second). Your solution solves nothing, I'm afraid.

▲

randunel 5 days ago | parent | prev [-]

How would you know which signals to trust and which to ignore?

	▲	uoaei 5 days ago \| parent \| next [-]
		Physics prevents detected objects from jumping unrealistically. Current systems seem not to account for that at all, reacting to objects which appear and disappear spontaneously. Sensor fusion is exactly the solution to this: use a variety of sensors as input to reliably identify actual obstacles. To fake all the sensors at once you'd need to fake vision, lidar, and transponder locations simultaneously.
	▲	jijijijij 5 days ago \| parent \| prev [-]
		Blockchain. Just kidding. Wait, no! Please. No! How do I delete this???