[SapporoChris]

I believe traffic lights currently use three bulbs, red, yellow and green. Even without color a computer system can easily determine when each light is lit.

If there are single bulbs displaying red, green and yellow please give clear examples.

[bluGill]

Flashing lights over rural intersections often do that. There is only one color there (yellow or red), but position is not a signal

[dham]

Have you driven in America? We have the craziest lights you've ever seen. And that's just in my state

[dzhiurgis]

How about turn signal vs brake lights?

[JumpCrisscross]

> How about turn signal vs brake lights?

Potentially as extraneous as range to a surface that a camera can’t tell apart from background.

More to the point, everyone but Tesla is doing cameras plus Lidar. It’s increasingly looking like the correct bet.

[dzhiurgis]

> doing cameras plus Lidar

At what proportion? Is it mostly lidar or mostly cameras? Or 50/50?

> Potentially as extraneous as range to a surface that a camera can’t tell apart from background.

I guess yeah for backside of the car you'd probably better off measuring actual actions.

How about when you come 4 way stop. LIDAR is useless as it wouldn't recognize anyones turn signals.

[lkois]

What do you mean by proportion? They are different data sources, and their usage is determined by system design.

eg A driving decision system needs to know object distances AND traffic light colours. It doesn't particularly need to know the source of either. You could have a camera-only system that accurately determines colour and fuzzy-determines distance. Or you could have a LIDAR-only system that accurately determines distance and fuzzy-determines colour.

Or you use both, get accurate LIDAR-distance and accurate camera-colour and skip all the fuzzy-determination steps. Or keep the fuzzy stuff and build a layer of measurement-agreement for redundancy.

So then the question becomes, what's your proportion when deciding whether to stop at a traffic light? Is it mostly light colour or mostly distance to other objects? Or 50/50?

I'd say it's 100/100.

[dzhiurgis]

Sounds like a solved problem and you can buy a solution with a perfect accuracy?

[ben_w]

I don't read the previous comment as either "you can buy" nor "perfect accuracy".

Like them, I don't understand what you're asking by "proportion". Bits/second? Sensor modules/vehicle? Features detected by the AI?

[Sohcahtoa82]

Is there a point you're trying to make?

Because it really feels like you're just JAQing off, either to come to some "gotcha" moment or a pseudo-intellectual exercise. In either case, the questions feel bad faith.

[lkois]

Who said that?

[JumpCrisscross]

> At what proportion? Is it mostly lidar or mostly cameras? Or 50/50?

What proportion of your vision is rods or cones? Depends on the context. You can do without one. But it’s better with both.

> How about when you come 4 way stop. LIDAR is useless as it wouldn't recognize anyones turn signals

Bad example. 99% of a 4-way stop is remembering who moved last, who moves next by custom and who may jump the line. What someone is indicating is, depending on where you are, between mildly helpful and useless.