My complaint is that it is not clear why you think what you describe is a problem. You describe that by the time the next image arrives the car traveled a certain distance. And that is correct. But you imply that it is a problem without spelling out why it is a problem in your opinion.
You seem to assume it is so trivial to understand that you don’t even need to spell out the problem. But it is not. Because i don’t know what is in your head I can’t argue with the details of it. I know that whatever you feel is a problem is not a problem in practice.
Definietly not a problem you would solve by having higher frame rate cameras. So what I’m seeing is that you are unclear on the problem and jumping at a non-solution. One which adds other complexities without actually solving anything for you. And that is a certified junior engineer behaviour.
> if this wasn't a problem, why would automotive grade cameras need to exist?
Automotive grade cameras are special in their supported temperature range (they won’t die if you leave them baking in the sun) and their physical and electrical intefaces being resilient to vibration and electrical interference. You can point your smartphone out the window of your car and see that it can record clear images.
"My complaint is that it is not clear why you think what you describe is a problem."
Well, while you read, do the math in your head and think about what OP was trying to say. The point - latency is a cold and often uncalculated bitch that will screw with reliability and integrity of the system - got across to me quite easily. I was already on that page by the 4th sentence.
> while you read, do the math in your head and think about what OP was trying to say.
I did the math in my head. Before i read their comment in fact. Did calculations both on paper and spreadsheets too. Run simulations, and field tests too. Based on what i know i do not believe that the latency imposed by the frame rate of the cameras is a limiting factor on self-driving car performance or safety. I was asking to see if they have some particular scenairo in their mind to check if maybe i’m missing something. If anything I’m much more concerned about the latency of brake actuators.
> The point - latency is a cold and often uncalculated bitch that will screw with reliability and integrity of the system - got across to me quite easily.
Ah, ok. If we are just catching the vibes, then sure. The vibes are great.
> Based on what i know i do not believe that the latency imposed by the frame rate of the cameras is a limiting factor on self-driving car performance or safety.
This is would be pretty tangential to the discussion so not sure why you are bringing it up? Did you think my post was illustrating that camera based self driving cars were infeasible? Also it appears you are mistaking framerate for latency, something I specifically warned about in my post... I don't really know what to say here.
> Did you think my post was illustrating that camera based self driving cars were infeasible?
You said this line: “The car is traveling 1.5 feet between each frame interval” As I said before, this is a true statement. What I’m asking is what do you think is the significance of this value. You wrote it. It does indeed sound like you were saying this is an impediment, or at least a complication for implementing a camera based system. But I don’t know because you didn’t spelled it out, and I can’t read your mind. Hence I asked why do you feel that number is a problem. (If you don’t think it is a problem, just an interesting fact you wanted to share of course you can say that too.)
> it appears you are mistaking framerate for latency
I’m not. If you are measuring latency from “something is happening in the world” to “robot is reacting to it” then a component of that end-to-end latency is the time delay before your sensor captures a new measurement. That delay is a function of your framerate. This delay is only part of the full end-to-end latency. It appeared to me you were concerned about this delay and that is why you calculated how much the vehicle travels during this time.
> I don't really know what to say here.
I asked specific questions. If you would care to answer them we would be ahead. When i wrote “I can’t quite understand your comment.” that is not a retorical snipe. It literally means what i wrote: I do not understand your comment and I’m asking for clarification. I even quoted the bits which I don’t understand and asked my specific questions about them.
> This is would be pretty tangential to the discussion so not sure why you are bringing it up?
Because it seemed to me you were bringing it up in your comment. Or at least that is how i could interpret those few lines in your comment I was talking about.
My complaint is that it is not clear why you think what you describe is a problem. You describe that by the time the next image arrives the car traveled a certain distance. And that is correct. But you imply that it is a problem without spelling out why it is a problem in your opinion.
You seem to assume it is so trivial to understand that you don’t even need to spell out the problem. But it is not. Because i don’t know what is in your head I can’t argue with the details of it. I know that whatever you feel is a problem is not a problem in practice.
Definietly not a problem you would solve by having higher frame rate cameras. So what I’m seeing is that you are unclear on the problem and jumping at a non-solution. One which adds other complexities without actually solving anything for you. And that is a certified junior engineer behaviour.
> if this wasn't a problem, why would automotive grade cameras need to exist?
Automotive grade cameras are special in their supported temperature range (they won’t die if you leave them baking in the sun) and their physical and electrical intefaces being resilient to vibration and electrical interference. You can point your smartphone out the window of your car and see that it can record clear images.