> LiDAR I've worked with in fact could suffer 'sun poisoning' if the sun shone directly into the receiver.
Notably, the optical guidance systems in all existing vehicles are subject to exactly the same exploit.
This is one of the criticisms (of self-driving cars, and with LIDAR vs. imaging specifically) I just simply don't get. You can blind a real driver much more easily and less recoverably than you can any sensor.
> This is one of the criticisms (of self-driving cars, and with LIDAR vs. imaging specifically) I just simply don't get. You can blind a real driver much more easily and less recoverably than you can any sensor.
Human optics is actually really, really good. We can adapt very well to having a light source as bright as the sun in the same field of view as shaded and make at details in both very bright and very dark regions. Optical sensors can't do that--you either wash out the bright stuff and see the shaded detail, or you darken the shade and make the bright stuff visible.
Drivers deal with having the sun shining in their eye using sunshades, visors and a whole raft of movement tricks to avoid having their retinas burned out. A passive sensor (which is where we're headed) has no protection at all, it just sits where while it is being fried.
It's true that the sun low near the horizon at sunup or sundown, especially on clear winter days causes accidents but I'm not all that sure whether or not LIDAR will do better here than humans. Time will tell.
What if you put an intensity sensor next to the LIDAR sensor and came up with some solution to position the LIDAR like sunshades, visors, and 'movement tricks.'
Notably, the optical guidance systems in all existing vehicles are subject to exactly the same exploit.
This is one of the criticisms (of self-driving cars, and with LIDAR vs. imaging specifically) I just simply don't get. You can blind a real driver much more easily and less recoverably than you can any sensor.