alt Hacker NewsI used to work in perception for autonomous aerial vehicles and horizontal wires were the hardest common object to avoid. Traditional stereo won't help you localize them -- wires are thin so even mere detection can be hard, and one portion of a wire looks much like another so feature matching fails resulting in bad or no depth estimates -- and LIDAR sacrifices resolution for weight and power consumption (which both have to be optimizied for drones). It's been years since I've worked in this field, and Amazon has many smart people thinking about it but I'm not surprised it's still a difficult problem.
Replies
Ah yeah I came up with the solution to that one. It's 'don't fly drones over our heads' approach. Also the 'upgrade the fragile infrastructure so a light breeze doesn't take out millions of people's power.'
It's very simple: don't fly there
there are very little aerial lines few meters highers and ones that exist can be probably spotted from satellite images and planned around.
Especially if delivery area is limited, they could just map them out of the routes.
> horizontal wires were the hardest common object to avoid... Traditional stereo won't help you localize them
This makes a lot of sense. I wonder if it wouldn't be better for autonomous vision to use three cameras instead of two for better spatial reasoning.. maybe in a triangle pattern?
Helicopter pilots have trouble with them as well.
Definitely tough. mmWave radar is useful for this use case; I know Amazon were testing it on earlier drones but I'm not sure if they still use it.
> Traditional stereo won't help you localize them
Wouldn't making a quick circuit around the house before landing allow wires to be observed from multiple angles be enough?
Cables don't move often. Why not simply have a map of all of them?
Google sell maps of things like this from street view data.
It’s really hard for people too. The advice I got for landing in a field was to assume that every pole you saw had wires going to every other pole. Which is reasonable enough for that scenario, but not workable for continual low altitude flying in a built up area.
> Traditional stereo won't help you localize them [...] and LIDAR sacrifices resolution for weight and power consumption
I wonder if a more mechanical solution wouldn't help:
Whiskers, like on a cat. A long enough set of thin lightweight whiskers could touch the wire before the propellers do, giving time for the drone to stop and change course. Essentially, giving the drone a sense of touch.