Hacker News Reader

Comment by sbilstein | Hacker News Reader

Oof some engineer is working on machine-learning to deal with the knockback of shooting a gun from a drone. It's probably an interesting as hell problem, enough to distract someone from the fact that they'll be enabling cheap robots to shoot people.

It is so sad that we, humans in general, devote so many resources to devising bigger and better means of violence.

View on HN

Bigger and better actually worked pretty well w.r.t. MAD. Now we are developing smaller and better, which seems almost more dangerous since we're already using drones more flippantly than conventional military arms.

It is very easy to work on these tools without even realizing it. Let us say that you are developing a video processing algorithm and publish the code on github. The developers of missile software can and will use it. At some point, they may ask you for consulting/support in exchange for a large amount of money and you will say yes, and never realize who they were. I'm not saying that this has happened several times to my lab.

Maybe to handle knockback you could allow recoiling rotation around one axis and have the rotors automatically anticipate the force on fire.

In the video the drone self-destructs by exploding and producing shrapnel, I doubt knockback is a problem.

Why do you need machine learning to "deal with the knockback of shooting a gun from a drone"?

‘cause people don’t understand this is a solvable problem any other way and of course ML can solve any problem you point it at.

well you need machine learning to coordinate these robots and they need to take into the effect of this robot shaking around a whole bunch.

Reply on news.ycombinator.com