Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I'm really of the belief, based purely on imagination, that a lot of the spending and research went into being able to make the F-35 autonomous with a switch.

Drone warfare really is the next step and having full jets that appear to be piloted but are actually completely autonomous would put the US ahead by decades.



Starting with a manned aircraft is a terrible way to build an unmanned one. A good fraction of the weight is there to provide life support and safety for the pilot. The canopy is a huge compromise between aerodynamics and visibility. And for manned aircraft, it's worth spending 10x more to get a slightly lower failure rate, because pilots are so valuable. For unmanned aircraft, the reliability calculations are all different.


But it gives access to thousands of hours of training data for that particular aircraft across a range of different situations, and it allows you to test that ML model in real situations.

Moving to something lighter or more aerodynamic becomes a lot easier after that. If you look at the Boeing Airpower/Loyal Wingman UAV, it looks like its based on this concept quite closely.


That doesn't seem to be the route the XQ-58 is going, though. [0] It's an attritable stealthy missile/bomb truck - and at a projected unit cost of $2-3 million, they'd be cheaper than some US air-to-air missiles.

0: https://en.wikipedia.org/wiki/Kratos_XQ-58_Valkyrie


A remotely controlled UAV would provide more hours of training data for less money.


I’d like to question that premise. Why is having a full sized, expensive aircraft remote controlled be “decades ahead”?


It doesn't force others to enter into a public arms race with you. It's something you can do completely under the radar indefinitely. Of course the per unit cost of aircrafts will go down when you don't need to account for the safety features, and performance will go up dramatically, and the enemy will never know that there is nobody in the cockpit.


I highly doubt that. A fully autonomous air force would make your entire air force susceptible to hacking and thus your enemy could turn your entire fleet back against you with a single hack. That is an insanely huge risk.

As for remotely controlled drones, that suffers from jamming.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: