Comment by nradov

3 years ago

And this is why fully autonomous flight control systems won't be certified for airliners in our lifetimes. While autonomous systems are capable of taking off, navigating to a destination, and landing they are largely incapable of handling major emergencies. It's impossible for engineers to foresee every possible failure mode and program for it.

15 comments

nradov

Reply
cesarb  3 years ago

> It's impossible for engineers to foresee every possible failure mode and program for it.

Playing devil's advocate: you don't have to. It just has to be better than a pair of experienced airplane pilots working together. Which is still very hard, and there's still a good chance we won't see it in our lifetimes, but at least it's not impossible.

  • lovemenot  3 years ago

    Also, let's not completely discount remote pilots

    • nradov  3 years ago

      Let's completely discount remote pilots. There is no technology on the horizon which would solve the network latency or sensor fidelity problems that prevent remote piloting from being adequate for handling in-flight emergencies.

      6 replies →

rgmerk  3 years ago

It’s worth pointing out that there are also plenty of airliner crashes that are attributed to pilot error.

  • kergonath  3 years ago

    Plenty compared to the set of airliner crashes, which is very small. There are also a lot of near misses that don’t turn into crashes precisely because of pilots being good at their jobs.

    For AI to replace pilots, you don’t need to prove that sometimes humans fuck up. You need to demonstrate that AI would fuck up less often and in a more acceptable way. This requires looking at the big picture, not only bad cases.