kristian1109

> Do you think your model's word error rate would decrease if it had access to raw feeds from towers or was trained on data from even more airports?

Yes, especially for local things like navaids, cities, etc. Our expectation is that we'll need to fine-tune for different deployments.

> Do you have any plans to make the data searchable/discoverable in real time? Something like being able to search for any audio transmissions regarding a specific flight by number, etc., available on ADS-B exchange, Flightradar, FlightAware, etc., both in text and audio form.

Definitely! This actually already exists and we're selling it to airports today.

There's lots to discuss about the most recent Potomac River crash, but I'll let that rest for now.

Your general point is 100% correct. It's not enough to only do the command parsing; you have to also compare that to radar + trajectory planning to get the full picture. That's exactly what we're working on now. Fortunately, the radar piece is much more deterministic.

Sure, feel free to email founders @ ...

One of the best parts of this job is how awesome the labeling community is. So many super qualified folks like yourself. Thank you!

But only after 1am when you're not fighting a 15 knot headwind with an A320 cleared number two.

A lot of drones these days will have ADS-B. The ones that don't probably have geo-fencing to keep them away from airports. There's also all kinds of drone detection systems based on RF emittance.

The bird problem is a whole other issue. Mostly handled by PIREP today if birds are hanging out around an approach/departure path.

Computer vision here is definitely going to be useful long term.

At an ASDE-X equipped airport like DCA, there is surface radar that the tower manager, for example, might be keeping an eye on. This is just some screen with a high-res view of everything on the ground. Then you "notice" the mistake, jump out of your seat, run over to the radio, and yell at both of them to stop in place. That's basically how it works today.

On a clear day though, it's probably just people looking out the window of the tower (maybe with binoculars) and realizing in horror that there's been a mistake. The "noticing" is just intuiting the trajectory of the two moving objects...

Not to spoil the reveal here, but ... yes. We're working on compiling more of these cases and will probably publish a website or paper when it's solid.

A lot of glass panels these days will do this in the PFD. You get your clearance via datalink from ATC, it loads everything right up, and you just keep the plane in the box or turn the autopilot on once you're in the air.

Of course, this still keeps the pilot in the loop and ideally they will notice if something seems weird.

Speaking as a pilot for a moment, I think your instincts are correct in theory but hard to actually implement.

In a critical function like control, you don't want to split a pilot's attention. You wouldn't want them to sometimes be monitoring a datalink system, but then also sometimes be listening to the radio for deviations. Even if it's less efficient 70% of the time, you reduce cognitive load by training a pilot to ALWAYS go to the radio for clearance and command.

Of course, there are edge cases these days where pilots use datalink for some clearance delivery before taxi and enroute, but you can see how these phases of flight (before you push back and after the auto pilot is on) are selected for very low competing load. In a live terminal environment, you want a pilot focused in one place for instructions.

Furthermore, you're correct that most pilot-controller communication falls largely within tight set of procedures, but deviations are common enough (weather, traffic, emergencies, hold patterns, taxi route, etc) that you find yourself on the radio regularly to sort it.

Last thing: pilots are allowed to say "unable" if they deem an instruction unsafe. I've personally had to do that many times (most common case for me is trying to comply with a vector instruction under VFR with a cloud in my way). VFR may seem like an edge case that commercial planes don't deal with, but again that's not always true in a terminal environment. Plenty of these planes fly visual approaches all the time. And if ATC is talking directly to the computer and not through the pilot, you lose the opportunity for the pilot to quickly and clearly decline an instruction.

Good callout — we're being a little vague to the public while we build out these first use cases (HN doesn't count as the "public"). Expect more detail soon!

Good callout, thanks

Exactly, this is one of our early beachheads. If we can train better pilots, the airspace system gets safer immediately.

No stress, appreciate you chiming in.

> We've accelerated past our capabilities and need to slow down.

This is a super interesting meditation. As much work as there is to be done now, the demand for air traffic is growing and power laws are concentrating it into tight airspace bubbles. It would behoove us to figure out how to make airspace more dense without compromising safety. There's lots of good economic incentive for this.

Interesting paper, thanks for sharing here. Encrypting ADS-B is a whole discussion... in my opinion, it's a good thing to have largely public location data for folks to consume and study.

What were your main takeaways from this paper?