Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control • Hacker News Board

Re: Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control

#101

Post by kristian1109 » Wed, Mar 05, 2025, 6:57 AM UTC

pj_mukh wrote: post #100

kristian1109 wrote: post #95

Earlier quoted context omitted.

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…

Jesus. On top of your analysis of commands that might flag conflicting commands, shouldn't we also be analyzing the radar to make sure there aren't any obviously conflicting paths? I saw your comment about pilot intentionality being the major time-saver but in a situation like the Potomac River crash, the intentionality and knowledge may have been a unintentional headfake for a system like yours i.e "Yes I see the CR…

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.

Re: Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control

#102

Post by raphting » Wed, Mar 05, 2025, 9:05 AM UTC

I worked a few years for German air traffic control and I own a PPL.

From a non-commercial viewpoint, I like to see when people get enthusiastic to make airspace and flying safer. From a commercial perspective, I agree with others writing here that going into a highly regulated market such as air traffic, is very hard, and I can tell you why I think so.

For example German air traffic control (DFS) publishes tools which are not directly ment for ATCOS https://stanlytrack3.dfs.de/st3/STANLY_Track3.html , so they are already covering part of this market. Then there are companies already specialised in tapping into the open data of the skies https://www.skysquitter.com/en/home-2/ (Or check https://droniq.de which is specialised in integrating drones into airspace). They are all either governmental or subsidiaries, or not directly involved in air traffic control itself.

I once built a 3D airspace app which I thought could become a commercial product, but I found it is too hard to compete with companies like DFS or Boeing (ForeFlight) and others. (I published the app for free to play around with: https://raphting.dev/confident/)

Saying that, I think I thought a lot about commercialisation of airspace products and my conclusion is that most countries have a good reason to leave air traffic control governmentally owned and continue gatekeeping for new entries. These gates are very well protected, and if it is only with high fees you need to pay to even gain access to data (like when I purchased airspace data from Eurocontrol for the 3D App).

Focusing on training or "post-ops", what I think you plan to do, is probably the more viable direction.

Re: Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control

#103

Post by Mikhail_K » Wed, Mar 05, 2025, 10:59 AM UTC

ryandrake wrote: post #21

> The latest system transcribes the VHF control audio at about ~1.1% WER (Word Error Rate), down from a previous record of ~9%. I'd be curious about what happens when the ASR fails. This is not the place to guess or AI-hallucinate. As a pilot, I can always ask "Say Again" over the radio if I didn't understand. ASR can't do that. Also, it would be pretty annoying if my readback was correct, but the system misunderstoo…

> I'd be curious about what happens when the ASR fails.

When, not if. The "artificial intelligence" as it is presently understood is statistical in nature. To rely on it for air traffic control seems quite irresponsible.

Re: Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control

#104

Post by btreecat » Wed, Mar 05, 2025, 12:23 PM UTC

Do you believe the FAA should mandate ADSB for all GA regardless of airspace, and unify on a single global frequency rather than dual freq UAT+ADSB?

Re: Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control

#105

Post by VBprogrammer » Wed, Mar 05, 2025, 1:20 PM UTC

kristian1109 wrote: post #35

Animats wrote: post #32

> To do this, we’ve developed Yeager, an ensemble of models including state of the art speech-to-text that can understand ATC audio. Listening on multiple channels might help at busier airports. Ground, ramp, approach, departure, and enroute are all on different channels. Military aircraft have their own system. (That may have contributed to the DCA accident.) Something like this was proposed in the late 1940s. The F…

It's been interesting to see that a product as simple as combining data from multiple frequencies at once has been really compelling to folks. Can't tell you the number of times we've heard "wait, can you compile ground, tower, and approach in one place?"... "... yes, of course." Military aircraft are typically equipped with UHF radios (in addition to civilian VHF). Many of the same systems apply, just a different RF…

> I can't imagine what would've happened if we adopted block signaling for ATC ...

You don't have to imagine. We already do in many places. The North Atlantic Tracks are essentially exactly that. Aircraft give position reports and estimates, those positions reports are used to decide whether an aircraft can climb though which levels etc.

It's also used extensively in an IFR non-radar environments. Exactly why aircraft have to cancel IFR at uncontrolled airfields in the US or under a procedural ATC service in the UK. You hear it a lot around the Caribbean and Bahamas too.

Re: Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control

#106

Post by ryry » Wed, Mar 05, 2025, 2:44 PM UTC

this is amazing!

I'm actually working on a similar ATC transcription project, but more along the lines of education / entertainment for non-pilots. I'm gonna be posting a YT video about it soon, but would love to chat if you guys are open to it!

Re: Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control

#107

Post by westurner » Wed, Mar 05, 2025, 2:45 PM UTC

kristian1109 wrote: post #96

westurner wrote: post #80

Can any aircraft navigation system plot drone Remote ID beacons on a map? How sensitive of a sensor array is necessary to trilaterate Remote ID signals and birds for aircraft collision avoidance? A Multispectral sensor array (standard) would probably be most robust. From https://news.ycombinator.com/item?id=40276191 : > Are there autopilot systems that do any sort of drone, bird, or other aerial object avoidance?

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.

FWIU geo-fencing was recently removed from one brand of drones.

Thermal: motors, chips, heatsinks, and batteries are warm but the air is colder around propellers; RF: motor RF, circuit RF, battery RF, control channel RF, video channel RF, RF from federally required Remote ID or ADS-B beacons, gravitational waves

Aircraft have less time to recover from e.g. engine and windshield failure at takeoff and landing at airports; so all drones at airports must be authorized by ATC Air Traffic Control: it is criminally illegal to fly a drone at the airport without authorization because it endangers others.

Tagging a bird on the 'dashcam'+radar+sensors feed could create a PIREP:

PIREP: Pilot's Report: https://en.wikipedia.org/wiki/Pilot_report

Looks like "birds" could be coded as /SK sky cover, /WX weather and visiblity, or /RM remarks with the existing system described on wikipedia.

Prometheus (originally developed by SoundCloud) does pull-style metrics: each monitored server hosts over HTTP(S) a document in binary prometheus format that the centralized monitoring service pulls from whenever they get around to it. This avoids swamping (or DOS'ing) the centralized monitoring service which must scale to the number of incoming reports in a push-style monitoring system.

All metrics for the service are included in the one (1) prometheus document, which prevents requests for monitoring data from exhausting the resources of the monitored server. It is up to the implementation to determine whether to fill with nulls if sensor data is unavailable, or to for example fill forward with the previous value if sensor data is unavailable for one metric.

Solutions for birds around runways and in flight paths and around wind turbines:

- Lights

- Sounds: human audible, ultrasonic

- Thuds: birds take flight when the ground shakes

- Eyes: Paint large eyes on signs by the runways

Re: Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control

#108

Post by westurner » Wed, Mar 05, 2025, 3:03 PM UTC

westurner wrote: post #107

kristian1109 wrote: post #96

Earlier quoted context omitted.

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.

FWIU geo-fencing was recently removed from one brand of drones. Thermal: motors, chips, heatsinks, and batteries are warm but the air is colder around propellers; RF: motor RF, circuit RF, battery RF, control channel RF, video channel RF, RF from federally required Remote ID or ADS-B beacons, gravitational waves Aircraft have less time to recover from e.g. engine and windshield failure at takeoff and landing at airpo…

> Sounds and Thuds [that scare birds away]

In "Glass Antenna Turns windows into 5G Base Stations" https://news.ycombinator.com/item?id=41592848 or a post linked thereunder, I mentioned ancient stone lingams on stone pedestals which apparently scare birds away from temples when they're turned.

/? praveen mohan lingam: https://www.youtube.com/results?search_query=praveen+mohan+l...

Are some ancient stone lingams also piezoelectric voice transducer transmitters, given water over copper or gold between the lingam and pedestal and given the original shape of the stones? Also, stories of crystals mounted on pyramids and towers.

Could rotating large stones against stone scare birds away from runways?

Re: Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control

#109

Post by fallingmeat » Wed, Mar 05, 2025, 3:33 PM UTC

RockyMcNuts wrote: post #48

Maybe the future is structured electronic messaging with the humans in the loop. Like, check in with the controller but most messages are sent electronically and acknowledged manually. I have your clearance, advise when ready to copy, then you write everything down on kneeboard with a pencil and then manually put it in the navigation system, is a little archaic. certainly speech to text is a useful transition but in…

also requires fairly expensive equipment (FMS with FANS support)

Re: Launch HN: Enhanced Radar (YC W25) – A safety net for air traffic control

#110

Post by RockyMcNuts » Wed, Mar 05, 2025, 4:26 PM UTC

kristian1109 wrote: post #60

RockyMcNuts wrote: post #48

Maybe the future is structured electronic messaging with the humans in the loop. Like, check in with the controller but most messages are sent electronically and acknowledged manually. I have your clearance, advise when ready to copy, then you write everything down on kneeboard with a pencil and then manually put it in the navigation system, is a little archaic. certainly speech to text is a useful transition but in…

The problem with datalink systems is they are poor substitutes for immediate control & confirmation. My co-founder Eric wrote a short piece about this: https://www.ericbutton.co/p/speech . This is why they are mainly relegated to low-urgency en-route & clearance delivery.

interesting! have PP but haven't flown really last couple of decades.

I feel like, with proper UX in the cockpit and on the controller console, making it easy to send/acknowledge the clearance, and intrusively demanding immediate acknowledgment for important messages, with the controller able to talk to the pilot if it isn't immediately acknowledged, structured messages would save time, be more accurate, allow automated checks, i.e. be a superior substitute.

UX needs a ton of work and human factors validation, and would take 20 years to implement. But if you were starting from a blank slate it seems like the way to go!